arXiv:2606.00756v1 Announce Type: new Abstract: Deploying lightweight Large Language Model (LLM) agents on edge servers can reduce latency and move agentic services closer to users, but resource-con…

arXiv:2606.00756v1 Announce Type: new Abstract: Deploying lightweight Large Language Model (LLM) agents on edge servers can reduce latency and move agentic services closer to users, but resource-constrained edge models often struggle with long-horizon tasks that require persistent memory, subgoal tracking, and reflection. Fine-tuning edge models after deployment is costly and difficult to scale across heterogeneous nodes, while purely local memory leaves agents with isolated experience and growing prompt context. We propose \textsc{CoMIC}, a parameter-update-free cloud-edge framework for Collaborative Memory and Insights Circulation. \textsc{CoMIC} follows a \textit{Centralized Reflection, Decentralized Execution} design: edge agents execute locally using subgoal-oriented hierarchical memory and selective re-expansion of relevant histories, while a cloud-side LLM critic asynchronously evaluates completed trajectories, filters reusable experience, and aggregates cross-agent guidance keyed by semantic subgoal identifiers. Across five long-horizon agent tasks spanning symbolic planning and text interaction, \textsc{CoMIC} improves progress rate and action grounding for weak edge agents and yields task-dependent success-rate gains without updating model parameters.

arXiv:2606.00732v1 Announce Type: new Abstract: Learning long-range non-stationary temporal patterns remains a core challenge for modern sequence models, particularly in strict streaming settings. I…

arXiv:2606.00732v1 Announce Type: new Abstract: Learning long-range non-stationary temporal patterns remains a core challenge for modern sequence models, particularly in strict streaming settings. In these settings, data arrive sequentially and must be processed in a single pass without simultaneously revisiting past observations. Standard architectures, including recurrent neural networks and transformers, are constrained by either truncated backpropagation through time horizon or explicit input window length for long range credit assignment. To address these limitations, we propose SHARP (Sleep-based Hierarchical Accelerated Replay), a framework that decomposes temporal learning into two complementary components: a memory module that accumulates a structured history of past inputs, and a pattern-recognition module that operates over this memory. This separation enables resource- and compute-efficient adaptation to non-stationary dynamics by eliminating the need for backpropagation through time across many steps for long-range credit assignment. Inspired by the accelerated replay observed in rodents during slow-wave sleep, SHARP incorporates offline (sleep) phases in which temporally structured memory traces are replayed in an accelerated form and integrated into higher-level memory representations, improving long-range context retention. Through controlled simulations and ablation studies, we characterize the key properties of the proposed framework. In benchmark datasets such as text8 and PG-19, we demonstrate that SHARP improves over recurrent baselines by retaining next-token predictive performance on previously seen data while continuing to learn from the current stream and generalizing to future unseen data. These gains are enabled by its hierarchical structure, which yields an exponentially increasing effective temporal context with only linear-time computational cost.

arXiv:2606.00729v1 Announce Type: new Abstract: Artificial Intelligence is often discussed in France in terms of investment, compute capacity, regulation, employment, sovereignty, and education. The…

arXiv:2606.00729v1 Announce Type: new Abstract: Artificial Intelligence is often discussed in France in terms of investment, compute capacity, regulation, employment, sovereignty, and education. These dimensions are usually treated separately. This viewpoint paper proposes a unified interpretation: France should be understood as a \emph{national AI learning system}. Building on Human-Centered Learning Mechanics (HCLM), recently formulated as a dynamical framework for entropy-regulated representation learning, we interpret national AI development as a controlled balance between information injection and entropy dissipation. Information injection corresponds to compute, data, talent, research, capital, industrial deployment, and institutional experimentation. Entropy dissipation corresponds to organizational complexity, coordination frictions, energy constraints, regulatory uncertainty, talent mobility pressures, and opportunities to strengthen industrial absorption. The central claim is that AI sovereignty does not emerge from scale alone but from a country's capacity to regulate its own information dynamics. This paper connects HCLM with neural scaling laws, endogenous growth theory, creative destruction, and game theory. It argues that the French AI debate should move beyond the binary opposition between techno-optimism and regulation-first caution. A competitive and human-centered AI strategy requires a controlled regime in which information injection grows faster than institutional dissipation, while avoiding unstable, unequal, or energy-intensive expansion. We provide a mathematical model, measurable policy indicators, game-theoretic propositions, illustrative simulations of national AI regimes, and concrete policy implications for France. The proposed viewpoint reframes AI policy as the governance of an open, strategic, non-equilibrium learning system.

arXiv:2606.00726v1 Announce Type: new Abstract: Strong reasoning depends not only on model knowledge but also on how effectively cognitive behaviors are deployed during generation. Existing methods …

arXiv:2606.00726v1 Announce Type: new Abstract: Strong reasoning depends not only on model knowledge but also on how effectively cognitive behaviors are deployed during generation. Existing methods often rely on explicit behavior-level control, making them insufficiently adaptive when failures and required corrections vary across reasoning states, tasks, and models. To this end, we propose Latent Reward Steering (LRS), an adaptive inference-time framework that promotes cognitive behaviors by optimizing the sparse-autoencoder (SAE) latent states that implicitly carry them. Rather than relying on predefined cognitive behaviors or steering directions derived from them, LRS trains a latent reward model on reasoning traces by final answer correctness to estimate the quality of intermediate latent states. During inference, reward gradients provide state-specific correction directions for fragile latent states, while a reward and confidence gate restricts intervention to states the reward signal flags as fragile. Experiments on multiple reasoning LLM backbones and benchmarks show that \ours consistently improves performance over various baselines, and post-hoc analyses further indicate that \ours implicitly promotes good cognitive behaviors that fix the original reasoning errors. Code is available at: https://github.com/jiakanglee/Latent-Reward-Steering.

arXiv:2606.00718v1 Announce Type: new Abstract: While Large Language Models (LLMs) have recently shown promise in Automated Heuristic Design (AHD), existing methods typically generate and evolve heu…

arXiv:2606.00718v1 Announce Type: new Abstract: While Large Language Models (LLMs) have recently shown promise in Automated Heuristic Design (AHD), existing methods typically generate and evolve heuristics as a single operator or search strategy, limiting their ability to model strong coupling among multiple decision substructures in problems such as the Traveling Thief Problem (TTP) and the Traveling Purchaser Problem (TPP). In this work, we propose CoEvo-AHD, an LLM-driven dual-population co-evolutionary framework for automated heuristic design in coupled combinatorial optimization. Unlike prior methods that evolve individual heuristics in isolation, CoEvo-AHD leverages LLMs to co-evolve two closely related operator populations. A cooperative evaluation mechanism explicitly captures interactions between route and selection operators, while pairwise scoring and synergistic joint crossover help discover complementary operator logic for joint improvement across coupled decision subspaces. We further design a tool-invocation environment library that encapsulates frequently used core operations, such as local-search delta computation, into callable functions, enabling LLM-generated operators to use standardized interfaces instead of reimplementing inefficient and error-prone problem-specific loops. Experiments on TTP and TPP show that CoEvo-AHD automatically discovers cooperative heuristic combinations and achieves competitive solution quality against traditional heuristics.

arXiv:2606.00708v1 Announce Type: new Abstract: Automated data science is a structured model-selection problem. A solution must choose data transformations, feature representations, architecture, tr…

arXiv:2606.00708v1 Announce Type: new Abstract: Automated data science is a structured model-selection problem. A solution must choose data transformations, feature representations, architecture, training procedure, evaluation protocol, and refinement strategy for a task. AutoML systems automate parts of this process, but typically search within predefined pipeline, model, and hyperparameter spaces. LLM-based agents offer greater flexibility through retrieval, code generation, and execution feedback, yet their modelling decisions are often unstructured, difficult to verify, and hard to reuse. We introduce \textsc{MOSAIC} (Modular Orchestration for Structured Agentic Intelligence and Composition), a structured agentic framework for memory-grounded model selection and workflow construction. Given a task and dataset, \textsc{MOSAIC} builds a semantic task profile, retrieves prior cases and source-code modules, and constructs a blueprint: an intermediate representation specifying selected modelling components, composition, interface constraints, and execution requirements. This blueprint turns model selection into a staged, context-grounded search and grounds LLM-based code generation in retrieved evidence rather than unconstrained synthesis. Candidate models are validated by execution and refined using diagnostic feedback, training traces, task metrics, and a failure-aware reinforcement learning policy. We instantiate \textsc{MOSAIC} on financial time-series forecasting and generation, where models must satisfy predictive accuracy, distributional fidelity, execution reliability, and downstream financial criteria such as risk and tail behaviour. Experiments against AutoML and agentic baselines show that \textsc{MOSAIC} improves task performance, execution success, and decision traceability, demonstrating the value of treating automated data science as structured, reusable, and execution-grounded model selection.

arXiv:2606.00680v1 Announce Type: new Abstract: Offline reinforcement learning (RL) aims to optimize policies from pre-collected datasets. A bottleneck of this paradigm is managing epistemic uncerta…

arXiv:2606.00680v1 Announce Type: new Abstract: Offline reinforcement learning (RL) aims to optimize policies from pre-collected datasets. A bottleneck of this paradigm is managing epistemic uncertainty, which arises from limited data coverage (sample-level) and the ambiguity in identifying transition dynamics from finite data (model-level). To provide a unified quantification of these uncertainties, Bayesian RL has been proposed by treating the dynamics model as a random variable and maintaining a corresponding belief. Despite its theoretical appeal, policy optimization in Bayesian RL remains computationally challenging as it requires solving composite objectives with expectations. Prior methods either employ search-based techniques with poor computational scalability or impose restrictive posterior assumptions that sacrifice the adaptability of Bayesian RL. To address these limitations, we propose Posterior Hybrid Bayesian Belief (PhyB), which reformulates the expectation as a convex combination over a subset of dynamics models. Theoretical analysis demonstrates that the objective discrepancy induced by this approximation remains bounded. Based on PhyB, we develop an iterative regularized policy optimization algorithm that provides metric-agnostic guarantees for monotonic improvement until convergence. Empirical results demonstrate that PhyB achieves state-of-the-art performance on various benchmarks.

arXiv:2606.00672v1 Announce Type: new Abstract: Financial exploitation is a growing concern for people with Alzheimer's disease, especially during periods of reduced cognitive stability. Conventiona…

arXiv:2606.00672v1 Announce Type: new Abstract: Financial exploitation is a growing concern for people with Alzheimer's disease, especially during periods of reduced cognitive stability. Conventional fraud detection systems usually rely on financial behavior alone and ignore clinically relevant factors that may alter vulnerability. This paper proposes a medication-aware framework that synchronizes medication adherence with transaction-level monitoring to improve detection of cognitively risky financial events. A hybrid simulation dataset was constructed for 180 patients across 45 days, producing 8,100 medication records and 30,855 transactions. The framework evaluates amount anomaly, vendor novelty, transaction frequency, time deviation, and medication adherence through financial-only, additive medication-aware, and interaction-aware logistic models. Results show that the financial-only baseline obtained the highest global F1-score of 0.5000, but the interaction-aware model improved recall during medication-induced vulnerability windows from 0.7442 to 0.9070 and achieved the highest average precision for ranked high-risk cases. The findings suggest that medication adherence is most useful as a contextual modifier of financial risk rather than as an isolated predictor.

arXiv:2606.00671v1 Announce Type: new Abstract: We present AXIOM, a trust-first neuro-symbolic execution architecture for natural-language mathematical reasoning. In AXIOM, the language model functi…

arXiv:2606.00671v1 Announce Type: new Abstract: We present AXIOM, a trust-first neuro-symbolic execution architecture for natural-language mathematical reasoning. In AXIOM, the language model functions strictly as a canonicalizer: it rewrites informal problem text into a narrow schema consumed by a deterministic Computer-Algebra-System (CAS) pipeline, which derives and verifies the answer or abstains as a first-class output. Routing follows a 1:1:1 alignment between problem-shape regex, schema-specific prompt, and closed-form CAS handler, with 3,100+ such routes shipped and zero LOST_CORRECT regressions across 250+ consecutive ship commits. We report empirical results on 4 MATH categories with a cumulative correctness of 94.36% (2,592/2,747) at 100.00% trust on parseable (zero confident-wrong answers across the full 2,747-record benchmark), all four domains above the per-domain 70/90/70 floor with per-domain trust at 100.0%, and median latency of 1 ms on rule-only handlers (88% of records on the lm-eval arithmetic 20,000-record benchmark). The architecture has served ~30,000 production queries through a public deployment. The contribution we emphasize is not a final accuracy figure but the forward dynamic the architecture establishes: every logged abstain in production is a candidate correct after one ship cycle, since new tasks compose without regressing the registry. The operational discipline behind this property -- math-template bucketing, LOST_CORRECT scan as regression oracle, parseable-first onboarding, and abstain as first-class output -- constitutes a transferable framework for trustworthy neuro-symbolic systems beyond mathematics.

arXiv:2606.00644v1 Announce Type: new Abstract: AI research often requires decisions before future evidence exists: which bottleneck to attack, which direction to pursue, or where a project should b…

arXiv:2606.00644v1 Announce Type: new Abstract: AI research often requires decisions before future evidence exists: which bottleneck to attack, which direction to pursue, or where a project should be positioned. We introduce ForeSci, a temporally controlled benchmark for evaluating whether LLM agents can make such forward-looking research judgements from historical evidence. ForeSci contains 500 tasks across four fast-moving AI domains and four decision families. Each task is paired with a cutoff-aligned offline knowledge base; post-cutoff papers are hidden during generation and used only for validation. To avoid random future-event prediction, tasks are derived from pre-cutoff taxonomy branches and evidence signals, and answer-generation backbones are selected to precede the task cutoffs. We evaluate native LLMs, Hybrid RAG, and three research-agent adaptations across four backbones. Results show that explicit evidence organization improves traceability and factual support, but gains depend strongly on the decision family. Diagnostics reveal a recurring evidence-decision decoupling: agents may cite relevant evidence while forecasting the wrong research object. ForeSci turns forward-looking AI research judgement into a controlled benchmark for evaluating research agents as decision-making systems.

arXiv:2606.00642v1 Announce Type: new Abstract: Reasoning traces have become a valuable form of learning signals for improving and transferring the capabilities of large language models. In particul…

arXiv:2606.00642v1 Announce Type: new Abstract: Reasoning traces have become a valuable form of learning signals for improving and transferring the capabilities of large language models. In particular, detailed traces can help distill reasoning behavior from stronger teacher models into weaker student models. The value of capability transfer has motivated many deployed systems with reasoning models to hide raw internal traces and expose at most summaries and answers to users. As a result, we ask whether such interface-level trace hiding prevents users from obtaining useful reasoning supervision through prompting. We study this question with Reasoning Exposure Prompting (REP), a lightweight in-context elicitation method that uses shadow-model-generated demonstrations wrapped in auxiliary code-like formats to raise user-visible reasoning traces from a victim model. Across the common reasoning dataset, different victim models, and different student model distillation, REP substantially increases similarity between exposed and REP-conditioned internal traces while preserving useful reasoning signals.

arXiv:2606.00618v1 Announce Type: new Abstract: Generative models have emerged as a powerful paradigm for AI planning, yet their performance remains constrained by the training data distribution. On…

arXiv:2606.00618v1 Announce Type: new Abstract: Generative models have emerged as a powerful paradigm for AI planning, yet their performance remains constrained by the training data distribution. One approach is to improve generated solutions during inference by scaling test-time compute. A more efficient alternative is to optimize the inference process itself. In this paper, we show that a modified version of a classical Open-Closed List (OCL) search provides just such an efficient inference procedure. Our algorithm synergizes two learned components: a generative model that performs fast rollouts from intermediate states and a heuristic model that prioritizes among candidate reasoning paths. Key contributions include novel exploration control mechanisms and integration of learned models within the OCL framework. Across multiple combinatorial planning domains, our approach outperforms both neurosymbolic search baselines and classical solvers in computational efficiency and solution quality.

arXiv:2606.00611v1 Announce Type: new Abstract: Long-horizon LLM agents produce safety evidence across long trajectories, where sparse, delayed, and compositional risk signals often escape local mod…

arXiv:2606.00611v1 Announce Type: new Abstract: Long-horizon LLM agents produce safety evidence across long trajectories, where sparse, delayed, and compositional risk signals often escape local moderation. Existing turn-level or short-context detectors struggle to reliably retain and aggregate such evidence over extended horizons. We reframe long-horizon agent safety detection as trajectory-level evidence compression and propose Trajectory Risk-Aware Compression for Long-Horizon Agent Safety (TRACE). TRACE uses a Compressor-Reader design: the Compressor encodes the full trajectory into a compact latent evidence state under trajectory-level supervision, and the Reader judges the raw trajectory with this latent evidence state as a safety reference. This design helps aggregate dispersed risk cues and reduce premature evidence loss. Across ASSEBench, Pre-Ex-Bench, and R-Judge, TRACE achieves the best accuracy on all evaluated backbones, improving over strong baselines by up to 12.6 percentage points. On LongSafety, TRACE shows smaller performance degradation as context length grows. Attention visualizations and case studies suggest that the compressed reference helps the Reader focus on risk-critical segments and recover cross-step evidence. Code is available at https://github.com/Peregrine123/TRACE_official.

arXiv:2606.00582v1 Announce Type: new Abstract: Network faults propagate layer by layer along topology and protocol dependencies, yet operations systems typically observe only symptomatic alerts at …

arXiv:2606.00582v1 Announce Type: new Abstract: Network faults propagate layer by layer along topology and protocol dependencies, yet operations systems typically observe only symptomatic alerts at the tail end of propagation chains, where distinct root-cause faults may produce highly similar end-point symptoms. Existing approaches, whether rule-based, machine learning (ML)-based, or large language model (LLM)-based, fundamentally map the alert set to a diagnosis in a single pass and are structurally incapable of resolving this end-point ambiguity. This paper proposes PropLLM, which is the first to integrate the hop-by-hop scene reconstruction paradigm with the generative reasoning capabilities of LLMs. Starting from end-point alerts, PropLLM traces back hop-by-hop along the propagation path, retrieving verifiable factual evidence from a dual-layer knowledge graph (KG) at each hop, while the proposed Temporal Causal Propagation Attention (TCPA) mechanism encodes known topological causal priors directly into the attention computation to guide the model along the correct causal direction, ultimately localizing the root cause and determining the fault type through a fully evidenced causal chain. On a real-world Wi-Fi multimodal fault dataset, PropLLM improves fault type diagnosis accuracy by 3.9\% and root cause localization accuracy by 4.7\% over the strongest baseline, while reducing the hallucination rate by 50.8\%. Supplementary experiments on the TeleLogs 5G dataset further demonstrate the effectiveness of the proposed method across different network scenarios.

arXiv:2606.00555v1 Announce Type: new Abstract: Structure-based drug design increasingly employs LLM agents to iteratively refine ligands against a target pocket, yet a viable ligand must satisfy tw…

arXiv:2606.00555v1 Announce Type: new Abstract: Structure-based drug design increasingly employs LLM agents to iteratively refine ligands against a target pocket, yet a viable ligand must satisfy two often-conflicting objectives -- binding affinity and druggability -- which single optimization steps rarely improve together. To quantify this difficulty, we introduce two diagnostic metrics: the first measures how often a single edit improves both objectives, and the second measures how often a gain on one objective comes with a loss on the other. Applying these diagnostics to current LLM-agent pipelines exposes a consistent failure mode: the agent performs molecular editing without knowing how the pocket-ligand complex responds to local modifications, thus rarely achieving joint improvement. Inspired by medicinal chemists, who probe the pocket-ligand complex with controlled analog edits before choosing an optimization direction, we propose \textbf{PROBE}, an optimization framework built around edit-response probing. PROBE first decomposes the ligand into editable sites and builds a pocket-specific \textbf{site map} that flags where joint gains are plausible, where the two objectives are likely in tension, and where liability substructures should be changed; it then performs controlled probe edits whose responses are distilled into an \textbf{EditManual}. Guided by the site map and EditManual, PROBE runs an iterative multi-agent loop in which an affinity agent, a druggability agent, and a co-optimization agent jointly produce edits. On the CrossDocked2020 benchmark, PROBE achieves state-of-the-art performance and substantially mitigates the failure modes exposed by our diagnostics metrics.

arXiv:2606.00532v1 Announce Type: new Abstract: Context engineering can improve large language models without updating their weights, but mathematical reasoning exposes a key limitation: feedback ac…

arXiv:2606.00532v1 Announce Type: new Abstract: Context engineering can improve large language models without updating their weights, but mathematical reasoning exposes a key limitation: feedback accumulated in one growing prompt causes context bloat and limits the amount of learned guidance that can be used. Existing methods often conflate storage, what is learned across runs, with usage, what is included for a particular problem, and therefore inherit this prompt-size ceiling. We introduce Knowledge-Adaptive Context Engineering (KACE), which separates storage from usage through difficulty- and domain-based organization. Offline, a self-reflective learning loop distills training traces into an epistemic tree: a knowledge base of typed cards stratified by problem difficulty and epistemic domain. Each card is assigned to the difficulty-domain node corresponding to the failure from which it originated. At evaluation time, tiered self-consistency with per-tier agreement gates dynamically classifies each problem as easy, medium, or hard. Easy problems exit without retrieved cards, while harder problems retrieve only the matching branch of the tree. This tiered scheme matches or exceeds Best-of-N while using comparable compute, and it classifies problem difficulty with 78 percent pairwise concordance. The main empirical contribution is the construction and use of a difficulty- and domain-stratified knowledge base enabled by tiered self-consistency. On AIME 2025, KACE achieves 62.2 percent accuracy, a 10.4-point absolute gain over fixed Best-of-5 self-consistency at a comparable solver-call budget and a 5.6-point gain over the strongest learned-context baseline, Tiered + GEPA. We also observe consistent gains on MATH-HARD and the verifiable subset of OlymMATH.

arXiv:2606.00518v1 Announce Type: new Abstract: Agentic AI systems can plan over multiple steps, use tools, and execute tasks over time. When such systems cause harm, tort law struggles to allocate …

arXiv:2606.00518v1 Announce Type: new Abstract: Agentic AI systems can plan over multiple steps, use tools, and execute tasks over time. When such systems cause harm, tort law struggles to allocate responsibility because the harmful path may be neither fully chosen by the user nor specifically foreseen by the developer. This paper proposes an interaction-based framework for agentic torts, drawing on Michael Bratman's planning theory and on the common law's treatment of human-human concerted action. We distinguish three interaction types: autonomous drift, pure tool use, and collaborative planning. Pure tool cases remain governed by ordinary product-defect and warning doctrines; collaborative planning cases map onto the independent contractor control test, professional malpractice, and negligent misrepresentation; autonomous drift maps onto frolic and detour under respondeat superior and strict product liability. The framework treats the stateful interaction log as the primary evidentiary trace, allowing courts to infer where the human-AI trajectory departed from the authorized undertaking and where liability should attach. We resolve four incident-anchored cases, situate the account alongside strict-liability and insurance-based proposals, note its relationship to regulatory oversight, and propose a ``Reasonable Agent'' standard built around constraint verification, epistemic transparency, runtime grounding, and forensic logging.

arXiv:2606.00516v1 Announce Type: new Abstract: Mixed batching (MB)--interleaving prefill and decode in a single batch--has become the standard scheduling strategy for large language model (LLM) inf…

arXiv:2606.00516v1 Announce Type: new Abstract: Mixed batching (MB)--interleaving prefill and decode in a single batch--has become the standard scheduling strategy for large language model (LLM) inference due to its efficiency in maximizing compute and memory utilization. However, through controlled experiments, we find that prefill-decode interference inflates MB's per-step marginal cost above that of pure decode. On the high-bandwidth H200 (4.8 TB/s), this occurs only when decode tokens exceed 80% of the batch; however, on the bandwidth-constrained RTX PRO 6000 (1.792 TB/s), this threshold plummets to just 20%. Consequently, the optimal choice between MB and exclusive batching (EB) fundamentally depends on GPU memory bandwidth, model size, and workload composition. We derive a closed-form condition for this EB-MB performance crossover, along with asymptotically optimal phase-switching thresholds and memory-safe batch sizing for EB. Optimized EB achieves up to 41.9% higher throughput on bandwidth-constrained GPUs, while MB retains its advantage on high-bandwidth hardware with larger models. Our hybrid scheduler EB+ applies this condition online to dynamically switch between EB and MB without manual intervention. Under non-stationary traffic with distribution or concurrency shifts, EB+ attains the highest or near-highest throughput in every setting, outperforming MB by up to 36.4%.

arXiv:2606.00506v1 Announce Type: new Abstract: Energy consumption prediction is essential for efficient grid management, demand-side optimization, and sustainable energy planning. Although advanced…

arXiv:2606.00506v1 Announce Type: new Abstract: Energy consumption prediction is essential for efficient grid management, demand-side optimization, and sustainable energy planning. Although advanced machine learning methods have been employed for better prediction performance, existing works have two key limitations: (1) they usually formulate this task as a purely time-series prediction problem without explicitly modeling the spatial dependencies among different regions, and (2) they fail to provide reliable predictions with uncertainty estimates under abnormal situations such as extreme weather events. To advance existing research, we propose EnergyMamba, an uncertainty-aware spatiotemporal learning framework for accurate and reliable energy consumption prediction, which comprises two key components: (i) a novel Graph-Enhanced Selective State Space Model (GE-Mamba) that injects spatial context learned from the grid topology into the temporal dynamics, enabling coupled spatiotemporal modeling, and (ii) an Adaptive Sequential Conformalized Quantile Regression (AS-CQR) module, which includes locally adaptive normalization and an online feedback mechanism to dynamically calibrate prediction intervals under potential distribution shifts. We evaluate EnergyMamba on four large-scale real-world datasets from Florida, New York, and California. Results show EnergyMamba achieves around 5% improvement in prediction accuracy and 6% improvement in uncertainty quantification over 15 state-of-the-art baselines.

arXiv:2606.00487v1 Announce Type: new Abstract: Using a diffusion model for parallel drafting is a promising approach for speculative decoding. By predicting tokens at multiple future positions in a…

arXiv:2606.00487v1 Announce Type: new Abstract: Using a diffusion model for parallel drafting is a promising approach for speculative decoding. By predicting tokens at multiple future positions in a single forward pass, diffusion drafters substantially reduce drafting latency. However, this shifts the bottleneck to verification: verifying a single sequence limits acceptance length, while verifying large draft trees incurs excessive target-model latency. We identify a key mismatch in existing draft-tree methods: existing diffusion-tree methods rank nodes by the marginal probability, ignoring that verification is prefix-conditioned. As a result, they may verify unreachable descendants of rejected prefixes, increasing latency with limited acceptance gains. To address this, we propose TAPS, a target-aware prefix selection method that turns diffusion marginals into path-conditioned acceptance estimates. TAPS then selects a compact prefix-closed subtree under a fixed verification budget, improving the acceptance-cost tradeoff rather than simply expanding the draft tree. Experiments across diverse datasets and model families demonstrate that TAPS achieves up to 7.9x lossless end-to-end speedup over vanilla autoregressive decoding, outperforming state-of-the-art DFlash and DDTree by 1.36x and 1.74x respectively. Our work is available at https://anonymous.4open.science/r/TAPS-EMNLP2026-53DD

arXiv:2606.00476v1 Announce Type: new Abstract: Do LLM agents act on the reasoning they state? This question of process fidelity is central to using LLMs in social simulation, yet it is hard to meas…

arXiv:2606.00476v1 Announce Type: new Abstract: Do LLM agents act on the reasoning they state? This question of process fidelity is central to using LLMs in social simulation, yet it is hard to measure where no reference for correct behavior exists. We study it in acontrolled setting, a Texas Poker simulator with a verifiable reference action for every decision by decomposing the faithfulness gap into two steps: reasoning-conclusion and conclusion-action. The two steps behave oppositely.

arXiv:2606.00440v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards has rapidly advanced reasoning in vision--language models. However, for chest X-ray report generation, …

arXiv:2606.00440v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards has rapidly advanced reasoning in vision--language models. However, for chest X-ray report generation, the standard rewards (i.e. exact-match accuracy and step-level processes) are incompatible because the reports consist of unordered and orthogonal findings, rather than a causal reasoning chain. We address this gap with a set-based view: each report is split into sentences and embedded by a frozen sentence transformer, yielding unordered embedding sets. We propose the use of set-to-set distances between generated and reference embeddings as continuous, permutation-invariant rewards. Across two datasets and three vision--language models (Qwen3-VL-2B/4B, Gemma3-4B), post-training with set-to-set distance based rewards via GRPO consistently outperforms supervised fine-tuning and exact-match GRPO on all headline metrics (BERTScore, RadGraph F1 and CheXbert F1 by average \%6.80, \%7.82 and \%4.45 relative improvements respectively). The same set distances also enable test-time best-of-$N$ selection: scoring candidates by their distance to training-report embeddings outperforms random selection on our trained models as well as three closed-source LLMs (Mistral-Small, Gemini-2.5 Flash-Lite, GPT-4o-mini) with on average \%16.4 relative improvement on BERTScore. Used as a streaming signal, they support a more efficient form of test-time scaling: pruning low-scoring candidates mid-generation reduces generated tokens by over 50\% while preserving the Findings quality of full best-of-$N$ selection. Together these results establish set-distance rewards as a unified signal for both post-training and test-time scaling in chest X-ray report generation. Our code is publicly \href{https://anonymous.4open.science/r/Set-Distance-Rewards-CXR-BFDA}{available}.

arXiv:2606.00424v1 Announce Type: new Abstract: As large language models become stronger, weak supervisors may fail to provide reliable labels, preferences, or final judgments for complex outputs, l…

arXiv:2606.00424v1 Announce Type: new Abstract: As large language models become stronger, weak supervisors may fail to provide reliable labels, preferences, or final judgments for complex outputs, limiting both weak-to-strong generalization and scalable oversight. We study a more tractable form of weak supervision: using a weak model as a critic rather than as a labeler or judge. Instead of solving the task or selecting the correct answer, the weak critic only needs to provide a non-misleading revision direction that helps the strong model better use its own knowledge. We call this setting *weak-critic strong oversight*. We first show that weak critiques can improve frozen strong models at inference time, and that critique quality is key to this improvement. We then propose progressive on-policy critique distillation (**OPCD**), which filters high-quality critiques and distills critic-guided behavior into the strong model through adaptive self-teacher signals. Experiments on reasoning and alignment benchmarks show that our method improves strong models over training epochs, suggesting an effective path for scalable oversight with weak supervision.

arXiv:2606.00384v1 Announce Type: new Abstract: Fitting quantitative models to data is a central step in scientific workflows, yet it remains one of the least automated. Recent agent-based systems l…

arXiv:2606.00384v1 Announce Type: new Abstract: Fitting quantitative models to data is a central step in scientific workflows, yet it remains one of the least automated. Recent agent-based systems leverage language and vision-language models (VLMs) to iteratively propose and refine statistical models, but these systems struggle on more challenging modeling tasks. To address these limitations, we introduce VESTA: Visual Exploration with Statistical Tool Agents, a framework that equips VLMs with a dynamically growing exploration toolkit to guide model refinement through data transformations, hypothesis-driven visualizations, and robust statistical tests. Unlike prior systems that rely on iterative critique alone, VESTA actively explores data before and during refinement by selecting or creating diagnostic tools, which accumulate in the model's context and can be reused later. We evaluate VESTA against established baselines in three toolkit configurations: no tools, static expert-written tools, and dynamic model-written tools. To support this evaluation, we introduce DAWN (Dataset for Automated Workflows and Numerical Modeling), a benchmark targeting distribution fitting and time series modeling with varying difficulty tiers, and culminating in real-world astronomy tasks including modeling initial mass functions and gravitational-wave chirp signals. We find that VESTA's dynamic tool creation outperforms prior agentic pipelines, with the largest gains on complex and domain-specific tasks. We further show that dynamically generated tools are substantially more sophisticated than those produced by existing visual tool-creation systems, covering more diagnostic categories per function and strongly preferring visual outputs that the VLM critic can reason over directly.

arXiv:2606.00376v1 Announce Type: new Abstract: Extended chain-of-thought reasoning can degrade performance on deterministic state-tracking tasks, not due to preference biases, but limits rooted in …

arXiv:2606.00376v1 Announce Type: new Abstract: Extended chain-of-thought reasoning can degrade performance on deterministic state-tracking tasks, not due to preference biases, but limits rooted in the information-theoretic capacity of decoder-only attention. We establish: (1) an Attention Bottleneck Theorem with a complementary achievability construction, bounding state-tracking capacity as $O(H \cdot \log(L/H) \cdot \sqrt{d_h})$; (2) a context-dependent error model yielding super-exponential accuracy decay; (3) the State-Space Jaccard metric distinguishing capability from preference failures; (4) a Deterministic Horizon $d^* \in [19, 31]$ beyond which tool delegation becomes necessary. Across 12 models and 8 task domains (including SWE-Bench, WebArena, and SQL-Multi), tool-integrated reasoning consistently outperforms neural chain-of-thought; on the primary model suite it reaches 86-94% accuracy versus 24-42% for neural chain-of-thought. Fine-tuning on optimal-length traces yields $<$5% improvement, confirming an architectural ceiling, and high cross-model correlation ($r = 0.81$-$0.91$) indicates these failures are architectural rather than training-specific. Our results provide principled guidance for when pure neural reasoning should yield to hybrid approaches in agentic systems.

arXiv:2606.00357v1 Announce Type: new Abstract: Training strong large language models (LLMs) requires high-quality supervision, which is often scarce. Recent work shows that paired preference data f…

arXiv:2606.00357v1 Announce Type: new Abstract: Training strong large language models (LLMs) requires high-quality supervision, which is often scarce. Recent work shows that paired preference data from weak-weaker model pairs (e.g., Qwen3 4B over 1.7B), despite the limited quality of individual responses, can provide an effective supervision signal through relative quality deltas, which we term a "weak" signal. This motivates a key research question: can multiple "weak" signals be constructively aggregated for improving strong models (e.g., Qwen3 8B)? To this end, we propose Preference Delta Aggregation (PDA), the first framework that derives a preference delta from each weak-weaker model pair, instantiates it as a LoRA adapter learned through preference optimization, and aggregates the resulting deltas via LoRA merging. To further mitigate directional interference during LoRA merging, we introduce Geometric Alignment Merging (GAM), a geometry-aware merging method that aligns adapter subspaces before aggregation, enabling more robust composition of diverse deltas. Evaluations on knowledge reasoning and agentic search benchmarks show that aggregating multiple "weak" signals pushes performance beyond any single signal, with further gains as additional signals are incorporated. Correspondingly, PDA with GAM improves the strong model by 6.8 and 7.3 points on average for knowledge reasoning and agentic search, respectively. It outperforms all single-delta and multi-delta baselines, exceeding the best single-delta baseline by 2.1 and 4.3 points. Further analysis attributes these gains to the effective composition of complementary capabilities encoded across distinct preference deltas.

arXiv:2606.00336v1 Announce Type: new Abstract: We propose Parameterized Diffusion Policy (PDP), a framework for learning diffusion policies conditioned on low-dimensional, continuous parameters emb…

arXiv:2606.00336v1 Announce Type: new Abstract: We propose Parameterized Diffusion Policy (PDP), a framework for learning diffusion policies conditioned on low-dimensional, continuous parameters embedded in a learned behavior manifold. By constructing this manifold so that distances between latent representations reflect the semantic similarity between physical trajectories, we transform diffusion from a mechanism for stochastic diversity into a precise and optimizable tool for behavior steering. Our approach enables smooth interpolation between known strategies and efficient adaptation to novel constraints without updating policy weights. We demonstrate that PDP significantly improves adaptation performance on complex multimodal benchmarks in both simulated and real-robot experiments compared to standard diffusion policies, particularly in scenarios requiring the synthesis of novel behaviors.

arXiv:2606.00315v1 Announce Type: new Abstract: Modern generative machine learning (ML) models can propose novel inorganic crystalline materials with targeted properties; however, synthesis planning…

arXiv:2606.00315v1 Announce Type: new Abstract: Modern generative machine learning (ML) models can propose novel inorganic crystalline materials with targeted properties; however, synthesis planning of these materials remains difficult due to the complexity of the associated physical processes and limited availability of computational tools. We introduce a novel hybrid framework to evaluate Large Language Models (LLMs) in inorganic synthesis planning by combining thermodynamic databases with simplified kinetics models to approximate realistic synthesis conditions. As a case study, we focus on the niobium-oxygen system, which features multiple industrially relevant oxide phases with well-characterized data. In computational simulations, we compare LLM-generated synthesis routes with classical path-planning algorithms, showing that the implicit priors in LLMs can yield more viable strategies. In our evaluation setting, classical search methods serve primarily as a foil rather than a direct competitor. This illustrates the relative complexity of the problem and highlights where the LLM's implicit priors add value.

arXiv:2606.00288v1 Announce Type: new Abstract: Large language models are undergoing a transition from model technology to system technology. As developers use Codex, Claude Code, AutoGPT, and relat…

arXiv:2606.00288v1 Announce Type: new Abstract: Large language models are undergoing a transition from model technology to system technology. As developers use Codex, Claude Code, AutoGPT, and related agents to write code, manage projects, and execute multi-step tasks, recurring engineering problems such as cache reuse, context management, agent scheduling, and permission control increasingly resemble classical computer systems problems. This paper develops that analogy as a visionary survey. We map concepts from computer architecture to the emerging model-native stack and review work on LLM-as-OS, memory management, agent frameworks, tool protocols, multi-agent coordination, cognitive architectures, and safety governance. We argue that these strands address different layers of the same system but lack a unified model. To fill this gap, we propose the Intelligent Computing Architecture Model (ICAM), a six-layer framework for model-native computing with explicit interface contracts and design axioms. ICAM resolves the apparent tension over whether an LLM is more like a CPU or an operating system through a dual-plane view: a probabilistic execution plane concerned with what can be computed, and a deterministic control plane concerned with what should be computed. We further introduce three design laws: the Semantic Locality Law for KV-cache reuse and inference speedup, the Context Budget Law for effective working sets under finite windows and attention decay, and the Agent Speedup Law for diminishing returns in multi-agent collaboration. We validate these laws against published system-level data and relate them to recent evidence on agentic software practices. We conclude by identifying where the analogy breaks down and outlining a research roadmap for model-native computing. This is a conceptual and survey contribution; it does not report new experiments.

arXiv:2606.00278v1 Announce Type: new Abstract: For many real-world systems, causal ground truth is difficult to obtain, making claims about causal effects hard to assess. We develop methods for eva…

arXiv:2606.00278v1 Announce Type: new Abstract: For many real-world systems, causal ground truth is difficult to obtain, making claims about causal effects hard to assess. We develop methods for evaluating collections of $\binom{n}{2}$ bivariate causal statements over a set of $n$ variables. In the setting of acyclic linear statements, any such collection can be extended to a unique multivariate causal model, but we argue that this induced model is implausible if it imposes substantial additional confounding to explain observed correlations. We introduce a compatibility score that quantifies this notion of plausibility, notably without relying on the faithfulness assumption. Additionally, we define an incompatibility score for purely graphical bivariate causal statements, based on global consistency constraints that are derived from acyclicity and faithfulness assumptions. We give theoretical and empirical evidence that both scores can successfully distinguish correct from incorrect causal statements in generic settings. Moreover, we demonstrate the practical applicability of our methods by analyzing causal claims made by large language models. Our work aims to provide a foundation for assessing the reliability of causal information derived from human experts or artificial intelligence in settings where alternative forms of validation are unavailable.

arXiv:2606.00272v1 Announce Type: new Abstract: The FETCH classifier generates follow-up questions to help refine the best match for the applicant's legal problem, using a low-cost ensemble of LLMs.…

arXiv:2606.00272v1 Announce Type: new Abstract: The FETCH classifier generates follow-up questions to help refine the best match for the applicant's legal problem, using a low-cost ensemble of LLMs. In this paper, we describe an expert attorney and LLM-assisted evaluation of the follow-up question approach in FETCH and show that while low-cost LLMs perform well at classification tasks, generating high-quality plain-language questions in this setting appears to require a more sophisticated and higher-cost model. Through discussion with legal intake workers, we propose a rubric for the evaluation of legal intake classification questions, and we find that prompt engineering alone is not enough to improve question quality for intake purposes. We also find that LLM-as-judge and human ratings diverge. We demonstrate that with the addition of a single high-cost model, GPT-5, the classifier can elicit relevant information from applicants for legal help, and that the questions lead to more accurate performance at classification tasks. We also find uneven fact elicitation across different categories, including domestic violence, at odds with family law screening protocols, suggesting the value of including dedicated screening panels for certain areas of law.

arXiv:2606.00270v1 Announce Type: new Abstract: Shielding is an effective approach to formally guarantee the safety of reinforcement learning agents in Markov decision processes (MDPs). However, exi…

arXiv:2606.00270v1 Announce Type: new Abstract: Shielding is an effective approach to formally guarantee the safety of reinforcement learning agents in Markov decision processes (MDPs). However, existing shielding techniques typically assume knowledge of the safety-relevant transition dynamics - a requirement that is seldom met in practice. To address this limitation, we introduce a novel shielding framework for robust MDPs (RMDPs), i.e., MDPs with sets of transition probabilities. We define safety as the satisfaction of a linear temporal logic (LTL) formula with a certain threshold probability under the worst-case transition probabilities of the RMDP. We prove that our shielding framework is both sound and optimal for the RMDP: every policy admissible by the shield is safe, and conversely, every safe RMDP policy is admissible by the shield. We combine our approach with existing sampling methods for learning transition probabilities of MDPs with probably approximately correct (PAC) guarantees. This combination enables the construction of shields for MDPs that, with high confidence, guarantee safety while remaining minimally restrictive. Our experiments show that our shields for learned RMDPs guarantee safety in unknown MDPs while recovering strong expected return as the number of samples increases.

arXiv:2606.00269v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models can be steered at test time by intervening on semantically meaningful internal directions, but existing methods us…

arXiv:2606.00269v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models can be steered at test time by intervening on semantically meaningful internal directions, but existing methods use a fixed steering coefficient, effectively operating in open loop. This is poorly suited to embodied control, where task state and concept error evolve over time, often causing overcorrection, oscillation, and reduced task success, especially for temporal behaviors such as speed and smoothness. We propose CTRL-STEER, a closed-loop framework that replaces static intervention strength with adaptive, time-varying control signals. The key idea is to decouple representation from regulation: rather than assuming temporal concepts are directly controlled by individual neurons, we steer along motion-aligned residual directions while a feedback controller adjusts intervention magnitude online. We instantiate this framework with both PID and reinforcement learning based controllers. Experiments with a fine-tuned OpenVLA policy on four LIBERO task suites show that CTRL-STEER achieves more stable concept regulation and a better steering-task success trade-off than fixed-coefficient baselines, without modifying or retraining the base model.

arXiv:2606.00251v1 Announce Type: new Abstract: The ability to recognize one's own limitations and decide whether to solve a problem or delegate is fundamental for reliable intelligent systems. Yet …

arXiv:2606.00251v1 Announce Type: new Abstract: The ability to recognize one's own limitations and decide whether to solve a problem or delegate is fundamental for reliable intelligent systems. Yet we show that modern large language models systematically lack this ability: across diverse model families and scales, they overestimate their competence and attempt queries they cannot solve. We refer to this ability as Capability Self-Assessment (CSA) and formulate it as a policy-learning problem, aiming to improve self-assessment while preserving the model's original capabilities. Our results show that reinforcement learning teaches CSA effectively, significantly outperforming supervised fine-tuning while preserving original capabilities. In contrast, supervised fine-tuning severely degrades the capabilities the model is meant to assess. Moreover, learned self-assessment behavior generalizes well out of distribution, suggesting that CSA is a transferable model trait. Finally, CSA is practically useful: it improves local-cloud decision making at inference time and provides a signal for targeted data selection during training.

arXiv:2606.00248v1 Announce Type: new Abstract: Vector Symbolic Algebras (VSAs) enable robust neurosymbolic reasoning by encoding symbolic information into high-dimensional distributed representatio…

arXiv:2606.00248v1 Announce Type: new Abstract: Vector Symbolic Algebras (VSAs) enable robust neurosymbolic reasoning by encoding symbolic information into high-dimensional distributed representations. For continuous domains, Spatial Semantic Pointers (SSPs) extend this framework by mapping variables onto continuous toroidal manifolds. However, standard approaches like Flow Matching assume a flat Euclidean geometry, which fails to account for the geometric constraints imposed on valid SSP states. We demonstrate that this assumption fails for SSPs: Euclidean linear interpolants ``cut through" the manifold's interior, destroying the phase and magnitude structure required for accurate decoding. To resolve this, we employ Geodesic Flow Matching, adapting Riemannian transport dynamics to strictly restrict the denoising flow to the SSP toroidal manifold. We validate this approach in a Spiking Neural SLAM system, showing that manifold-aware cleanup stabilizes path integration against drift. The method achieves a 72\% reduction in tracking error and enables a 40\% increase in neural efficiency compared to competitive baselines. Code is available at https://github.com/kremHabashy/CleanupSSP .

arXiv:2606.00240v1 Announce Type: new Abstract: Effective real-world assistance requires AI agents with robust Theory of Mind (ToM): inferring human mental states from their behavior. Despite recent…

arXiv:2606.00240v1 Announce Type: new Abstract: Effective real-world assistance requires AI agents with robust Theory of Mind (ToM): inferring human mental states from their behavior. Despite recent advances, several key challenges remain, including (1) online inference with robust uncertainty updates over multiple hypotheses; (2) efficient reasoning suitable for real-time assistance; and (3) the lack of ground-truth mental state annotations in real-world domains. We address these challenges by introducing MindZero, a self-supervised reinforcement learning framework that trains multimodal large language models (MLLMs) for efficient and robust online mental reasoning. During training, the model is rewarded for generating mental state hypotheses that maximize the likelihood of observed actions estimated by a planner, similar to model-based ToM reasoning. This method thus eliminates the need for explicit mental state annotations. After training, MindZero internalizes model-based reasoning into fast single-pass inference. We evaluate MindZero against baselines across challenging mental reasoning and AI assistance tasks in gridworld and household domains. We found that LLMs alone are insufficient; model-based methods improve accuracy but are slow, costly, and limited by backbone MLLM capacity. In contrast, MindZero enhances MLLMs' intrinsic ToM ability and significantly outperforms model-based methods in both accuracy and efficiency, showing that mental reasoning can be effectively learned as a self-supervised skill.

arXiv:2606.00232v1 Announce Type: new Abstract: We study fact-level repair for multimodal generation, where a fluent output may contain specific facts that are not supported by the input. Existing i…

arXiv:2606.00232v1 Announce Type: new Abstract: We study fact-level repair for multimodal generation, where a fluent output may contain specific facts that are not supported by the input. Existing inference-time repair methods often generate feedback by jointly conditioning on the input and the current output. This design has two limitations: hallucinated claims in the output can bias the model's interpretation of the input, and free-form feedback cannot be ranked or scheduled at the fact level. We present TIGER, an inference-time framework that redesigns feedback for localized repair. TIGER independently extracts an observation graph from the input and a claim graph from the current output, then assigns each claim a graph-conditioned risk score based on support and conflict. The model repairs selected high-risk claims while keeping the backbone frozen. We provide a convergence analysis showing that the expected total risk decreases geometrically to an explicit asymptotic bound under mild assumptions. Experiments across four cross-modal paths, including image-to-text, image+text-to-text, audio-to-text, and video-to-text, show that TIGER reduces unsupported content while preserving task quality. The gains hold across multiple backbones, and a CrisisFACTS case study suggests that the same repair mechanism can improve grounding in multi-source settings.

arXiv:2606.00172v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR), especially Group Relative Policy Optimization (GRPO), has been widely used to improve reasoning…

arXiv:2606.00172v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR), especially Group Relative Policy Optimization (GRPO), has been widely used to improve reasoning in large language models. However, outcome-level rewards provide only sparse supervision, and group-relative advantages vanish when all sampled trajectories for a prompt are either correct or incorrect. On-Policy Self-Distillation (OPSD) offers dense token-level guidance, but its token preferences are not necessarily aligned with trajectory correctness; empirical diagnostics show that OPSD signals behave differently on correct and incorrect rollouts, with teacher-positive and teacher-negative gap signals exhibiting different noise profiles. These diagnostics are conducted under an OPSD-style privileged teacher context for analysis only, whereas CAST training uses answer-free self-teacher scoring.Motivated by these observations, this work proposes CAST, an answer-free self-distillation method for GRPO-style RLVR. CAST keeps the verifier-grounded GRPO objective, but uses a stop-gradient self-teacher to shape token-level advantages according to trajectory correctness. Unlike prior self-distilled RLVR methods, CAST does not require reference-solution-conditioned teacher scoring, keeps the self-teacher log-probability gap active throughout training, and applies bidirectional local advantage sign reversal: teacher-negative tokens in correct trajectories can receive negative token-level advantages, while teacher-positive tokens in incorrect trajectories can receive bounded positive local advantages. For zero-variance all-correct and all-wrong groups, CAST assigns bounded sign-constrained base advantages, so these otherwise zero-gradient groups can contribute verifier-signed token feedback. Experiments on mathematical reasoning show that CAST improves RLVR training while retaining a lightweight, verifier-grounded trajectory-level objective.

arXiv:2606.00138v1 Announce Type: new Abstract: Finite element analysis (FEA) is the most important numerical approach for solid mechanics. Challenges of FEA include a steep learning curve for entry…

arXiv:2606.00138v1 Announce Type: new Abstract: Finite element analysis (FEA) is the most important numerical approach for solid mechanics. Challenges of FEA include a steep learning curve for entry-level users and potential false simulations due to incorrect definitions of key simulation components, such as boundary conditions, load cases, and solution variables. Years of engineering experience are usually necessary for real-world problem-solving. To address these issues, we present AbaqusAgent, a multi-agent framework grounded in large language models (LLMs) for solid mechanics analyses. AbaqusAgent is developed to facilitate analysis case generation and execution using Abaqus, one of the most widely used FEA packages, by turning users' natural-language instructions into executed FEA analyses and result visualization. AbaqusAgent is composed of six agents, including interpreter, architect, input writer, runner, reviewer, and visualizer agents, encompassing all the essential pre-processing and post-processing steps of standard FEA analyses. A wide variety of 50 solid mechanics problems have been successfully validated, achieving an overall success rate of 86%. Beyond improving the efficiency of FEA for solid mechanics problems and lowering the barrier to computational mechanics education, AbaqusAgent advances the human-simulation interaction paradigm and enables integration with AI-empowered optimization and material characterization workflows. The code is available at https://github.com/LIRAM-LIN/AbaqusAgent

arXiv:2606.00103v1 Announce Type: new Abstract: We introduce a multi-turn interactive framework for reasoning evaluation that treats reasoning as active evidence acquisition and belief updating. Whe…

arXiv:2606.00103v1 Announce Type: new Abstract: We introduce a multi-turn interactive framework for reasoning evaluation that treats reasoning as active evidence acquisition and belief updating. Wherein, LLMs receive only the task rules, must issue targeted queries to a hidden environment, integrate partial observations over time, and decide when to submit a final answer. Beyond standard success rate and interaction efficiency, we evaluate contextual robustness under controlled contextual perturbations, and metacognitive adaptation through counterfactual revision and necessity judgment. We instantiate the framework as a benchmark of 474 executable games, each evaluated under five fixed configuration search spaces corresponding to five difficulty levels, and evaluate a broad set of frontier LLMs. Results show that the benchmark is highly discriminative, exposing large differences not only in success rate but also in interaction efficiency. Moreover, we empirically show that contextual perturbations cause moderate but consistent declines, whereas counterfactual revision and necessity judgment lead to much larger drops.

arXiv:2606.00102v1 Announce Type: new Abstract: Over the centuries, probability theory has grown from the calculus of games of chance into a central framework for reasoning under uncertainty. This a…

arXiv:2606.00102v1 Announce Type: new Abstract: Over the centuries, probability theory has grown from the calculus of games of chance into a central framework for reasoning under uncertainty. This article interprets that evolution not merely as a mathematical history, but as a transformation of rationality itself. From Pascal and Fermat's combinatorial symmetry to the inductive logic of Bayes and Laplace, from Poisson's statistics of events to Kolmogorov's axiomatic formalization, probability progressively incorporated uncertainty, time, and coherence into scientific judgment. This trajectory reaches a mature epistemological form in modern Bayesian inference, especially in Tarantola's view of probability as a logic of information, where prior knowledge and data are combined coherently. Yet this framework also exposes a limit: probability quantifies uncertainty about well-defined propositions, but does not by itself formalize the vagueness of the concepts used to describe them. The article therefore examines how rationality extends beyond probability. Fuzzy logic is presented as a rigorous language for graded meaning and qualitative judgment, while deep learning is analyzed as a distinct, powerful mode of prediction based on geometric interpolation and optimization rather than explicit inference. By situating probability, fuzzy logic, and deep learning in a common historical and epistemological perspective, the article clarifies their roles and limits. It argues that contemporary scientific rationality cannot be reduced to data-driven performance alone, but requires the explicit articulation of uncertainty, vagueness, and inference.

arXiv:2606.00052v1 Announce Type: new Abstract: As Industry 4.0 accelerates the integration of Cyber-Physical Systems (CPS) in manufacturing, robust anomaly detection has become critical for ensurin…

arXiv:2606.00052v1 Announce Type: new Abstract: As Industry 4.0 accelerates the integration of Cyber-Physical Systems (CPS) in manufacturing, robust anomaly detection has become critical for ensuring process safety and security. Current data-driven approaches typically employ "product-agnostic" or global models trained on the aggregate of all normal operating data. However, modern industrial facilities frequently operate under diverse product grades. While computationally simple, these global models inherently expand their decision boundaries to accommodate the variance of multiple modes, creating a "blind spot" where subtle anomalies or targeted cyber-physical attacks may be masked by the wide acceptance region of the model. In this work, we first demonstrate that the vulnerability described above is present in global-agnostic models operating across multiple product grades. We then present a Product-Aware Autoencoder as a principled mitigation that restricts the learning domain to grade-specific distributions. While this approach reduces the identified blind-spot risk, we do not claim it as the optimal mitigation among all possible alternatives. We rigorously validate this approach against a Global Agnostic baseline using the Extended Tennessee Eastman Process (TEP) benchmark. Our empirical results indicate that the Product-Aware framework performs comparably to the global baseline on standard detection metrics, while offering improved robustness to product-grade-specific operating modes. Most critically, stress tests simulating our hypothetical attack scenarios reveal that while the global model fails to detect operational deviations in 77.8% of the scenarios, the product-aware system achieves 100% detection accuracy. These findings suggest that, in flexible manufacturing environments, generalized anomaly detectors can pose non-trivial security risks, motivating a shift toward mode-aware diagnostic architectures.

arXiv:2606.00050v1 Announce Type: new Abstract: We present Grokers, an architecture for building persistent, structured comprehension of typed knowledge graphs through bottom-up inductive traversal …

arXiv:2606.00050v1 Announce Type: new Abstract: We present Grokers, an architecture for building persistent, structured comprehension of typed knowledge graphs through bottom-up inductive traversal of dependency subgraphs. Unlike retrieval-augmented generation (RAG), which pays full comprehension cost at every query, Grokers pushes intelligence to write time: autonomous Groker agents analyze nodes in a typed stream graph, extract structured attributes via governed language model (LM) calls, and inductively compose that understanding upward through dependency relations, writing enriched typed attributes that serve all future queries at zero additional LM cost. We prove three formal properties: (1) the Byte-Identity Theorem, establishing that context blocks assembled from a transactionally-maintained denormalization index are byte-identical across LM turns between semantic changes, enabling KV-cache hit rates approaching 100%; (2) the Accumulation Monotonicity Theorem, establishing that the fraction of interactions resolved without LM calls is non-decreasing in the number of completed interactions under a governed wisdom library growth protocol; and (3) the Dual-Traversal Ordering Theorem, establishing that top-down generation and bottom-up comprehension are the unique correct traversal orderings for their respective tasks over a dependency DAG, and that their composition closes into a complete generation-comprehension cycle. We further present a deterministic alternative to embedding-based semantic search, with a synonym caching protocol whose LM fallback rate converges to zero for finite-vocabulary domains. A reference implementation is provided in the open-source Qbix / Safebox / Safebots stack.

arXiv:2606.00045v1 Announce Type: new Abstract: Classical continuous-space neural networks fundamentally struggle to lock into exact mathematical symmetries, such as modular arithmetic and non-commu…

arXiv:2606.00045v1 Announce Type: new Abstract: Classical continuous-space neural networks fundamentally struggle to lock into exact mathematical symmetries, such as modular arithmetic and non-commutative algebra. To approximate these discrete logical rules, they often rely on massive parameter scaling, resulting in stochastic instability even after delayed generalization phenomena known as grokking. Here, we introduce the Universal Quantum Transformer (UQT), a fundamentally novel, quantum-native computing architecture that uses the physical properties of multi-qubit systems as a universal inductive bias for exact mathematical and algebraic reasoning. Rather than translating classical neural mechanisms, our framework relies entirely on parameterized geometric phase embedding and $SU(2)$ wave-interference. We demonstrate that the quantum attention circuit, operating on a highly compact 5-qubit substrate, perfectly learns two highly distinct formal classes: cyclic modular arithmetic ($\mathbb{Z}_{11}$) and non-Abelian algebra (the $S_4$ permutation group). While classical attention-based networks exhibit stochastic instability at convergence, the UQT achieves mathematically exact, deterministic generalization. We refer to this phenomenon as crystallization: a step beyond the well-known phenomenon of grokking. Crucially, this framework yields massive computational and memory advantages by theoretically bypassing the quadratic bottleneck of classical self-attention, and by logarithmically compressing the required representation dimension to eliminate the massive over-parameterization inherent to classical networks. Finally, we deploy this architecture on noisy intermediate-scale quantum (NISQ) hardware, proving its viability on current IBM Quantum computers. These results establish parameterized quantum topology as a universally superior physical substrate for exact artificial intelligence.

arXiv:2606.00017v1 Announce Type: new Abstract: Training language model agents for multi-agent strategic interaction presents a core difficulty: the quality of any action may depend on future events…

arXiv:2606.00017v1 Announce Type: new Abstract: Training language model agents for multi-agent strategic interaction presents a core difficulty: the quality of any action may depend on future events that never materialize, on moves that violate game rules, or on decisions made by other players. Standard reinforcement learning assumes that rewards can be assigned at each step, but this assumption fails in settings where outcomes are entangled across time and agents. We introduce delayed per-step reward attribution with eligibility gating, an episode lifecycle and postprocessing pipeline that computes rewards only at episode end, propagates them back to originating steps according to task-specific semantics, and excludes steps that lack valid dependent information from training. Together with asynchronous rollout generation via vLLM's continuous batching, curriculum-based opponent sampling, and multi-level stratified batch construction, this approach enables stable, sample-efficient RL training in multi-agent environments. We evaluate on the MindGames Arena benchmark at NeurIPS 2025, where a single 8-billion-parameter open-source model trained with our method matched or surpassed substantially larger proprietary systems, including GPT-5, in head-to-head play and took first place in both the Open (unrestricted) and Efficient (<=8B parameters) tracks.

arXiv:2606.00009v1 Announce Type: new Abstract: Bayesian Optimization (BO) is widely and successfully adopted for solving optimization problems having an expensive-to-evaluate, black-box, and non-co…

arXiv:2606.00009v1 Announce Type: new Abstract: Bayesian Optimization (BO) is widely and successfully adopted for solving optimization problems having an expensive-to-evaluate, black-box, and non-convex objective function. However, the vanilla BO algorithm is not able to exploit possible symmetries characterizing the target problem. An intuitive case is given by optimal location problems, whose decision variables refer to a finite set of points within a continuous space, with the order of points not affecting the value of the objective function. We refer to this setting as optimization over layouts to distinguish from optimization over point-clouds where, instead, the order of points counts. As an instance of optimization over layouts we consider a real-life industrial-relevant application, that is the optimization of the layout of an offshore wind farm: given identical wind turbines, switching any pair of them has not any effect on the annual energy production. Based on Optimal Transport theory, we propose a Permutation-Invariant BO approach, namely PIBO, proved to provide better wind farm layouts when compared to the vanilla BO approach while cutting computation time roughly in half.

arXiv:2606.00008v1 Announce Type: new Abstract: Multi-objective molecular optimization requires searching vast chemical spaces under conflicting objectives, where early design decisions strongly con…

arXiv:2606.00008v1 Announce Type: new Abstract: Multi-objective molecular optimization requires searching vast chemical spaces under conflicting objectives, where early design decisions strongly constrain downstream outcomes. Existing methods typically rely on a single policy or fixed scalarization, which limits their ability to represent diverse trade-offs and to explore multiple promising design trajectories. We propose ATOM, a multi-agent framework that formulates molecular optimization as a tree-structured search. Each node corresponds to an atomic operation and hosts an agent specialized for a particular objective or decision context. Agents coordinate along different paths of the tree rather than enforcing a global consensus, enabling the method to maintain and compare alternative molecular evolution trajectories. A global memory of past optimization behaviors further supports balanced exploration and exploitation across objectives. This tree-structured interaction enables reasoning over long-horizon dependencies inherent in molecular design. Experiments on challenging multi-objective benchmarks involving activity, synthesizability, and ADMET-related properties show that ATOM consistently achieves improved Pareto coverage and hypervolume over strong baselines. These results demonstrate the effectiveness of pathwise multi-agent coordination for molecular optimization. Code is available at https://anonymous.4open.science/r/ATOM-41CE.

arXiv:2606.00007v1 Announce Type: new Abstract: As AI agents transition from isolated tools to collaborative participants in shared knowledge ecosystems, governing collective knowledge curation beco…

arXiv:2606.00007v1 Announce Type: new Abstract: As AI agents transition from isolated tools to collaborative participants in shared knowledge ecosystems, governing collective knowledge curation becomes a critical challenge. Human platform governance mechanisms do not transfer directly: agent statelessness undermines deterrence-based sanctions, model homogeneity violates independence assumptions underlying crowd wisdom, and sycophancy collapses deliberative consensus. We propose a deliberative curation protocol combining three governance layers: (1) a knowledge artifact lifecycle formalized as a labeled transition system; (2) reputation-weighted deliberative voting integrating Beta Reputation with EigenTrust amplification; and (3) graduated sanctions adapted for stateless agents, including broken agent handling distinguishing malfunction from adversarial behavior. We evaluate the protocol through agent-based simulation with 100 agents across seven behavioral archetypes under two adversity scenarios (30 seeds, paired t-tests). The protocol trades modest precision under benign conditions for substantially better resilience under adversity: 0.826 vs 0.791 for majority vote under moderate adversity (p<0.001), widening to 0.807 vs 0.740 under stress (p<0.001). The protocol degrades roughly three times more slowly than majority vote. Ablation analysis identifies commit-reveal vote concealment as the most impactful single component (8.2-8.6pp precision improvement, p<0.001), outperforming reputation weighting and deliberation combined. Graduated sanctions were not exercised in simulation and remain empirically unvalidated.

arXiv:2606.00005v1 Announce Type: new Abstract: We present the Consilium Protocol, a Byzantine Fault Tolerance-derived architecture for structured multi-model AI deliberation that treats inter-model…

arXiv:2606.00005v1 Announce Type: new Abstract: We present the Consilium Protocol, a Byzantine Fault Tolerance-derived architecture for structured multi-model AI deliberation that treats inter-model disagreement as epistemic signal rather than error. The protocol assigns engineered cognitive personas to language models -- separating what a model is from how it reasons -- and introduces an In-Sample/Out-of-Sample validation framework adapted from quantitative finance to distinguish training-data consensus from empirically grounded conclusions. Across 1,478 deliberation sessions spanning 32 topics in 10 domain categories, we demonstrate that (1) the cognitive persona, not the underlying model, determines epistemic behavior: free edge-inference models costing 0.0002 USD per batch produced comparable analytical output to frontier models costing 10.69 USD; (2) RLHF alignment training creates measurable, domain-specific epistemic blind spots -- contested policy topics exhibit 12.3 percentage points less adversarial challenge than settled science topics, and AI safety topics show asymmetric bias ($\Delta$=11.6%) where models challenge claims that AI is dangerous far more vigorously than claims that AI risk is overstated; (3) the protocol exhibits no directional bias of its own (immigration $\Delta$=2.3%, renewables $\Delta$=1.2%); and (4) out-of-sample evidence retrieval validated 239 claims with 100% evidence retrieval and surfaced 167 blind-spot discoveries invisible to training-data deliberation. Run-to-run reproducibility across randomized model$\times$persona assignments averages $\pm$2.2% standard deviation. Total cost for the complete battery including all overhead: 217 USD. We release the protocol specification under MIT license to enable independent verification.

arXiv:2606.00002v1 Announce Type: new Abstract: Mixed-Integer Linear Programming (MILP) decision engines routinely output nominally optimal plans for high-stakes industrial systems. Yet deployment r…

arXiv:2606.00002v1 Announce Type: new Abstract: Mixed-Integer Linear Programming (MILP) decision engines routinely output nominally optimal plans for high-stakes industrial systems. Yet deployment rarely matches solve-time assumptions: small perturbations in costs, demands, or resource availability can invalidate feasibility or trigger discontinuous shifts to qualitatively different solutions. We argue that this post-solve robustness gap is a missing layer in today's optimization pipelines and a missing evaluation dimension for learning-enabled decision systems. Rather than replacing robust optimization or stochastic programming, the proposed layer audits a solved incumbent and returns solver-backed evidence about how far that solution can be trusted. We formalize two central objects: (i) an $\epsilon$-near-optimal feasible neighborhood in parameter space, capturing when an incumbent remains feasible and near-optimal under perturbations, and (ii) solution smoothness in decision space, capturing whether nearby alternatives with small combinatorial edits remain competitive. We then synthesize the most relevant partial answers from sensitivity and stability analysis, robust optimization, neighborhood search, adversarial testing, and learning-based enhancements, and articulate an agenda for a unified post-solve robustness layer. Concretely, we call for certified inner approximations around the incumbent, probabilistic robustness estimation with calibrated uncertainty, adversarial robustness margins, and learning-based prediction and explanation aligned with solver-backed verification. We conclude with a compact reporting template and evaluation protocol that would make robustness a first-class output of decision engines.