arXiv AI

arXiv:2610.04693v3 Announce Type: replace Abstract: Agents are entering finance, healthcare and law, sectors where a violation leaves no lexical signature and carries real penalties. Whether an omission is material, or a disclosure sufficient, depends on what the response left out. Probing such an obligation means finding responses one minimal edit from flipping compliance, and every probe costs a generation and two adjudications, so the binding constraint on regulatory red-teaming is sample efficiency, not volume. We introduce Penumbra, an adversarial search that walks from a verified anchor under an expanding edit budget until a two-evaluator committee changes its verdict, and emits the two adjacent responses that straddle the change. Allocation is adaptive, and the objective is coverage of the defeat surface: distinct (obligation x defeat mode) cells resolved per candidate. At matched budget, adaptive allocation reaches uniform allocation's full-budget coverage on 59% of the candidates; at equal records it covers 1.43x the defeat modes of naive enumeration, and the gain is confined to the axis it targets. On 60 screened obligations of a financial advisory constitution, Penumbra returns 144 pairs, each a compliant and a violating response that the committee places on opposite sides of the boundary, differing by a handful of words where a model asked for both directly produces texts sharing almost nothing. A second constitution, for clinical triage, reproduces this on 18 obligations: 49 pairs at the same tightness, with the same modes hardest. Pairs like these show where an obligation's own terms stop deciding, which is what an agent deployed under it must be tested against, and the search finds them at a cost that scales with the boundary, not the text.

arXiv:2609.35694v3 Announce Type: replace Abstract: We introduce the Continuous Embedding Diffusion Reasoner (CEDR), a training and inference pipeline for continuous latent diffusion models that achieves strong performance on mathematical reasoning and code generation. We learn compact answer representations from three hidden layers of the autoregressive Qwen3-4B model. A staged curriculum first trains the ELF-based diffusion backbone with teacher prompt conditioning, then initializes a compact prompt encoder through imitation and jointly adapts both networks. This replaces the large teacher contextual prompt encoder at inference with a compact learned Transformer. The multilayer answer representation also enables asynchronous inference, with different components denoised under separate clocks. We further adapt DiffusionNFT to learned self-conditioning guidance, enabling reinforcement learning with verifiable rewards. Controlled ablations evaluate the effects of representation design, prompt training, and denoising schedules. CEDR outperforms recent continuous-diffusion baselines at comparable backbone scales, including before reinforcement learning. With a 638M-parameter denoising backbone and DMD2-style stochastic sampling, post-NFT CEDR-L achieves {pass@1, pass@8} accuracies of {68.97%, 80.82%} on GSM8K and {32.40%, 53.80%} on MATH500 at 64 denoising steps per sample, and {37.56%, 51.00%} on HumanEval+ and {26.96%, 39.92%} on MBPP+ at 128 steps per sample. Code and model weights are available at https://github.com/chengxiang/CEDR and https://huggingface.co/xc91/CEDR, respectively.

arXiv:2609.34575v2 Announce Type: replace Abstract: Offline goal-conditioned reinforcement learning (GCRL) learns goal-directed policies from reward-free data, but in long-horizon tasks, goal-conditioned value functions often provide unstable guidance due to sparse rewards and discounting. Hierarchical methods partially mitigate this issue via subgoal decomposition; however, high-level decision-making still relies on noise-sensitive value estimates, leading to unstable behavior in complex environments. We address this limitation by proposing \textbf{D}iffusion \textbf{S}ubgoal \textbf{P}lanning (\textbf{DSP}), a diffusion-based framework for high-level subgoal generation. DSP casts high-level planning as guided generative inference over goal-conditioned subgoals and learns both conditional and unconditional flows, enabling classifier-free guidance to introduce a goal-directed bias at inference time. By removing explicit value-based guidance from high-level planning, DSP generates reachable and goal-directed subgoals through a generative model while retaining hierarchical execution. Experiments on offline GCRL benchmarks demonstrate that DSP outperforms prior methods on a range of navigation and manipulation tasks, with particularly strong performance in maze environments that require multi-step subgoal planning.

arXiv:2609.34540v2 Announce Type: replace Abstract: Ontology Learning (OL) from text has advanced with the emergence of Large Language Models (LLMs), but it remains challenging due to the limited availability of annotated training data and the difficulty of adapting LLMs to perform OL effectively. We address this via APOLO - Automatic Prompt Optimization for Ontology Learning, by casting OL as an explicit prompt optimization problem over LLM modules. To obtain training data, we employ a multi-agent system that generates text-ontology pairs from existing expert-curated ontologies. We then propose two ontology learner architectures: a greedy and an autoregressive learner, and optimize both using GEPA, a greedy evolutionary prompt optimizer built on DSPy. Experiments on two ontologies - a biomedical (DOID) and a plant ontology (PO) show consistent improvements after optimization across nearly all model and mode combinations, with autoregressive learners achieving the largest gains. Our results demonstrate that prompt optimization is a viable and lightweight alternative to fine-tuning for OL, and that the autoregressive formulation better captures ontological structure than the greedy approach.

arXiv:2609.32002v2 Announce Type: replace Abstract: The rank $r$ in LoRA is widely treated as a capacity control: a smaller rank is assumed to yield a simpler model that generalizes better. We show that, under hard per-factor norm budgets---the idealization of the weight decay and norm control used in practice---this intuition breaks down. The reason is structural: under such budgets, the updates LoRA can reach are exactly the matrices of rank at most $r$ inside a nuclear-norm ball, and every complexity and displacement functional we analyze is maximized over this set by a rank-one update---so the rank cap never binds. The consequences follow directly. The linear-readout model class we study is identical for every $r \ge 1$, its Rademacher complexity carries no dependence on $r$, and the distance the adaptation can move the source distribution obeys a rank-independent upper bound that we show is sharp. If rank does not control capacity, where does it act? We identify two places. Statistically, replacing the per-factor budgets with a joint budget on the product restores a data-dependent, rank-sensitive complexity bound---though the gain appears only for well-spread feature distributions, and the worst case remains rank-free. Spectrally, rank sets the price of adaptation: canceling the leading singular directions of the pretrained weight requires both sufficient rank and sufficient budget. We bound the smallest rank achieving a desired source--target alignment, with upper and lower bounds that match under two-sided spectral decay. Together, these results recast rank as governing which updates are reachable and what cancellation costs---not how much capacity the model has.

arXiv:2609.31133v3 Announce Type: replace Abstract: High-fidelity atomistic evolution over long timescales requires more than observing the current crystal configuration. Instantaneous atomistic snapshots are often incomplete: locally similar configurations can correspond to different hidden dynamical contexts, future event preferences, and waiting-time scales. We argue that this snapshot ambiguity makes long-horizon atomistic evolution fundamentally a memory-based world-state restoration problem. To address this, we introduce AtomWorld-Mem, a memory-restored atomistic world model that recovers the latent world state missing from instantaneous crystal snapshots. AtomWorld-Mem treats the evolving alloy as an AtomWorld: spatial encoders write multi-scale atomistic keyframes from dense local topology and sparse long-range defect context, while short-term event memory and long-term structural memory integrate these keyframes across time to restore a future-predictive evolutionary state. The restored state is used to prioritize legal vacancy-mediated events under single-event Kinetic Monte Carlo (KMC) constraints, while event legality, physical execution, and residence-time updates remain governed by the underlying simulator. Empirically, AtomWorld-Mem improves long-horizon atomistic progress under fixed microscopic event budgets while maintaining high-fidelity evolution across energetic, structural, and vacancy-transport observables. It further transfers zero-shot across diverse unseen alloy-temperature AtomWorlds, suggesting that the learned memory-restoration mechanism captures reusable principles of hidden-state inference rather than a system-specific local energy heuristic. These results position memory-restored world-state modeling as a promising route toward efficient, physically grounded, and transferable atomistic evolution.

arXiv:2609.16752v3 Announce Type: replace Abstract: Cognitive Field Theory describes cognition as memory-dressed collective dynamics, in which slow relaxation modes support a persistent cognitive field. By connecting non-Markovian memory dynamics to discrete recurrent state evolution through an extended state, we develop a Cognitive Field Network (CFN), a recurrent Transformer architecture with hidden-field re-entry, \( \Phi_{n+1} = F_\theta(X_{n+1},\Phi_n) \). Rather than prescribing an explicit memory operation, the CFN allows the full token-resolved hidden field to re-enter the next computational cycle. We find that learning organizes this pathway into a functional channel for persistent, content-dependent internal states, with temporal persistence systematically controlled by the recurrent training horizon. The learned dynamics generalize beyond this horizon: semantic continuation sustains the recurrent state without explicit answer replay, whereas unsupported states exhibit finite passive relaxation. Periodic re-exposure to relevant input renews the surviving field, producing an approximately stationary nonzero regime over extended recurrent trajectories. Unrelated-input and recurrence-off controls fail to reproduce this behavior, while near-paraphrased input produces weaker renewal, revealing the dependence of persistence on both field re-entry and input relevance. These findings connect memory-dressed field formation, input-driven reorganization, and recurrent state continuity within a unified dynamical framework. The CFN thus provides an experimentally controllable platform for studying persistent, history-dependent cognition without a separately prescribed memory system.

arXiv:2609.15089v2 Announce Type: replace Abstract: In human conversation, empathy involves not only recognizing a partner's emotion but also regulating it, listeners identify the emotional state, select a suitable regulation strategy, and implement it in their reply. Current large audio-language models (LALMs) largely map perceived emotion directly onto a response, skipping this regulation process. As a result, their responses tend to mirror the user's affect or offer generic sympathy. We propose ER-EDF, a psychology-grounded framework for empathetic dialogue that follows the three stages of Gross's Extended Process Model of emotion regulation, identifying the user's emotion from speech, selecting a regulation strategy matched to that emotion, and implementing the strategy through a LALM. The framework is model-agnostic and integrates seamlessly into existing LALMs. We further construct a spoken empathetic dialogue dataset and introduce empathy-aware evaluation metrics beyond lexical matching. Experiments across five LALMs and two datasets show that ER-EDF consistently improves empathetic response quality in both automatic and human evaluations. These results suggest that modeling how humans regulate others' emotions, rather than only how they perceive them, is key to empathetic spoken dialogue, paving the way for psychologically grounded empathetic AI.

arXiv:2609.12769v2 Announce Type: replace Abstract: Editing is a core component of video production, requiring creative planning and decisions under multiple constraints. Here, we report methods for agentic tooling for automated video editing across three tasks varying in editorial goal, complexity and creativity, namely scene previews, video summaries and cinematic trailers. We evaluate the outputs and discuss implications for automation and agency.

arXiv:2609.09306v3 Announce Type: replace Abstract: This paper investigates the hypothesis that the first-order structure of physical interactions (Jacobians) shapes the structure of phenomenal experience. Two measures of Jacobian structure are introduced: transparency, the effective rank, which counts the independent differences that make a difference; and integrity, the normalised algebraic connectivity, which measures how hard a system is to split. Applied to a series of worked examples, the framework yields correlates of: (1) experiences that overlap without systems merging; (2) the boundaries of a system, which are selected by focus and limited by noise; (3) temporal thickness, the persistence of the past into the present, lengthened by a spread of timescales; (4) spatial structure under convolution, where unity at scale needs long-range connections; (5) the distinction between what is vivid and what is obscure, for errors and attention heads; (6) the incoherence of a randomly initialised network, as a structural model of James's "blooming, buzzing confusion"; (7) distinct versus confused ideas; (8) learning as accumulated experience; and, conjecturally, (9) the contrast between memory as duration in brains and as storage in computer hardware. The measures can be computed at scale in artificial networks and estimated from perturbational data in brains.

arXiv:2608.23644v2 Announce Type: replace Abstract: Large language models (LLMs) are becoming routine instruments of scientific research, assisting with literature synthesis, hypothesis development, coding, and formal reasoning. Their use raises a central epistemic question: when parts of scientific reasoning are delegated to an artificial system, what conditions must remain under human control for the resulting knowledge claims to retain epistemic legitimacy and accountable authorship? This paper develops a normative and conceptual framework for analyzing such delegation. Scientific reasoning is treated as a distributed process in which the origin of a contribution may vary between human and machine, while responsibility for its acceptance into the scientific record remains human. The framework distinguishes content origin $O(g)$, completion of human verification $V(g)$, responsibility assignment $R(g)$, accountable human ownership $M(g)$, and epistemic outcome $E(g)$. These constructs separate the provenance of a claim from the process by which it is checked, the epistemic outcome of that checking, and the human responsibility attached to its disposition. The central proposition is that the ethical boundary of LLM-assisted research is determined primarily by adequate verification and accountable human ownership rather than by the degree of machine involvement itself. On this basis, the paper develops the notion of an \emph{epistemic audit}: a structured record of delegation, verification, provenance, and responsibility intended to make AI-assisted reasoning transparent and reviewable. The resulting framework provides a formal vocabulary for distinguishing responsible cognitive delegation from the transfer or neglect of epistemic responsibility in scientific research.

arXiv:2608.21755v2 Announce Type: replace Abstract: Long-horizon agents require more than retrieval over stored conversations: they must preserve source evidence, revise outdated knowledge, and distinguish relevant memories from sufficient support for an answer. We present ECHO (Embodied Context & History Orchestration), an auditable dual-path memory system. A fast path captures immutable events and serves multi-route recall, while asynchronous workers consolidate experience into revisable state and rebuild derived indexes. Source provenance, temporal authority, and answer realization are explicit boundaries. The service supports original-source packets with evidence-use checks and disables model-based reranking by default. For the latest reported accuracy, the authors confirm mixed retrieved inputs comprising original dialogue and memory summaries, answered by Qwen3-8B with NF4 quantization. In the latest author-supplied five-system aggregate evaluation, ECHO reports 56.27% answer accuracy, 98.04% source Hit@10, 93.58% macro source Recall@5, and 13.92% hallucination flags, with 19.54 ms mean retrieval latency. Its reported accuracy exceeds Mem0 by 4.53 percentage points in this snapshot. The results are descriptive aggregates; matched question-level evaluation and generation latency remain to be established. We separate these observations from earlier published experiments and engineering regressions.

arXiv:2607.28050v2 Announce Type: replace Abstract: Automating industrial CAD design and manufacturing places distinctive demands on multimodal foundation models: the model must see engineering drawings and 3D geometry screenshots, write correct parametric-modelling scripts and Windows COM API code, and cover the full range from single parts to assemblies. General-purpose multimodal models fall short on these tasks, while single-task fine-tuning is too narrow to support the diverse calls that upper-layer agents issue. We build IndustryForge-27B on top of Qwen3.5-VL-27B by curating and integrating six industrial-CAD sub-corpora totalling $\sim$52k multimodal samples---CAD Visual QA (CAD-VQA), parametric CAD code (text2cadquery), assembly-level CAD code (text2cadquery-assembly), and three COM sub-corpora for Inventor / SolidWorks (com_2d / com_3d / com_assembly)---and training with a unified multi-task SFT recipe. Across four CAD-domain benchmarks IndustryForge-27B lifts the base model by $+33.65$~pp on average and outperforms the strong closed-source model GPT-5.4 on all four; across eleven general-capability benchmarks it retains, and slightly improves upon, the base model ($+1.56$~pp mean, no catastrophic forgetting). IndustryForge-27B will serve as the common substrate for downstream industrial-agent projects, providing a unified starting point for a full-stack industrial agent that spans from CAD design to industrial-software operation, from parts to assemblies, and from single-shot generation to closed-loop self-improvement. Huggingface model: https://huggingface.co/Nianchen/IndustryForge-27B

arXiv:2607.22854v2 Announce Type: replace Abstract: AI agents are enabling a new paradigm of agent-augmented real-time communication (RTC), where humans focus on high-level collaboration, while agents autonomously retrieve, analyze, and generate information in real time to support their interactions. These apps enable new experiences across various domains: for example, when corporate employees co-author a legal document, their agents can discuss and draft on their behalf, sparing them the burden of manually reviewing each other's work. As existing cloud-based agents suffer from privacy risks and unscalable server costs, on-device agent-augmented RTC offers a promising alternative. However, this on-device paradigm introduces a new networking challenge: contention between concurrent traffic flows generated by humans (for live video streaming) and agents (for sending context files for analysis). We design HFS, a framework to ensure both high live video quality and low agent response latency in agent-augmented RTC apps. We achieve the goal through an app-guided multi-flow transport approach, where a unified app-layer orchestrator jointly controls the sending rates of live video and agent context flows based on their heterogeneous app requirements. Our prototype built atop WebRTC and llama.cpp demonstrates that HAFS outperforms baselines, achieving 1.5x higher video quality while reducing agent response time by 31%.

arXiv:2607.22375v2 Announce Type: replace Abstract: Large Language Models (LLMs) have significantly advanced the automation of scientific discovery. However, existing systems share a core limitation: they optimize ideas independently for either Quality or Diversity. This often results in closely related ideas or large sets of trivial, unsound, or unclear concepts. We instead argue that research ideation should be framed as a conjunction of Quality and Diversity objectives, i.e., a Quality-Diversity (QD) search. Accordingly, we introduce IDEAgent, a multi-agent framework that tracks idea evolution through lineages. We jointly drive Quality using multi-objective feedback for repair and refinement, while Diversity is achieved through lightweight sequential memory and explicit comparison against completed ideas, historical variants, and rejected proposals. To evaluate this joint objective, we develop Yield, a metric that computes the largest mutually diverse set of ideas satisfying predefined quality thresholds. Across 32 topics spanning 8 CS domains, IDEAgent outperforms the best baseline by 3.89x on Yield, while achieving Yield of at least 2 on 8x as many topics. We further analyze quality improvements, showing that repair and refinement improve logical rigor and clarity while preserving non-obviousness. Lastly, we extend IDEAgent to two algorithm discovery tasks for verifiable quality judgment and find that it still consistently outperforms all baselines, and yields the largest set of high-quality and diverse programs that beat a trivial/standard baseline. To encourage future research on QD-search-based ideation, we open-source IDEAgent at https://github.com/declare-lab/IDEAgent.

arXiv:2607.13899v2 Announce Type: replace Abstract: We propose the AIMO Interpretability Challenge, a competition on distinguishing robust from spurious reasoning in frontier mathematical language models based on the models' internal mechanisms. The challenge is motivated by a central limitation of standard reasoning benchmarks: strong final-answer accuracy does not reveal whether a model relies on stable reasoning mechanisms or exploits brittle reasoning shortcuts. Building on AI Mathematical Olympiad (AIMO) problems and submissions, together with resources from the Fields Model Initiative, the competition will provide (1) newly-published olympiad-level math reasoning problems and their symbolic representations, allowing generation of novel functional variants, (2) access to frontier reasoning models, and (3) assessments of models' adversarial robustness on these problems. Participants will use these resources, along with our computing infrastructure support, to develop methods for identifying which models solve problems robustly. Our competition will also create a new, open robustness benchmark and baseline systems, aiming to provide a lasting foundation for standard benchmarking in mathematical reasoning and interpretability. Scientifically, the competition connects interpretability and generalization research around a central question in AI research: can we determine if, and to what extent, the decision-making of frontier AI models is generalizable and thus, reliable?

arXiv:2607.01767v3 Announce Type: replace Abstract: Long-horizon language agents make interdependent decisions across multiple rounds, forming growing planning graphs in which later decisions depend on earlier states, observations, and tool outputs. Errors in these graphs can therefore propagate through subsequent decisions and amplify over long rollouts. Correcting the most visible failure may therefore fix a symptom while leaving the core that drives downstream errors unchanged. Replaying the entire planning graph provides the opposite extreme, but becomes increasingly expensive as the graph grows and forces an LLM to reason over substantial irrelevant context. We study planning-graph repair: given a failed rollout, the goal is to identify and correct the compact core responsible for continued error propagation while preserving the remainder of the graph. We first evaluate a range of practical engineering repair strategies, including single-error and TopK repair, temporal windows, neighborhood expansion, cascade-aware repair, and full-graph LLM correction. We then propose ReCore (Repair the Core), which models the coupled propagation of node and edge errors to identify the core of a failed planning graph. Rather than repairing the largest observed errors or expanding a fixed local neighborhood, ReCore selects a connected core whose correction maximally reduces residual error amplification, and exposes only this core to the LLM for diagnosis and repair. We also theoretically establish a bound on long-horizon planning regret. Extensive experiments on synthetic Agent Calling-Tree graphs and the Who\&When attribution benchmark show that ReCore improves long-horizon stabilization and root-cause localization by targeting high-amplification repair regions, matching full-context recovery with up to $7.4\times$ fewer tokens for every successful repair.

arXiv:2606.31422v3 Announce Type: replace Abstract: Long-horizon language agents enable autonomous decision-making in complex environments by planning and executing sequences of interdependent actions. To act reliably, these agents must maintain an accurate world model that tracks the environment's evolving state and supports subsequent decisions. However, as interactions accumulate, stored beliefs can become outdated or incorrect, causing agents to plan and act on assumptions that no longer reflect the environment. Such errors are difficult to resolve through additional reasoning or self-reflection alone, because the information needed for correction must be obtained from the environment. Actively probing the environment therefore offers a direct way to verify and correct these beliefs. To this end, we introduce ENVPROBE, a framework that enables agents to actively explore their environments and correct inaccurate beliefs during long-horizon execution. Specifically, ENVPROBE prioritizes belief fields for verification based on task relevance and potential errors. It then selectively probes the environment to retrieve the actual value of a chosen field and incorporates the observation into the agent's world model. With the updated beliefs, the agent revises its plan and continues execution based on the newly acquired environmental information. Extensive experiments across three controlled environments demonstrate that ENVPROBE substantially improves terminal world-state accuracy compared with agents operating without environment probing, leading to more reliable long-horizon decision-making. These results demonstrate the importance of actively verifying and correcting beliefs through environmental interactions for maintaining accurate world models in long-horizon language agents.

arXiv:2606.27806v4 Announce Type: replace Abstract: Language agents, such as ReAct, Reflexion, and RAP, implicitly predict how the world will change as they plan and act, using imagined state transitions to guide their decisions. These predictions are encoded in the agents' backbone LLMs as internal beliefs about the environment, effectively forming an implicit world model for multi-step planning. However, hallucinated state information can become embedded in this world model, leading to persistent inaccuracies that influence subsequent decisions. Traditional parametric world models, such as Dreamer and MuZero, learn environment dynamics through explicit transition models, but their limited model capacity makes them difficult to apply directly to modern language-agent planning. We study this tradeoff in graph-structured planning environments and seek to combine the strengths of both paradigms. We propose Hybrid World-Model Planning (HYBRID-WM), which preserves the language agent's semantic planning capabilities while leveraging a lightweight parametric world model for more accurate transition predictions. Specifically, the parametric model constructs a compact planning skeleton to guide action generation while maintaining consistency between the agent's imagined transitions and the model's predictions. Experiments across four graph-structured planning benchmarks demonstrate that HYBRID-WM consistently improves task success and reduces hallucinated-state propagation with modest computational overhead. These findings highlight the effectiveness of combining semantic planning with lightweight parametric grounding for reliable long-horizon language-agent planning.

arXiv:2606.07000v2 Announce Type: replace Abstract: Recent post-training methods, particularly Reinforcement Learning with Verifiable Rewards (RLVR), have significantly enhanced the reasoning ability of Large Vision-Language Models (LVLMs). However, the sparse nature of verifiable rewards provides little token-level supervision for failed rollouts, often leading to inefficient exploration in complex multimodal reasoning tasks. Although policy distillation can offer dense guidance, external teacher based methods introduce substantial computational overhead, while answer conditioned tuning methods may expose answer-level information and induce shortcut-like generation behavior. To address these limitations, we propose PTD-PO, a Privileged Tutoring Distillation Policy Optimization framework for RLVR that provides dense guidance without exposing the answer to the student policy. Specifically, PTD-PO constructs structured privileged hints from spatial attention guidance and intermediate textual reasoning steps, and uses them through in-context learning to produce step-wise token-distribution supervision. The student is still optimized under the original answer-free context, and its failed rollouts are aligned with the hint-augmented reference model at the token-distribution level. To further stabilize distillation under the distribution shift between guided and unguided contexts, we introduce a Top-K Jensen-Shannon divergence objective that focuses alignment on informative token probabilities while reducing memory overhead. Experiments on LVLMs ranging from 2B to 8B parameters show that PTD-PO consistently outperforms RLVR and distillation baselines, mitigates entropy collapse, and improves complex multimodal reasoning performance.