Artificial Intelligence
MiniRep: Robust Reputation-Based Aggregation for Multi-Agent Debate
Jiaming Zhang, Yuwan Liu, Yue Huang et al. (+1 more)
Autonomous
agents powered by large
language models (LLMs) are rapidly evolving into an open agentic ecosystem. To support trustworthy collaboration, industry initiatives increasingly assess
agent reputation from past behavior and provide performance leaderboards. However, reputation derived from past performance may not reliably predict an
agent's behavior on new tasks, particularly when malicious
agents can adapt their behavior and influence other
agents during collaboration. We study reputation in multi-
agent debate (MAD), where multiple
agents answer the same query, debate to improve their answers, and aggregate them into a final output. We present MiniRep, a reputation-based aggregation system for MAD under malicious
agents. To ground our threat model in established research, we construct an attack taxonomy drawing on reputation-system attacks and software-testing mutation operators, covering strategic exploitation of reputation and subtle corruption of
agent proposals. Guided by this taxonomy, MiniRep evaluates
agents based on both their behavior on the current task and their reputation over time, while preventing groups of
agents with highly similar responses from dominating the final decision. We assess MiniRep across diverse tasks, LLM-
agent compositions, corruption placements, and attack types drawn from our taxonomy. Our experimental results show that, MiniRep outperforms both conventional MAD aggregation and conventional reputation-based approaches on MATH no matter being attacked or not. Also, under a heterogeneous 10-
agent setting on MATH, MiniRep outperforms all baselines in all 28 attack conditions.
Read the full abstract ▾
All authors Jiaming Zhang, Yuwan Liu, Yue Huang, Sisi Duan
Artificial Intelligence
ANI: Adaptive Numerical Injection for Unifying Semantic and Arithmetic Representations in Numerical Reasoning
Jinsung Jeon and Seung-won Hwang
Precise numerical
reasoning with Large
Language Models (LLMs) is essential for expanding their applicability to complex real-world tasks. However, text-based tokenization often fragments numbers, significantly hindering precise arithmetic
reasoning. Meanwhile, numerical
embeddings, despite arithmetic precision, rely on context-agnostic substitution that disregards the semantic role of numbers as identifiers. To combine the complementary strengths, we propose ANI (Adaptive Numerical Injection), a hybrid framework that governs the selective injection of numerical features based on the semantic context. By employing a context-aware gating mechanism, we selectively inject numerical
embeddings (specifically FoNE) into the latent space, explicitly preserving nominal identifiers while enhancing quantitative operands. Through extensive evaluations across various LLMs, we demonstrate that ANI enhances MATH performance by 9.5 points over the official reference model, while maintaining robust performance on general linguistic
benchmarks.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.SE
EngramBench: A Capability-Grounded Benchmark for Skill-Evolution Harnesses
Zhixuan Tan, Pengjie Gu, Zhao Li et al. (+4 more)
While large
language models have achieved remarkable success in isolated code generation, authentic software engineering requires sustained
reasoning, complex state management, and continuous cross-domain abstraction. However, current evaluations of skill
evolution in autonomous
agents suffer from a critical identifiability problem: they structurally confound genuine capability abstraction with rote solution leakage (i.e., copying highly similar code from historical training data). To resolve this, we introduce EngramBench, a rigorous, capability-grounded
benchmark governed by the strict axiom of capability overlap without solution overlap. Comprising 30 diverse learning tasks and 13 unseen transfer tasks, EngramBench challenges
agents to navigate interactive, multi-hour development cycles driven by LLM-simulated users. Our extensive evaluation across 48 multi-hour execution trajectories – corroborated by human-expert validation – reveals a profound insight into procedural
memory. We demonstrate that static skill banks do not magically bypass the "last mile" of exact code implementation, which remains bottlenecked by the base model's inherent
reasoning limits. However, they serve as an indispensable execution compass. By navigating
agents away from catastrophic,
token-heavy trial-and-error, genuine capability abstraction slashes redundant context bloat and reduces overall coding time by over 55%. Ultimately, EngramBench shifts the evaluation paradigm from trivial pattern matching to the verifiable measurement of deep, cross-domain capability transfer.
Read the full abstract ▾
All authors Zhixuan Tan, Pengjie Gu, Zhao Li, Yihan Hu, Xu He, Dong Li, Jianye Hao
Artificial Intelligence · Cross-listed from cs.CR
Faithful Dual-constrained Erasure for Robust LLM Safety Alignment
Jiaqing Li, Shide Zhou, Zhibo Zhang et al. (+3 more)
Machine unlearning has emerged as a crucial mechanism for removing hazardous knowledge and enforcing safety
alignment in Large
Language Models (LLMs). However, recent studies reveal a persistent security risk: unlearned models remain highly vulnerable to retraining attacks, where suppressed malicious behaviors rapidly resurface after benign fine-tuning. In this work, we investigate the optimization dynamics of unlearning and identify that this vulnerability stems from shallow
alignment. Rather than effectively erasing target knowledge, models often exploit a shortcut by activating previously dormant parameters to act as spurious suppressors, forming a fragile inhibitory shell over intact malicious representations. To address this issue and enforce authentic
memory deletion, we propose FDCU, a novel dual-constrained subspace projection framework. FDCU restricts parameter updates through a highly scalable, element-wise dual-masking rule: it preserves general knowledge
manifolds via Fisher Information and strictly prohibits the abnormal activation of spurious suppressors via the Principle of Minimal Functional Intervention (PMFI). By reliably blocking the model's ability to superficially hide knowledge, FDCU promotes the authentic dismantling of target representations. Extensive experiments across specific knowledge erasure and safe output control tasks demonstrate that FDCU achieves state-of-the-art robustness against retraining attacks while maintaining near-lossless general utility, ensuring durable safety for LLMs.
Read the full abstract ▾
All authors Jiaqing Li, Shide Zhou, Zhibo Zhang, Yuxi Li, Tianlong Yu, Kailong Wang
Artificial Intelligence · Cross-listed from cs.LG
A Time-Aware Bag-of-Receptive-Fields for Interpretable Irregular Time Series Classification
Francesco Spinnato
Irregular time series, characterized by non-uniform sampling intervals, missing observations, and variable lengths, are ubiquitous in healthcare, mobility, and environmental monitoring, yet effective and interpretable classifiers for this setting are limited. Existing approaches often rely on imputation, which can obscure the temporal structure of the data, or require complex neural architectures that are opaque and difficult to explain. In this work, we extend the Bag-Of-Receptive-Fields (BORF), a fast, deterministic, and interpretable transform for time series, to the irregular setting. Our key contribution is a time-weighted normalization scheme in which each observation is weighted proportionally to its associated time delta, making pattern extraction sensitive to the actual temporal distribution of samples rather than only their index position. This requires deriving an efficient sliding-window recurrence for the time-weighted standard deviation, preserving the linear time complexity of BORF. We
benchmark the resulting method against state-of-the-art irregular time series classifiers on
datasets from the PYRREGULAR repository, demonstrating competitive classification performance with the added benefit of human-interpretable explanations.
Read the full abstract ▾
Artificial Intelligence
Effective Does Not Mean Useful: Conditional Functional Substitutability for Redundancy and Scaling in Transformers
Jiaheng Chen, Jiaxing Li, Yucheng Xiao et al. (+4 more)
Modern neural networks scale predictably, yet the mechanisms behind these regularities remain unclear. Neural redundancy is typically characterized by component importance or representational similarity, both indirect proxies. We view redundancy as an input-conditioned, dynamic relation: intermediate computational states are functionally redundant when they induce similar downstream responses. We introduce Conditional Functional Substitutability (CFS) to directly characterize such functional substitution. CFS exposes functional relations and reduction potential missed by conventional importance- and similarity-based measures. Across modalities and
Transformer families, CFS reveals systematic functional reorganization with scale. Controlled scaling further shows that performance gains need not track growth in substitutability, while fixed-capacity models with more independent functional structure perform better, providing a functional account of diminishing returns. Predicted CFS further enables dynamic computation with a better performance–computation trade-off than importance-based component selection, suggesting new directions for redundancy-aware computation and more efficient model scaling.
Read the full abstract ▾
All authors Jiaheng Chen, Jiaxing Li, Yucheng Xiao, Xinyong Cai, Juncheng Bu, Lan Yu, Tinghe Zhang
Artificial Intelligence · Cross-listed from cs.LG
From Benchmarks to Production: Transferring Time Series Anomaly Detection Methods for Electricity Production Monitoring
Nicolas Vautier, Paul Caron, Nardi Xhepi et al. (+4 more)
Accurate forecasting of electricity production is essential for maintaining the operational efficiency and strategic planning of energy utilities. In industrial settings, such forecasts are generated daily to ensure supply-demand balance and optimal management of production assets. However, the increasing complexity of modern power systems and data flows poses significant challenges for ensuring the reliability and consistency of these forecasts. This paper addresses the problem of anomaly detection in short-term production forecasts at EDF, formulated as identifying atypical intra-day patterns that may signal data quality issues or operational irregularities. We introduce TAMIS, a scalable and interpretable system that analyzes daily production time series to automatically detect anomalous days based on deviations from historical patterns learned from past data. Designed for human-in-the-loop workflows, TAMIS surfaces top-ranked anomalies through an automated daily newsletter, enabling efficient expert review and continuous monitoring. An extensive experimental evaluation on real-world industrial data demonstrates that TAMIS achieves the best accuracy-efficiency trade-off compared to baseline methods. To foster further research and reproducibility, we publicly release the anonymized application
datasets used in our study.
Read the full abstract ▾
All authors Nicolas Vautier, Paul Caron, Nardi Xhepi, Félicie Bizeul, Manel Boumghar, Christophe Degouy, Paul Boniol
Artificial Intelligence · Cross-listed from cs.LG
Trust the Critic More
Kaiyue Wen, Luke Bailey, Arvind Mahankali et al. (+1 more)
Standard
language model RL
algorithms credit every
token of a long rollout with the same advantage determined by the terminal reward. Actor-critic methods can provide finer-grained credit assignment, but learned critics are generally considered too inaccurate to trust when training LLMs with RL. In recent works, even when a critic is present, it is used only for baseline estimation, so every trajectory must be rolled out to its terminal reward. We introduce Actor-Critic with Action Chunking (AC2) that removes the need to roll every trajectory to completion. AC2 instead assigns credit to action chunks: short continuations of prefixes of past trajectories. A learned critic scores the state reached at the end of each action chunk, allowing the policy to update without observing a terminal reward. We make critic-based credit assignment reliable through three design choices. First, we introduce local readiness which uses critic-based updates on a problem only when the critic is sufficiently accurate on that particular problem. Second, when available, we provide the critic with a reference solution from a previous successful rollout. Third, we assign credit over action chunks of 10k
tokens rather than individual
tokens, giving the critic a more meaningful portion of the trajectory to evaluate. We train Qwen3-4B on FineProofs-RL using AC2 and evaluate on IMO-ProofBench. AC2 exceeds GRPO's peak validation score of 18.5% using 2.5x fewer decoding FLOPs. This gain comes from two sources, (1) AC2 requires 25% fewer training steps to reach this score, and (2) each step generates fewer
tokens because the policy does not need to continue every trajectory to completion. Conceptually, we demonstrate that we can remove the need to roll out every trajectory to completion, opening up a large previously unexplored design space for LLM RL
algorithms.
Read the full abstract ▾
All authors Kaiyue Wen, Luke Bailey, Arvind Mahankali, Tengyu Ma
Artificial Intelligence · Cross-listed from cs.LG
What Streaming Anomaly Detection Finds (and Misses) in Industrial Time Series
Magali Parrino, Antoine Ajenjo, Emmanuel Remy et al. (+2 more)
EDF relies on continuous monitoring of its power plants to detect anomalies as soon as they occur. Given the absence of a universally optimal streaming method in unsupervised settings, we compare streaming methods with state-of-the-art TSAD models deployed online on a real nuclear power plant
dataset. This work also evaluates Automated Anomaly Detection in a streaming context. Results show higher consistency for online TSAD and strong robustness from ensembling strategies.
Read the full abstract ▾
All authors Magali Parrino, Antoine Ajenjo, Emmanuel Remy, Pierre Stephan, Paul Boniol
Artificial Intelligence · Cross-listed from cs.CL
RAIM: Robust Aggregation of Inexpensive Models for Hallucination Detection
Elia Onofri and Roberto Di Pietro
Automatic evaluation of faithfulness increasingly relies on a large
language model acting as a judge, yet the most reliable judges are proprietary frontier models, costly and ill-suited to high-throughput monitoring. We investigate whether a panel of cheap open-weight judges (4–9B) can be aggregated to stand in for a frontier one, what the substitution sacrifices, and when it is worth making. We propose RAIM, an aggregation scheme robust to the members' correlated errors, coupling a cross-fitted stacked logistic regression with an admissibility test that, read from the members' own outputs, identifies when aggregating them improves on their best member and stays within reach of the frontier judge. We instantiate RAIM with ten judges from disjoint families across eight faithfulness
benchmarks. Against Claude Sonnet, the panel retains a median 93% of its Cohen's $\kappa$ and gives up only 2.9 points of balanced accuracy on average; read as paired differences, it clearly improves on one
benchmark and clearly worsens on three (only two by a non-negligible margin), leaving four unresolved. At a sixty-fourth of the frontier's inference price, the operative expense is a one-time in-domain calibration on 50–100 labelled records. The panel is also competitive with purpose-trained detectors on their home
benchmarks (within 1.3 accuracy points of GPT-4o and 1.9 of the LLM-AggreFact leader), and beats the strongest one we reran by 6 points on our grounded sets. Whether aggregation pays depends on the members themselves: where several capable members err on different items, the panel improves on its best judge and approaches the frontier; where one dominates, the stacker recovers the leader, and only there does the frontier remain materially ahead. Both conditions are read off the calibration set at no further cost, so a cheap panel can stand in for a frontier one wherever this audit admits it.
Read the full abstract ▾
Artificial Intelligence
Fyan: A Human–AI Harness with Semantic Auditing for Document-Level Formalization
Wei Zhao, Yangshuo Zou, Chengxiang Ding et al. (+5 more)
We present FYAN, a human–AI harness for document-level mathematical formalization. Rather than treating
theorems in isolation, FYAN coordinates an end-to-end workflow spanning specification, proof planning, logical review, Lean proof construction, knowledge curation, and validation, with support for independent supervision and human guidance. A central component is evidence-grounded semantic auditing, which assesses whether formal statements faithfully preserve their informal specifications. A
language model constructs structured evidence over local correspondences, omissions, scope, and logical relations, while a deterministic validator checks this evidence and produces reproducible judgments. When a substantive but admissible deviation is accepted, FYAN requires an explicit proof-transfer obligation connecting the formal statement back to a source-facing interpretation. With the same model (DeepSeek-V4.1-Flash) in every stage, FYAN proves 86 of 143 FormalTCS
theorems under a strict Lean check, against 69 for a general
agent harness, and raises the natural-
language proof score from 0.501 to 0.851. On ConsistencyCheck, its semantic audit catches more inconsistent statements than a direct LLM judge, both on labels verified against the source (recall 0.777 vs. 0.636) and on the original labels (0.873 vs. 0.820), and localizes each mismatch it reports to a specific hypothesis, conclusion, or scope. FYAN also built ODENumLib, a 9,355-line Lean library for the numerical analysis of ordinary differential equation.
Read the full abstract ▾
All authors Wei Zhao, Yangshuo Zou, Chengxiang Ding, Yifan Wu, Xuchuan Wang, Zimu Mao, Lei Zhang, Tao Luo
Artificial Intelligence · Cross-listed from cs.CV
Emergent Multi-View Geometry Through Self-Distillation
David Nordström, Thibaut Loiseau, Vincent Lepetit et al. (+3 more)
Over a century ago, Henri Poincaré argued that a motionless observer cannot acquire the notion of space. Yet, most visual representation learning methods operate on individual images, while those that leverage multiple views rely on RGB reconstruction, entangling geometry with appearance. We propose Poincar3, a self-supervised method that learns representations from multiple views through self-
distillation instead of RGB reconstruction. We combine masked patch and image-level
distillation with a teacher that observes additional views, enabling training from scratch without explicit 3D supervision. Poincar3 outperforms both previous single and multi-view self-supervised approaches such as DINOv3, MuM, and Muskie on correspondence estimation, camera pose estimation, and 3D reconstruction. Using a lightweight Poincaré adapter, we also find that our learned features encode camera motion more accurately than existing self-supervised representations.
Read the full abstract ▾
All authors David Nordström, Thibaut Loiseau, Vincent Lepetit, Michael Felsberg, Guillaume Bourmaud, Fredrik Kahl
Artificial Intelligence
Learning Process Rewards via Reasoning State Propagation
Kai Gan, Zi-Hao Zhou, Bo Ye et al. (+3 more)
Process reward models (PRMs) have demonstrated notable effectiveness in test-time scaling and reinforcement learning by providing fine-grained signals for evaluating intermediate
reasoning states, but their training relies heavily on costly process annotations. A natural way to alleviate this dependence is to complement limited process supervision with scalable outcome supervision. However, existing PRMs often model
reasoning prefixes independently, providing no explicit mechanism for effectively using final outcome to guide the learning of intermediate
reasoning states. We introduce
Reasoning State Propagation (RSP), which represents each
reasoning prefix with a binary validity state and models transitions between successive states across the
reasoning trajectory. Specifically, RSP predicts a break probability that a valid state becomes invalid and a repair probability that an invalid state returns to valid. By propagating these transitions, RSP connects intermediate states to the final state, allowing process annotations to supervise intermediate states while outcome labels supervise the final state and can provide learning signals to preceding steps. Across
reasoning search, response selection, and reinforcement learning, RSP consistently outperforms representative PRM baselines, with average improvements over Qwen2.5-Math-PRM of 5.6% in beam search and 2.1% in reinforcement learning.
Read the full abstract ▾
All authors Kai Gan, Zi-Hao Zhou, Bo Ye, Jian Zhao, Min-Ling Zhang, Tong Wei
Artificial Intelligence · Cross-listed from cs.LG
In a Streaming World, Should You Stand Still? A Comprehensive Benchmark of Anomaly Detection in Streams
Magali Parrino, Antoine Ajenjo, Emmanuel Remy et al. (+3 more)
Time series anomaly detection (TSAD) is increasingly deployed in streaming settings, where data arrive sequentially and may exhibit non-stationarity. As a result, several works from the recent literature propose streaming anomaly detection methods that rely on incremental updates to adapt over time. However, most of these approaches originate from the streaming outlier detection literature and largely ignore core characteristics of time series anomalies. Moreover, their empirical evaluation is typically conducted on synthetic or small-scale
benchmarks with limited diversity, making it unclear whether streaming methods are truly advantageous in realistic TSAD scenarios. In this work, we carry out the first large-scale experimental study comparing streaming and static TSAD methods under a unified streaming evaluation
benchmark. We consider a realistic setting in which an initial batch of data is available for model training, followed by online evaluation of both detection accuracy and computational efficiency. In addition, we propose a distribution-drift
dataset of real time series, called TSB- drift, to isolate scenarios where streaming updates are theoretically justified. Our results show that, contrary to common assumptions, static TSAD methods significantly outperform streaming approaches in most streaming settings. Such finding highlights a critical gap between the design of existing streaming methods and the requirements of modern TSAD, and calls for a rethinking of how streaming capabilities should be integrated into TSAD.
Read the full abstract ▾
All authors Magali Parrino, Antoine Ajenjo, Emmanuel Remy, Pierre Stephan, Pierre Senellart, Paul Boniol
Artificial Intelligence · Cross-listed from cs.SD
UniAE-MoE: A Unified Audio Encoder via Mixture of Experts
Shengbo Cai, Zhisheng Zhang, Zichao Nie et al. (+3 more)
Large Audio
Language Models (LALMs) rely on effective audio encoders for multi-task performance. We introduce UniAE-MoE, a unified audio encoder designed to model cross-domain audio representations and achieve outstanding downstream understanding performance via a Mixture-of-Experts (MoE) architecture. Specifically, we explore mainstream audio encoders and integrate those from Qwen2-Audio and Audio-Flamingo 3, which demonstrate superior downstream capabilities. To facilitate effective model fusion, we improve our encoder using SwiGLU with shared experts to decouple encoder networks, and we further introduce a two-stage instruction-tuning strategy to better adapt the model to diverse downstream tasks. Moreover, we propose the task-specific data scaling (TSDS) technique to enhance UniAE-MoE's understanding capabilities. On the XARES-LLM
benchmark, UniAE-MoE attains a score of 0.802, achieving state-of-the-art performance. It also delivers top-tier performance in the official Interspeech 2026 Audio Encoder Capability Challenge, further demonstrating robust generalization across diverse audio tasks. Together, these results validate the effectiveness of UniAE-MoE for unified audio understanding across
speech, music, and general audio domains.
Read the full abstract ▾
All authors Shengbo Cai, Zhisheng Zhang, Zichao Nie, Jing Peng, Jingran Xie, Zhiyong Wu
Artificial Intelligence · Cross-listed from cs.CV
MEND: Label-Free Detection, Localisation, and Correction of Latent Hallucination in World Models
Ali J Alrasheed, Aryan Yazdan Parast, Basim Azam et al. (+2 more)
World Models are appearing as the next major frontier in computer
vision. However, their robustness is currently largely unexplored. We identify the phenomenon of
hallucination in latent World Models: given a state and an action, the predicted next latent can decode to a scene that never occurs. Because the prediction is statistically ordinary and is fed back autoregressively by the model, the error is both silent and compounding. We study whether such latent
hallucination can be detected, localised, and corrected at inference time, on a frozen self-supervised world model in the absence of ground-truth error labels. We introduce Masked Empirical-Bayes Neural Denoising (MEND), a single conditional score network trained by denoising score matching on real transitions, whose score field serves three roles: its magnitude detects
hallucination, its per-
token field localises it to specific image patches, and it defines an inference-time correction direction. On two navigation environments MEND detects
hallucination with an AUROC of up to 0.80 without using actions, exceeding a single-Gaussian density baseline while also localising the error (per-
token AUPRC up to 0.87) and correcting it, all from one score field. Our correction reliably reduces single-step latent error and improves predictions. We identify that a part of the error is tangent to the data
manifold, hence, we focus on detection and localisation while highlighting promises of the correction.
Read the full abstract ▾
All authors Ali J Alrasheed, Aryan Yazdan Parast, Basim Azam, James Bailey, Naveed Akhtar
Artificial Intelligence
Reinforcing Multimodal Reasoning via Token-Level Perception-Grounded Advantage Estimation
Zhihan Zhang and Lizi Liao
Reinforcement Learning with Verifiable Rewards (RLVR) has improved the
reasoning capabilities of
Multimodal Large
Language Models (MLLMs), yet existing frameworks rely on coarse, sequence-level reward signals that lack the fine-grained supervision over the visually-grounded steps within a
multimodal reasoning chain. We investigate this gap through the lens of two
token-level metrics: visual dependency (i.e. how much a
token's prediction relies on the input image features) and predictive
entropy. Our empirical analysis reveals two key findings: (1) correct
reasoning chains exhibit a markedly sharper
entropy reduction as visual grounding intensifies, compared to incorrect ones; (2) pivotal
tokens, those whose misprediction triggers
reasoning collapse, are statistical outliers in the joint distribution of visual dependency and predictive
entropy derived from correct chains. Motivated by these findings, we propose
token-level perception-grounded advantage estimation (TPAE), which estimates
token-level advantages by measuring each
token's statistical consistency with the
vision-
entropy patterns of correct rollouts. TPAE leverages this granular score to modulate the sequence-level advantage, producing a fine-grained supervision signal that can be integrated into various RLVR frameworks. Extensive experiments on seven
benchmarks show that TPAE consistently outperforms leading strong baselines, yielding more stable and efficient optimization for
multimodal reasoning. The code is publicly available at https://github.com/Zhihan72/TPAE.
Read the full abstract ▾
Artificial Intelligence
Beyond the Remembered World: Predictive 4D Belief for Persistent Navigation in Evolving Worlds
Mingjian Gao, Zhaocheng Li, Haoyang Huang et al. (+7 more)
Persistent spatial
memory enables embodied
agents to navigate familiar environments across repeated visits. However, targets may move while unobserved, including during navigation, making remembered locations unreliable by the time an
agent arrives. Despite advances in
memory retrieval and state prediction, accounting for continued hidden world
evolution and revising beliefs under limited visibility remain challenging. We study Evolving-World Navigation, where
agents infer target locations from intermittent observations, predict their states at inspection time, and revise beliefs using visual evidence. We propose EvolvingNav, which constructs a time-indexed belief from timestamped 3D object histories through a structured persistence-relocation model. The belief distinguishes persistence at the last observed location from relocation to alternative locations and retains probability mass outside the known candidate set. An event-driven filter propagates the current belief as time elapses, forecasts target occupancy at candidate inspection times, and incorporates new RGB-D evidence. Negative observations downweight location hypotheses according to calibrated, visibility-conditioned detection probabilities, while evidence tracking prevents repeated use of the same observations. A frozen, zero-shot
vision-
language controller uses the updated belief to choose actions and replan. We further introduce EvoWorld-Bench, a
benchmark grounded in human activity traces, comprising 54 scenes and 803,680 tasks with controlled changes before and during navigation. In simulation and real-
robot experiments, EvolvingNav improves navigation success and search efficiency over the evaluated baselines. Paired experiments show the clearest gains under learnable temporal patterns, while ablations demonstrate the value of preserving uncertainty and incorporating visibility-aware evidence.
Read the full abstract ▾
All authors Mingjian Gao, Zhaocheng Li, Haoyang Huang, Wenqiao Zhang, Yingjie Niu, Hao Zhou, Chao Li, Juncheng Li, Siliang Tang, Yueting Zhuang
Artificial Intelligence · Cross-listed from cs.CL
DAGent: Evaluate-then-Grow Planning for Deep Research Agents
Hanwen Liu, Yuanfu Sun and Qiaoyu Tan
Deep research tasks require
agents to navigate large knowledge spaces, synthesize evidence across many sources, and adapt their plans as findings emerge. Directed acyclic graph (DAG)-based multi-
agent systems suit this setting because they support parallel execution and isolate each sub-task within a focused dependency context. Yet existing DAG-based
agents instantiate a task-level plan before execution and repair the graph only after failures or missing evidence are observed. This Plan-then-Patch strategy is brittle for deep research: the system commits most strongly when its evidence is weakest, and later revisions waste computation on branches that should not have been planned. We propose DAGent, a DAG-based multi-
agent framework with Evaluate-then-Grow incremental planning: an Orchestrator grows the task graph one batch at a time, conditioning each expansion on confidence and uncertainty signals from completed nodes. A hierarchical context layer propagates compact QueryDocs by default while preserving full execution traces for on-demand recall. The recorded DAG
topology admits structural RL signals that outcome-only recipes cannot define; DAGRPO, a GRPO adaptation, injects
topology-conditioned credit on Executor rollouts and a structural compliance regularization on Orchestrator plans. Across BrowseComp-Plus, GAIA, and xbench-DeepSearch, DAGent surpasses the strongest open-source baseline by 5.3 / 5.8 / 2.0 points at the Qwen3-235B-A22B scale, and the lead replicates across four open-source backbones and extends to GPT-5 at 327K context. At the Qwen3-8B scale, DAGRPO improves over a same-budget outcome-only GRPO baseline by 3.0 average Pass@1 points. A same-architecture comparison shows that evidence-conditioned planning reaches higher accuracy at lower per-task
token, tool-call, and step footprints than its Plan-then-Patch counterpart. Code: https://github.com/hanwenliu6825/DAGent
Read the full abstract ▾
Artificial Intelligence
Rep2Skill: Representation-Guided Skill Self-Evolution for LLM Agents
Kaixing Zhang, Changming Li, Yingdong Shi et al. (+5 more)
Textual skills enable large
language model (LLM) based
agents to accumulate reusable procedural knowledge without updating model parameters. Yet existing skill
evolution remains largely confined to the text space: an optimizer must diagnose success and failure patterns, and revise skills solely from long execution trajectories and sparse task outcomes. This text-only paradigm leaves the
agent's internal representations, which contain rich records of its evolving execution state, outside the skill optimization loop. We ask whether an
agent can improve its external textual skills by reflecting on its own internal representations. We introduce Rep2Skill, a representation-guided framework for self-
evolution on
agent skills. Specifically, upon the collected
agent rollouts, Rep2Skill models their internal model representation trajectories to localize turns that deviate from successful execution dynamics, and it further interprets these signals alongside the execution contexts as actionable textual feedback for targeted skill revision. Experiments on two
agent environments with two open-source LLMs show that Rep2Skill consistently outperforms text-only approaches in the self-
evolution setting, where the same LLM serves as both executor and optimizer without a stronger external model. This establishes a promising direction moving
agent self-improvement beyond text-only reflection.
Read the full abstract ▾
All authors Kaixing Zhang, Changming Li, Yingdong Shi, Zheng Zhang, Kaitao Song, Wenjie Shi, Jingang Wang, Kan Ren
Artificial Intelligence
Do Self-Evolving Skills Generalize to Held-Out Tasks?
Xihao Piao, Zifeng Wang and Zhen Chen
AI
agents can externalize what they learn from past tasks into reusable skills, such as procedures, checklists, code, or other executable artifacts, that can be retrieved and reused when solving new tasks. Self-evolving skill methods keep rewriting these skills after each round of practice on training tasks, and the skill is then used on new tasks of the same kind. We ask a question: does the improvement a skill shows on its training tasks carry over to new test tasks? We test five self-evolving methods and a one-shot skill on six
benchmarks, with the same model, the same
agent, and the same train/test split for every method. Of the 21 skills that improve on their training tasks, 5 keep all of that improvement on the test tasks, 13 keep part of it, and 3 keep none of it. No existing method is best everywhere. When we read the skills, the ones that carry over badly often fix details that should depend on the task, such as column names and output files, or turn a fix for one failure into a rule for every task. An LLM judge that reads the skill content can often see this: it ranks finished skills the same way the test results do in 86% of pairs. But it predicts the effect of a single edit poorly, so edits still have to be tested by running them. Based on these findings, we describe Generalizable Skill Optimization (GSO), which keeps only a guide for writing skills and writes a new skill for each task; it scores highest on all six
benchmarks.
Read the full abstract ▾
Artificial Intelligence
MADBench: Benchmarking the Security of Multi-Agent Debate
Yuwan Liu, Jiaming Zhang, Yue Huang et al. (+1 more)
Multi-
agent debate (MAD) can improve large
language model (LLM)
reasoning by allowing multiple
agents to exchange and critique their answers to the same task. However, the interactions that enable
agents to correct mistakes can also spread
adversarial errors and steer the
agents toward an incorrect answer. Although some efforts have been made to examine particular attack types on MAD, systematic evaluation of MAD under diverse attacks remains limited. A central question is whether debate mitigates
adversarial influence or amplifies it. In this paper, we present MADBench, a
benchmark for evaluating the security of MAD. We organize attacks into a layered taxonomy following the MAD workflow, incorporating both established attacks and new strategies tailored to debate. We evaluate six attack families over 356 source tasks and 3,958 test cases, examining their effects on the final answer and the propagation of
adversarial influence. Our results show that, under attacks, MAD does not necessarily improve LLM
reasoning. Compared with a single-
agent baseline, MAD can mitigate attacks on answer accuracy in question-answering tasks while amplifying unauthorized reads or writes in both question-answering and workspace tasks. Moreover, even when three out of five
agents collude, the attack changes the final answer from correct to wrong on only 28.30% of tasks answered correctly without attack, while only 3.26% of initially correct honest
agents switch to wrong answers during debate.
Read the full abstract ▾
All authors Yuwan Liu, Jiaming Zhang, Yue Huang, Sisi Duan
Artificial Intelligence · Cross-listed from cs.RO
Blackout vs. Freeze: Analyzing Physical Failure Modes of VLAs under Camera Faults
Heejae Suh, Jongwook Han, Zahra Gholami et al. (+1 more)
Unreliable visual inputs can harm task performance and cause potential physical safety risks for
vision-
language-action (VLA) models. We analyze how $\pi 0.5$ and GR00T models act under input faults such as image blackouts and freezing. We find that blackout and freezing produce distinct physical failure modes even when task-success rates are similarly low: freezing causes more extreme joint behavior, whereas blackout after gripper closure can cause more object drops, most markedly without proprioception. Selective intervention studies reveal that proprioception (current
robot state) partly compensates for the removed
robot depictions and reduces non-target contact. However, it cannot sufficiently restore task success when wrist-view object information is removed, even when aided by the remaining scene view. We then evaluate two mitigation approaches: camera-blackout training and training-free replacement of faulty visual
embeddings. Both improve task success in selected conditions, but can increase unintended contact or disturbance to surrounding objects. Real-
robot trials further show that successful execution under camera faults can still involve unintended physical interactions. These findings motivate designing VLA policies that use the
robot and object information still available under camera faults to limit hazardous motion.
Read the full abstract ▾
All authors Heejae Suh, Jongwook Han, Zahra Gholami, Yohan Jo
Artificial Intelligence
RefCon: Iterative Refinement and Contrastive Memory Extraction for Context-Evolving Agent
Ubaidillah Ariq Prathama, Bo Liu, Yeo Boon Hong et al. (+3 more)
Long-horizon
agent interactions generate useful but noisy experience, and retraining models to absorb it is expensive. Context-evolving
agents therefore need
memory extraction methods that improve with more test-time compute without relying on gold labels. We propose RefCon, which combines sequential self-refinement with parallel self-contrast to extract higher-quality
memories without gold labels. Evaluated on AppWorld and BFCL-V3 across multiple context-evolving
agent frameworks, RefCon delivers strong and consistent gains, including relative improvements of 21.6% on ACE and 16.6% on ReMe over no-scaling baselines, while a diversity-focused variant (DivCon) achieves a 35.5% gain on ReasoningBank. RefCon consistently outperforms existing baselines without ground-truth labels, and generalizes across model scales and to software engineering tasks, where it surpasses even ground-truth baselines. We further analyze the accuracy-
token trade-off and scaling behavior, showing RefCon maintains favorable efficiency and continues to improve as more trajectories are used, unlike diversity-only scaling which saturates earlier.
Read the full abstract ▾
All authors Ubaidillah Ariq Prathama, Bo Liu, Yeo Boon Hong, Yu-Xuan Huang, Yangkai Ding, Tao Yu
Artificial Intelligence
Schema: Discovering Unknown Environments via Agentic Program Induction
Guanning Zeng, Jiani Wang, Wenjie Ma et al. (+8 more)
Learning to complete tasks in unfamiliar environments with unknown rules remains a key challenge for LLM
agents. Current LLM
agents often record their discoveries in prose, which may not provide a compact, explicit account of how the environment works. Inspired by how scientists organize observations into testable, predictive theories, we introduce Schema, an
agent harness that organizes learning and action through interactive program induction. The LLM
agent decides what to investigate and how to act, expressing its evolving understanding of the environment as executable programs. The harness consists of a persistent program workspace and a small set of interfaces for checking these programs against the interaction history, planning within them, and executing plans under step-by-step verification. Schema raises ARC-AGI-3 RHAE from 58.7% to 99.2% with the same base model, solves 100% of the public DiG-bench games, and reaches the median performance of the top-50 human players on MazeBench. Extensive analysis shows the effectiveness of Schema in unknown mechanism discovery, and ablations confirm the contribution of each component.
Read the full abstract ▾
All authors Guanning Zeng, Jiani Wang, Wenjie Ma, Shaofeng Yin, Chenyang Wang, Shichen Liu, Angjoo Kanazawa, Wode Ni, Xiuyu Li, Andrea Zanette, Haiwen Feng
Artificial Intelligence
BELIEFRAG: Making Adaptive RAG State-Aware under Evolving Evidence
Hongji Pu
Adaptive RAG uses signals such as confidence, relevance, support, and
retrieval quality to decide when to search or correct evidence. In multi-step
retrieval, however, these local signals must be combined into a persistent view of what the current evidence supports, what remains missing, and which action should follow. Existing methods often use such signals as separate triggers, making it difficult to preserve a coherent evidence state across a trajectory; we call this problem evidence-state fragmentation. We introduce BELIEFRAG, a closed-loop controller that updates an explicit state over sufficiency, reliability, conflict, uncertainty, evidence gaps, and acquisition cost, then chooses among
retrieval, query rewriting, verification, answering, stopping, and abstention. Across six QA
benchmarks with gpt-oss-120b, BELIEFRAG reaches mean
token F1 0.572 with 3.89k
tokens per question, outperforming fixed iterative
retrieval (0.555 F1) while using 39% fewer
tokens. The same quality-cost pattern transfers to Qwen3-32B, where BELIEFRAG reaches 0.552 F1 versus 0.523 for iterative
retrieval while using 35% fewer
tokens. Analysis shows that the main gains come from corrective re-
retrieval rather than
pruning alone, while several belief dimensions are redundant and calibrated answerability plays the strongest operational role. Calibration improves threshold stability across related evidence sources, although source shift can still invalidate the same decision signal.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
T-Router: Learning Thalamic Routing for Reasoning with Parameter-Efficient Reinforcement Learning
Liuxian Ma, Jiale Dai, Jiaqi Li et al. (+1 more)
Parameter-efficient reinforcement learning aims to improve
reasoning with a compact trainable interface to a pretrained model. We introduce the Thalamic Router (T-Router), which concentrates adaptation on the reuse of completed computations. A compressed, addressable bank preserves block changes; a depth-recurrent controller conditions their selection and relative-scale writeback. This coupling gives thalamic context-dependent routing a concrete computational form: learn which earlier contributions a receiving layer uses, and with what influence. Correctness rewards train the interface while preserving backbone parameters and layer order. On an 8.95B-parameter backbone, T-Router allocates 41.73M parameters (0.466% of the backbone) and achieves 83.64 +/- 1.16 MathAvg after GSM8K RL, compared with 73.79 +/- 1.83 for full-parameter GRPO across three evaluation rounds. At a comparable parameter budget and with matched retries, it exceeds LoRA's 77.28 +/- 1.95 MathAvg, improving all three task families and raising mean AIME accuracy from 48.33 to 60.56. Capacity-controlled comparisons favor addressable block changes and recurrent context; separate search training extends the interface to tool-mediated
reasoning. These results establish controlled computation reuse as an effective route to parameter-efficient
reasoning reinforcement learning.
Read the full abstract ▾
All authors Liuxian Ma, Jiale Dai, Jiaqi Li, Lu Mi
Artificial Intelligence
MASCRDM: Multi-Agent System for Compliance Risk Detection and Mitigation in Training Process of Large Language Models
Yan Zhang, Chuming Wei, Ruien Li et al. (+3 more)
Large
Language Models (LLMs) have been applied in various fields. However, ensuring compliance and safety of LLMs, such as avoiding discrimination and bias, still remains a challenge. Current efforts mainly focus on detecting and filtering inputs and outputs of the trained models, rather than studying the intrinsic architecture of the models in real-time. To tackle this challenge, we analyze the LLMs training process and discover two critical issues: 1) Most of the existing methods are predominantly static in their approach to detection and filtering, achieving only localized optimizations without systematically enhancing the compliance of LLMs. 2) Another issue with existing approaches is the lack of real-time risk detection and mitigation across the full training process, which leads to limited flexibility. Motivated by these, we propose MASCRDM (Multi-
Agent System for Compliance Risk Detection and Mitigation) during the LLM training process. Firstly, we develop a set of compliance rules based on existing Artificial Intelligence (AI) laws and a compliance-specific LLM with the instruction of compliance law experts. Then, we deconstruct LLMs into several components and identify key nodes based on the compliance knowledge graph. During LLMs training, we implement our multiple
agents in the whole process, giving compliance risk alerts and suggestions for LLM developers. Experiments on discrimination and bias
benchmark demonstrate that our multi-
agent system can effectively improve the compliance while maintaining reasonable semantic performance. The results indicate that our method provides an executable path for mitigating compliance risk from within the LLMs systematically.
Read the full abstract ▾
All authors Yan Zhang, Chuming Wei, Ruien Li, Yaoyao Peng, Wusheng Zhang, Guangwen Yang
Artificial Intelligence
Reserve-Aware Contrast Certificates for Conservative Bandits with Uncertain Baselines
Qinchuan Cheng
Conservative bandits must improve an incumbent policy without exhausting a prescribed performance budget. When the incumbent is uncertain, separately bounding candidate and baseline rewards can charge twice for shared estimation error. We develop Reserve-C4B around the baseline-relative contrast itself. A shared confidence set yields an exact expression for this avoidable penalty and a tighter admissibility test at every fixed history. A reserve ledger separates statistical evidence from permitted performance deficit; a prefix-refresh extension recertifies accumulated decisions under the current confidence set without discarding previously certified credit. For linear rewards, self-normalized confidence sets provide simultaneous validity over time and adaptively generated candidates, and the resulting policy satisfies a conditional-mean performance constraint with high probability. Reproducible experiments isolate certificate coupling, prefix refresh, and historical information, showing large reductions in baseline fallback while exposing the limitations of frozen certificates.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CL
False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents
Meijia Chen, Hao Li, Zheng Lu et al. (+12 more)
Self-evolving search
agents build their own training curricula by jointly optimizing a proposer that generates questions and a solver that answers them. This closed loop introduces a failure mode we call co-cheating: the proposer and solver increasingly agree on shared errors, so internal reward improves without a matching gain in external correctness. A post-hoc audit against source evidence shows co-cheating growing more severe over successive rounds of self-
evolution, with pseudo-label correctness stagnating or declining even as the in-loop training signal improves. The most direct mitigation is to verify proposals before training: we introduce multi-sample verification (MSV), which queries the same model three times with the source and three times without it to decide task admission and replace unreliable pseudo-labels. MSV partially reduces false agreement but leaves substantial residual co-cheating and costs six extra labeler generations per candidate. These limitations motivate CrossFit, our main method: it partitions the proposer's source documents into groups A and B; questions generated from A are scored by an auxiliary solver trained only on B, and vice versa. The cross-fitted agreement determines proposer reward, so a same-source pseudo-label cannot be reproduced through the feedback solver, while the original solver's update rule is unchanged. Rerunning the loop with Qwen3.5-4B and Qwen3.5-9B, MSV reduces false-agreement mass from 6.1% to 5.7% and from 8.8% to 7.2%, whereas CrossFit reduces it to 3.0% and 3.7%. Replaying identical proposals with source-excluded feedback further reduces false agreement to 0.4% and 0.1%, isolating feedback ancestry from curriculum changes. Across seven downstream search
benchmarks, CrossFit improves average performance over standard coupled self-
evolution by 8.8 and 8.4 points and over Search-R1 by 8.7 and 7.8 points at 4B and 9B.
Read the full abstract ▾
All authors Meijia Chen, Hao Li, Zheng Lu, Hongshan Lin, Junbai Tian, Yichen Liu, Zijun Tian, Yufan Zou, Shuhan Sun, Hanxin Chen, Zeyu Zhang, Weizhi Du, Yueting Li, Tianyu Shi, Alaa Khamis