Artificial Intelligence
Agentic4PDM: Host-Governed Evidence Admissibility for Industrial Fault Diagnosis
Nam V. Nguyen, Hoang Van Truong, Hieu D. D. et al. (+3 more)
We study industrial fault diagnosis as a classification task that assigns sensor time-series windows to predefined health states or fault types. Scarce labels and changing operating conditions make repeated training of specialized classifiers costly. Yet structures such as periodicity, trends, and transients can remain diagnostically informative and be examined through reusable analytical tools. LLM
agents can select and interpret these tools, but fixed rules or training-derived guidance may not resolve each signal's ambiguity, while unconstrained interpretation may overstate weak or conflicting results. We introduce Agentic4PDM, a framework that separates adaptive investigation from control over evidence use. LLM
agents compare each signal with labeled references from every candidate class, identify unresolved distinctions, and propose follow-up measurements. A deterministic software controller, called the host, enforces contract-checked gated adjudication (CCGA): it checks requests, requires commitment to a complete tool batch before results are observed, and assigns evidence roles based on tool checks against labeled references. These roles distinguish corroborative support from advisory information. The Judge
Agent proposes a diagnosis, while the controller checks protocol compliance and records the investigation. Agentic4PDM supports training-free diagnosis using pretrained representations and labeled references without task-specific diagnostic models, and a standard setting that additionally investigates trained-model predictions. Experiments on selected bearing and motor diagnosis challenges and an unfiltered industrial test set supplied by our customer show gains in aggregate macro F1 over the evaluated diagnostic and agentic baselines. Ablations further support the value of the governed workflow.
Read the full abstract ▾
All authors Nam V. Nguyen, Hoang Van Truong, Hieu D. D., Duy Khuong Nguyen, Quang Pham, Tung Kieu
Artificial Intelligence · Cross-listed from cs.CL
Efficiently Learning To Reason or Not to Reason: Root-token Policy Optimization for Adaptive Thinking
Taehyeon Kim, Hyunsoo Lee, Youngsoo Jang et al. (+1 more)
Large
reasoning models (LRMs) achieve strong performance by externalizing explicit
reasoning traces before producing the answer, yet suffer from overthinking challenge that allocates uniformly heavy computation to queries of varying difficulty. While proprietary models mitigate this via opaque routing, open-source LRMs still lack an efficient mechanism to internalize adaptive
reasoning due to both expensive training cost and limited disclosure of training recipes. In response, we introduce RPO (Root-
token Policy Optimization), a framework that enables LRMs to self-determine when to reason by training only the initial root
token (e.g., whether to invoke the <think> tag) via group relative reward and group-wise advantages. By focusing on this pivotal branching point, RPO drastically reduces training overhead and VRAM usage. Across multiple model families and scales, RPO learns difficulty-aware adaptive thinking at just ~2% of the training compute of prior adaptive-
reasoning methods.
Read the full abstract ▾
All authors Taehyeon Kim, Hyunsoo Lee, Youngsoo Jang, Moontae Lee
Artificial Intelligence
Memory Echo in Single-Agent Long-Term Memory: Lifecycle Evaluation and Provenance-Guided Mitigation
Yufeng Li, Sheng Yao, Peng Zeng et al. (+5 more)
Long-term
memory supports
agents across sessions. Repeated
retrieval and write-back can let one historical claim occupy multiple
retrieval positions and influence current answers without independent evidence. Existing work examines
retrieval, updating, and question answering, leaving same-source record accumulation and post-correction persistence underexplored. Motivated by research in social cognition and
memory psychology on repeated exposure,
retrieval, and revision, we define
Memory Echo as the excess
retrieval exposure gained by historical information from the same source without additional independent evidence, and introduce MEchoBench to evaluate its emergence, correction resistance, persistence, and effect on answers. To address this phenomenon, we introduce the Family–Provenance–Authority framework (FPA). Specifically, FPA selects one representative per source family, conditions the eligibility of old records for the answer context on verified corrections, and constrains final answers with authoritative evidence. In paired replay on 190 fixed questions across four
memory frameworks, FPA raises accuracy from 0.825 to 0.920 with DeepSeek V4 Flash and from 0.782 to 0.916 with Kimi K2.6; mean Decision Contamination Effect falls from 0.106 to 0.030 and from 0.109 to 0.038, respectively. These results show that
agent memory can preserve traceable history without allowing repeated historical information to govern current decisions. The code is available at https://github.com/OrcasSam/
memory-echo-
benchmark.
Read the full abstract ▾
All authors Yufeng Li, Sheng Yao, Peng Zeng, Dezhang Kong, Shi Lin, Changting Lin, Xun Wang, Meng Han
Artificial Intelligence
Autonomous 3D Visual-Thermal Inspection for Utility-Scale Solar Farms
Lachlan Tychsen-Smith, Mark Cox, Brett Wood et al. (+6 more)
Utility-scale photovoltaic (PV) inspection is dominated by aerial surveys, which are effective for identifying module-level hot
cells but provide limited visibility of critical components located under the array, including connectors, cabling, fasteners and structural elements. These assets are difficult to inspect consistently at scale, and their defects are often spatially small, partially occluded and difficult to localise from isolated images. We present an automated 3D visual-thermal inspection system (Tricorder) for under-panel PV asset inspection. The approach combines
LiDAR-inertial Simultaneous Localization and Mapping (SLAM) with geometrically calibrated RGB and thermal imagery and machine-learning-based object detection and segmentation. Detected assets are associated with the reconstructed 3D environment, allowing visual and thermal observations from multiple viewpoints to be spatially fused and localised. We demonstrate the approach on utility-scale PV data for MC4 connector detection and connection-state recognition, thermal anomaly identification, and detection of structural components including bolts, nuts and torque tubes. The results demonstrate a pathway from image-based inspection toward spatially grounded autonomous inspection, where defects are detected and linked to specific assets and their 3D locations within the solar farm.
Read the full abstract ▾
All authors Lachlan Tychsen-Smith, Mark Cox, Brett Wood, David Haddon, Kenrick Anderson, Benjamin Duck, Jim O'Malley, Noel W Duffy, Peyman Moghadam
Artificial Intelligence · Cross-listed from cs.LG
Gaussian Process Bandits for AI System Optimization with Selectively Verified Feedback
Shuang Wu
Gaussian process bandits exploit similarities among configurations to optimize
prompts,
retrieval systems, and
agent workflows. In these applications, however, inexpensive model-based evaluations can disagree with trusted task outcomes. We study selective verification when an action is chosen before a diagnostic is observed and trusted feedback is informative on an unknown set of diagnostic states. A finite reliability class and a finite RKHS signal dictionary describe these two sources of uncertainty. We construct a fixed audit design that combines reliability coverage with reward separation and establish a finite-time regret bound that accounts for a hard audit budget and the rounds needed to obtain informative observations. A safe adaptive extension mixes this robust design with predictable Chernoff allocations while preserving a uniform identification floor and exact expected acquisition-cost accounting. For signed-coordinate kernels, structured and diffuse reliability classes require different audit scales despite sharing the same reward geometry. Synthetic experiments distinguish these certified designs from an adaptive posterior heuristic and GP controls. Safe adaptive allocation reduces aggregate regret relative to the fixed design under the exact dictionary, but its finite-budget error certificate is numerically loose. Conditional-feedback errors can remove the heuristic's advantage and target perturbations can reverse it. Separate AI-task replays assess feedback correction and fitted-dictionary policies without establishing end-to-end validation of a learned selective-verification method.
Read the full abstract ▾
Artificial Intelligence
Instructions Are Evidence, Not Objectives: Measuring Outcome Alignment of Agents
Kaiming Liu, Yuxuan Liu, Jinrui Ju et al. (+4 more)
Large
language model
agents can follow complex human instructions to solve real-world tasks. In practice, however, initial instructions are often incomplete. In our analysis of 100 user-
agent trajectories from SWE-chat, 56% of initial instructions omit requirements that later emerge as necessary, and 52% of the useful follow-up requirements could have been inferred from the project. A user states requirements from their own understanding of the task, and these stated requirements often differ from the true requirements that completing the task imposes. An
agent should therefore treat the instruction as evidence rather than as the objective, inferring the true requirements from the instruction and the environment and satisfying them even when the user is not yet aware of all of them. We call this ability outcome
alignment. In this work, we construct TiGanEval, a
benchmark of software engineering and research tasks. In every task the user genuinely lacks part of the requirements, each requirement stays discoverable from the code and runtime behaviour of the environment, and requirements the
agent infers are separated from those the user adds after observing delivered work. These properties together make outcome
alignment measurable. Evaluating eight frontier models including GPT-5.6-Sol, we find outcome
alignment broadly missing: the models lose 53 to 67 points of success rate when moving from the full specification to the partial instruction, and consequence feedback across four submissions does not close the gap. Furthermore, a plan-mode harness cannot compensate for the missing ability of the model itself, which places outcome
alignment among the abilities the next generation of models should be developed for.
Read the full abstract ▾
All authors Kaiming Liu, Yuxuan Liu, Jinrui Ju, Minyuan Ruan, Xuanyu Lei, Peng Li, Yang Liu
Artificial Intelligence · Cross-listed from cs.MA
Degrees of Freedom in Multi-Agent Coordination: Between Centralized and Decentralized Regimes
Yiqing Peng, Hehai Lin, Zixuan Wang et al. (+7 more)
Large
language model (LLM)-based multi-
agent systems (MAS) are commonly organized around two coordination regimes. Centralized coordination provides explicit control but can create a bottleneck at a single coordination locus, whereas decentralized coordination offers local autonomy but must achieve effective collaboration through distributed decisions and experience. These trade-offs motivate a systematic study of the space between the two regimes. We introduce Degrees of Freedom (DoF), a continuous configuration framework that quantifies the size of the decision space delegated to downstream
agents. DoF controls the granularity of delegated work and the target probability that each task unit is assigned to the branches. Its endpoints recover the two coordination regimes. Across multiple task domains, DoF reveals a hierarchy of organizational effects. Delegated granularity and within-regime routing produce structured but bounded profile reallocations, whereas task domain and retained experience are associated with stronger differences between the centralized- and decentralized-branch profiles. The resulting performance landscape is task-dependent: different domains favor different DoF configurations, while atomic-target conditions are more consistent across runs. In-domain retained experience brings the two branch profiles closer together. The same controlled sweep reveals a task-dependent coordination landscape: some domains exhibit higher-performing configurations, whereas others show flatter responses and no single configuration dominates across domains. In five of the six evaluated state, an intermediate DoF configuration achieves higher mean accuracy than both endpoints, demonstrating the value of exploring the coordination space between them. Together, these findings provide empirical guidance for studying and designing intermediate coordination regimes in LLM-based MAS.
Read the full abstract ▾
All authors Yiqing Peng, Hehai Lin, Zixuan Wang, Dongyi Zhang, Zhengjie Zhu, Yi Han, Yangyang Zheng, Hao Wang, Qian Li, Chengwei Qin
Artificial Intelligence · Cross-listed from cs.RO
I3L: Iterative Interactive Imitation Learning for Whole-Body Mobile Manipulation
Wensi Ai, Christopher Luey, Karthik Dharmarajan et al. (+7 more)
Policies trained offline from teleoperated demonstrations can degrade outside their training distribution. This gap is particularly acute in long-horizon whole-body mobile manipulation, where long horizons amplify compounding errors and coordinated arm, torso, and base motion makes exhaustive demonstration coverage impractical. We introduce I3L, an integrated hardware and learning system that combines whole-body correction with iterative policy refinement to address this last-mile reliability gap. Its low-cost, open-source JoyLo+ interface uses policy-tracking leader arms and touch-triggered takeover to enable coordinated corrections across the body parts, while iterative deployment and retraining allow operators to target failures of the updated policy. We evaluate I3L across three
robot embodiments and eight simulated and real-world tasks, including four long-horizon whole-body mobile manipulation tasks. Controlled simulation experiments show that four-round HG-DAgger achieves the highest final success on both tasks. Under this protocol, I3L improves autonomous success over the base policies by an average of 68.3 percentage points and achieves at least 90% success on every task, outperforming demonstration-only training by 35.6 percentage points on average with the same number of training trajectories. Averaged across tasks, takeover duration per episode decreases by 72% over four rounds. Together, these results show that I3L helps close the last-mile gap between offline training and reliable deployment and provides practical insights into collecting and using corrections for long-horizon whole-body mobile manipulation.
Videos, visualizations, and appendix are at https://i-3l.github.io/.
Read the full abstract ▾
All authors Wensi Ai, Christopher Luey, Karthik Dharmarajan, Evans Han, Yunfan Jiang, Stef Ren, Jianwen Xie, Jiajun Wu, Li Fei-Fei, Ruohan Zhang
Artificial Intelligence · Cross-listed from cs.CL
Auditing Failure Attribution: Label Predictability and Judge Behavior
Tianyang Xu and Jing Gao
Failure-attribution
benchmarks ask an LLM judge which step or
agent caused a failure. A high score should mean the judge checked the faulty step against the run (a cross-step check). However, spurious signals (surface cues) that predict the annotation can produce a high score. In this paper, we propose four tests to separate checking from cue use. Input restriction asks whether partial input predicts the annotation. Cue following checks whether moved cues change answers. Residual accuracy scores judges where cue-only predictors fail. Aggregation asks whether the failure mix or metric changes rankings. Real observations motivate these tests: on three
benchmarks, simple predictors match or beat GPT-4.1. In two Who&When Pro systems, a classifier reading one step's
reasoning finds 95-100% of faulty steps, motivating input restriction. In one of them, error injection leaves no
reasoning after the faulty step; judges fine-tuned on its labels beat GPT-4.1 by 41 points. Adding task-related
reasoning after that step moves this cue: fine-tuned judges lose 31-99 points, but zero-shot judges lose at most 9, motivating cue following. On Aegis, blaming every
agent matches GPT-4.1 on micro-F1 but trails by 19 points in exact-set accuracy, motivating aggregation. We recommend reporting these tests when developing failure-attribution
benchmarks.
Read the full abstract ▾
Artificial Intelligence
Coupled Harness–Model Evolution for Scientific Equation Discovery
Pengze Li, Jiaquan Zhang, Encheng Su et al. (+8 more)
Large
language models (LLMs) are increasingly used to discover scientific equations from experimental data. Such a discovery system has two parts that must work together: a library of executable computational tools and the model's tool-use policy. The tools supply the solving capability, from diagnosing structure in the data to fitting candidate equations; the policy plans and orchestrates their use. Yet existing systems adapt only one part, keeping either the toolset or the model fixed, which leaves the corresponding failures uncorrectable. We develop a coupled
evolution framework that improves both parts from the same verifiable fit-error signal. In the tool-
evolution phase, an
agent grows an executable tool library from a small set of generic numerical operations by diagnosing its own failures: it authors a new tool when a capability is missing and revises its selection rules when the right tool went unused. In the policy-
evolution phase, a small open model (roughly 3B active parameters) is fine-tuned on successful tool-use trajectories collected with the frozen library, on training formulas screened to be disjoint from all evaluation
benchmarks. Ablations show the two phases are complementary: with no tool library at all the same model solves almost nothing, the tools account for most of the gain, and trajectory training adds a further gain that is largest on the most difficult problems. The full system solves 79.1/71.3% of LSR-Synth problems at fit tolerances $10^{-2}$/$10^{-3}$, reaches 63.8% pooled accuracy on the distributionally different SRSD-Feynman panel, and obtains a normalized CP3-28 aggregate of $-7.27$. These results suggest a broader recipe for scientific
agents: let the model and its instruments improve each other under verifiable feedback.
Read the full abstract ▾
All authors Pengze Li, Jiaquan Zhang, Encheng Su, Yunbo Long, Zihang Zeng, Xinping Liu, Han Zhang, Junchi Yu, Shixiang Tang, Aoran Wang, Xi Chen
Artificial Intelligence · Cross-listed from cs.LG
HiSTOR: Structured Treatment-outcome Representation Learning for High-Dimensional Longitudinal Data
Chuanqi Lao, Junzhou Huang and Qiao Liu
Estimating potential outcomes under alternative treatment sequences is essential for personalized decision-making, but remains challenging with high-dimensional
covariates and time-varying confounding. In this study, we propose HiSTOR (High-dimensional Structured Treatment-Outcome Representation), an end-to-end framework that integrates nonlinear dimension reduction with longitudinal counterfactual prediction. The central idea is to learn structured low-dimensional representations of both current patient states and evolving histories, according to their shared and distinct relationships with treatment assignment and outcomes. This extends latent-space
covariate adjustment to longitudinal settings, jointly addressing
covariate dimensionality and historical complexity. The resulting framework supports one-step and multi-step outcome prediction under specified treatment sequences. Experiments on CVSim and CancerSim demonstrate the superiority of HiSTOR across varying
covariate dimensions, confounding strengths, and prediction horizons compared to state-of-the-art methods. To sum up, HiSTOR offers a unified approach to connecting high-dimensional
covariate adjustment with longitudinal potential-outcome prediction.
Read the full abstract ▾
Artificial Intelligence
DuplexAct: How Interactive Are Frontier Full-Duplex Spoken Language Models?
Jiaheng Dong, Shihong Tan, Gongping Huang et al. (+3 more)
End-to-end (E2E) full-duplex spoken
language models (FD-SLMs) enable simutanous listening and speaking continously, requiring models to take appropriate interaction actions as conversations unfold. However, existing
benchmarks lack a structured action-level formulation, often evaluate action occurrence rather than success, and provide limited coverage of diverse real-world conversations. We introduce DuplexAct, a
benchmark for evaluating interaction action taking in E2E FD-SLMs. DuplexAct defines a three-level action taxonomy spanning eight interaction actions and 24 corresponding interaction conditions. We further characterize successful action-taking through immediate execution and subsequent follow-through, and develop action-specific evaluation metrics for both. DuplexAct contains 4,691 test instances spanning casual conversation, meetings, customer service, and interviews, including 2,531 instances derived from real-world conversational recordings. Together, DuplexAct provides a structured and real-world-grounded framework for systematically assessing how E2E FD-SLMs participate in ongoing spoken interaction.
Read the full abstract ▾
All authors Jiaheng Dong, Shihong Tan, Gongping Huang, Jean Honorio, Abhirup Ghosh, Ting Dang
Artificial Intelligence · Cross-listed from cs.LG
Train for Many, Update with One: Improving Multi-Sample Reasoning via Fenchel-Bregman Posterior Learning
Sungjun Lim, Adrian Robert Minut, Nico Carlsen Daheim et al. (+3 more)
Multi-sample
reasoning measures candidate coverage, the probability that at least one of $K$ candidates is correct. However, minimizing the average loss of individual attempts does not directly optimize candidate coverage. We therefore formulate finite-$K$ posterior learning, which trains a distribution over solver parameters to reduce the probability that all $K$ independently generated candidates fail. To optimize this objective efficiently, we propose a Fenchel-Bregman (FB) approach that requires only one posterior draw per update, rather than the $K$ used by direct Monte Carlo optimization. FB first uses an exact Fenchel reformulation to separate problem-specific weights from the posterior update, enabling one-draw posterior updates. It then applies a closed-form Bregman update to track these weights through an exponential running average of observed failures, reusing the same draw. We instantiate FB with IVON, a variational optimizer for Gaussian posteriors over solver parameters, yielding Fenchel-Bregman IVON (FBI). Across diverse recursive and autoregressive
reasoning tasks, FBI improves candidate coverage. In a matched comparison, it achieves comparable Pass@10 using 12.3% of the direct Monte Carlo baseline's measured training time per update.
Read the full abstract ▾
All authors Sungjun Lim, Adrian Robert Minut, Nico Carlsen Daheim, Mohammad Emtiyaz Khan, Kyungwoo Song, Thomas Möllenhoff
Artificial Intelligence · Cross-listed from cs.LG
Explore with Memory, Learn without It: In-Context Exploration and Self-Distillation for LLM Reasoning
Yutong Chen, Zhichao Xu, Rui Liu et al. (+1 more)
Exploration bounds learning efficiency in reinforcement learning with verifiable rewards (RLVR). Current methods explore mostly through independent sampling, without fully using the information gathered along the way, such as known wrong answers and environment feedback. We propose LEAF, which injects a dynamic, problem-specific
memory into the context before every rollout. The
memory contains the most recent response, its reward, and other environment feedback. It is updated after every verifier call. We decouple policy updates from rollouts and update the policy through self-
distillation. On four
benchmarks and two open models, LEAF accelerates exploration by about 4x compared with a random sampling baseline. On unseen test sets, it improves accuracy over the strongest baseline by 1.59 and 1.83 percentage points on the two models, while using less compute than any RL baseline. These results highlight the potential of LEAF in improving both exploration and learning efficiency. Code is available at: https://github.com/on1262/LEAF
Read the full abstract ▾
All authors Yutong Chen, Zhichao Xu, Rui Liu, Kunpeng Liu
Artificial Intelligence · Cross-listed from cs.LG
CoCA: Criterion-Aware Credit Assignment for Rubric-Based Reinforcement Learning
Guangcheng Zhu, Yingfan Ma, Xing Zheng et al. (+7 more)
Rubric-based reinforcement learning (RL) evaluates responses against explicit criteria to construct rewards, offering a viable way to train large
language models on open-ended tasks. However, standard methods compress criterion-level feedback into scalar rewards and assign uniform
token advantages, leaving structured rubric supervision underutilized. Recent work seeks finer-grained guidance by treating rubrics as privileged information to derive self-
distillation targets, but the resulting learning signal is not grounded in criterion outcomes and can lead to reward degradation. This motivates us to reframe the problem as criterion-aware credit assignment, where privileged rubric information serves as a relevance cue for credit allocation rather than a source of imitation targets. Accordingly, we propose CoCA, which derives criterion-level credits from group-relative outcomes and allocates them across
tokens based on criterion-induced distribution shifts, yielding both outcome-grounded and fine-grained learning signals. Empirically, CoCA achieves an average gain of +4.2% over standard rubric-based RL across medicine and science
benchmarks, demonstrating more effective learning on open-ended tasks.
Read the full abstract ▾
All authors Guangcheng Zhu, Yingfan Ma, Xing Zheng, Haobo Wang, Shenzhi Yang, Kai Tang, Zhengqing Zang, Bowen Song, Weiqiang Wang, Gang Chen
Artificial Intelligence
Safety for Whom? Benchmarking Understanding Beyond Refusal in Egocentric Multimodal Assistants
Yewon Han, Jisu Jeon, Suhyun Choi et al. (+5 more)
Egocentric
multimodal assistants see through the user's eyes and guide what the user does next, so their outputs directly shape physical actions, including those that affect bystanders. Yet existing safety evaluations do not distinguish whom a response would harm, and score only whether a model refuses. Pooling all harms into one refusal rate hides two failures: a model may protect one target but not another, and it may refuse without understanding the risk, or understand it and comply anyway. We present STOU, a
benchmark of 2,902 egocentric
video-audio and
video-text queries whose potential harm targets the user (Self), co-present individuals (The Others), or society at large (Others). Our evaluation decouples safety understanding from refusal behavior: beyond refusal, we score whether the model recognizes the user's intent, the presence and target of harm, and its downstream consequences. Across 10 open and closed source omnimodal and
multimodal LLMs, we find that refusal varies systematically with the harm target, and that models often recognize a harm yet still assist with it. These results show that refusal rates alone cannot certify an assistant as safe, and that safety
alignment must account for who would be harmed. Project page: https://onedayoneyeah.github.io/safety-for-whom
Read the full abstract ▾
All authors Yewon Han, Jisu Jeon, Suhyun Choi, Juan Yeo, Minsoo Jo, Gihoon Kim, Hyunggyu Lim, Taesup Kim
Artificial Intelligence · Cross-listed from cs.CR
SkillScreen: High-Recall Screening of Malicious Agent Skills with Decision Models
Jerrold Huang, Junwei Quan, Saiyue Lyu et al. (+2 more)
Agent skills turn natural-
language instructions into actions, creating a security challenge: legitimate automation and malicious behaviour can look deceptively similar. A practical screen must catch nearly every attack while keeping the review load manageable. We present SkillScreen, a compact decision model trained to score skill maliciousness directly from SKILL$.$md in a single forward pass. On MaliciousSkillBench, SkillScreen flags 20-25% of benign skills at 99% recall on unseen attack families, substantially fewer than the word-level classifier and prompted LLM judges tested. Under the same training protocol, it also generalizes better than a fully fine-tuned encoder to unseen sources. Yet unfamiliar benign sources sharply increase false positives, showing that recognizing new attacks does not ensure reliable screening of new skill collections. Our results demonstrate the value of task-trained decision models for high-recall skill screening. Project page: https://jerroldh.github.io/SkillScreen-webpage/
Read the full abstract ▾
All authors Jerrold Huang, Junwei Quan, Saiyue Lyu, Zihan Guo, Yingqiang Ge
Artificial Intelligence · Cross-listed from cs.LG
TSRL: Trigger-based Supervised Reinforcement Learning for Continual Agent Training
Yuqian Fu, Kaiwen Jiang, Zijun Song et al. (+3 more)
Large
language model (LLM)
agents excel at complex, multi-step tasks but suffer from catastrophic forgetting during continual learning–acquiring new skills often degrades previously mastered capabilities. Existing post-training paradigms face a fundamental trade-off: Supervised Fine-Tuning (SFT) is sample-efficient but prone to severe forgetting, while Reinforcement Learning (RL) preserves prior capabilities but converges slowly without expert guidance. To bridge this gap, we introduce Trigger-based Supervised Reinforcement Learning (TSRL), a framework that integrates the strengths of both paradigms through an adaptive, state-dependent expert supervision mechanism. TSRL employs RL as the optimization backbone, activating SFT selectively on "hard states" where the policy fails. Theoretically, we show that restricting supervision to failure states derives an upper bound on the cumulative parameter updates, thereby reducing forgetting compared to full SFT. Empirically, TSRL achieves consistent gains across three
agent benchmarks (ALFWorld, WebShop, and Deep Search) at both 7B and 32B scales. In continual learning scenarios, our method retains up to 9.6 points more capability on prior tasks than SFT->RL baselines, while matching or exceeding target-task performance.
Read the full abstract ▾
All authors Yuqian Fu, Kaiwen Jiang, Zijun Song, Jiawei Wang, Yuanheng Zhu, Dongbin Zhao
Artificial Intelligence
Evidence-First Agentic Verification
Reza Sanayei, Razvan-Gabriel Dumitru, Sunjie Hou et al. (+7 more)
Long-horizon, semi-verifiable agentic tasks often rely on rubric-based evaluation, but the evidence needed to assess these tasks can be spread across the environment state and the execution trace. A judge may overlook this evidence or accept unsupported claims, including an
agent's own reports of success. When rubric verdicts serve as reinforcement-learning rewards, such errors can reinforce undesirable behavior. We introduce Sauron, an evidence-first agentic verifier that investigates both state and trace and relies on a claim only after independently validating it against its source. Bounded queries and joint investigation of related criteria reduce context use and redundant work, and each verdict carries an auditable receipt of its supporting evidence. Across 2,586 human-labeled criteria from 100 personal-assistant episodes, Sauron achieves the highest F1 of five verifiers on all eight backbones tested while costing less than Gandalf, the strongest baseline. With GPT-5.6 Sol, it reaches 0.96 F1 versus Gandalf's 0.92 at 23% lower cost, with a wider margin on process criteria. On a paired fault-injection suite covering 13 families, several of which simulate reward hacking, Sauron detects 97% of injected failures while flagging only 2% of clean controls, outperforming baselines even when they are given the full trace. On TRAIL, a
benchmark for detecting and localizing real
agent errors, Sauron leads both Gandalf and TRAIL's own judge on all three quality metrics.
Read the full abstract ▾
All authors Reza Sanayei, Razvan-Gabriel Dumitru, Sunjie Hou, MohammadHossein Rezaei, Haris Riaz, Robert Vacareanu, Minglai Yang, Ying Liu, Mihai Surdeanu, Daniel Yue Zhang
Artificial Intelligence
Upstream Influence, Downstream Re-Anchoring in LLM Agent Chains
Chun-Yu Hsu, Lun-Wei Ku and Chung-Chi Chen
People act on evaluative judgments produced by LLM
agents, and in multi-
agent systems those judgments pass through several
agents before reaching a person. We show that a workflow's information architecture—source access, handoff format, and which model reads the untrusted content—governs how much of a coordinated manipulation reaches the end. On 32 Taiwan~2025 recall cases, ten authentic Threads comments shown to one
agent move its stance by $+0.171$ toward the injected position, and a mirrored set moves it the other way. Passing that judgment down a chain removes more than half of the shift by the third
agent; keeping the comments in front of every
agent sustains more of it. The reduction is not attrition in transit: each receiver discounts the inherited stance in proportion to how far it sits from its own reading of the evidence, returning to what that evidence implies for the case rather than to neutrality—consistent with partial re-anchoring. Handoff format is a second lever: a stance relayed without its
reasoning is largely discounted. Susceptibility at the exposed seat varies fourfold across models, while the chain's arrangement does not matter at all. None of this is visible in the transcripts—the injected claims are almost never restated, so
reasoning-trace audits miss the attack.
Read the full abstract ▾
Artificial Intelligence
Keep Your Receipts: Trustworthy Cleanup of Agent-Built Knowledge Graphs
Vishisht Choudhary
Agents build knowledge graphs as
memory, and building them has become easy. Maintaining them has not. When a source is retracted, overruled, or erased, everything built on top of it (entity merges, entailed edges, community summaries) must be re-examined, and the maintainer must choose between deleting too much and too little. Deployed pipelines delete only the directly extracted facts: on our corpus that reduces contaminated queries from 32.2% to 28.0% under a real retraction and changes nothing under predicate revocation. Rebuilding is no repair for a constructor that samples: two builds of the same 300-document corpus differ in 29,475 artifacts, five times the 6,248 that removing the 61 retracted documents changes. PolyGraph instead asks the constructor for receipts: for every artifact, alternative bundles of source evidence, each claimed sufficient on its own, emitted in the call that creates it. Cleanup is then set arithmetic over the receipts, with no model calls. Because receipts are the model's own self-report, a re-derivation audit checks them by deleting the cited evidence and testing whether the constructor still produces the artifact. The audit finds that a receipt is trustworthy when it is shaped like the claim it backs. Merge receipts, each backing one narrow claim, agree with re-derivation 68% and 85% of the time. Summary receipts, elicited per sentence but stored as one flat list for the whole text, are wrong about two thirds of the time, almost always by keeping dead content. One receipt per sentence instead is 100% and 88% faithful and lets cleanup keep 33 of 35 touched summaries. The result holds under a second oracle model, a claim-blind
prompt, ten further deletions, a second domain and a second constructor. Distrusting the summary layer cuts contaminated queries to 0.4% and 0.8% at 99.8 to 100% of the recall a perfect maintainer would return.
Read the full abstract ▾
Artificial Intelligence
ECG-RSI: Recursive Self-Improvement through Targeted Electrocardiogram Waveform Evolution
Xiaoliang Wang, Zhuo Chen, Chuanyang Zheng et al. (+8 more)
Electrocardiogram (ECG) models need supervision that targets evolving weaknesses and remains faithful to waveform evidence. We introduce ECG-RSI, a recursive self-improvement framework combining verified waveform synthesis with feedback-guided intervention search. Signal remeasurement verifies waveform edits; construction errors guide generator repair, while learner errors motivate interventions compared on a separate selection set. Across seven
benchmarks, three rounds raise Qwen3.5-35B-A3B's mean question-answering accuracy from 34.57% to 56.04% and mean classification F1 from 24.27 to 34.03. Across the retained trajectory, the preferred supervision shifts from direct reinforcement to confusion-focused contrasts. Continued feedback correction yields diminishing external gains. These results motivate separating error diagnosis from intervention selection and checking whether gains on the feedback set transfer to independent
benchmarks.
Read the full abstract ▾
All authors Xiaoliang Wang, Zhuo Chen, Chuanyang Zheng, Jiangwei Lao, Quanbin Wang, Honglin Lin, Jiajia Liu, Zhihong Lu, Hao Jin, Jian Wang, Lijun Wu
Artificial Intelligence
Adaptive-Group Process Rewards for GUI Agents
Zirui Shang, Yang Liu, Xin Shu et al. (+3 more)
Training graphical user interface (GUI)
agents with reinforcement learning suffers from sparse outcome rewards, leading to inefficient learning. Process rewards offer a promising direction for credit assignment to intermediate actions; however, accurately evaluating an action requires identifying evidence across long-horizon GUI trajectories, as its value may depend on information beyond its immediate state and observation. In this paper, we propose an adaptive-group process reward framework that dynamically partitions a GUI trajectory into semantically coherent subgoal groups, enabling process reward estimation at both the action and group levels. At the action level, a critic evaluates each action based on the visual changes and subsequent actions within the group for action correctness and contribution to the subgoal. At the group level, the framework aggregates action-level evaluations to assess subgoal completion and contribution to the overall task, and further refines these assessments by leveraging the context of all groups in the trajectory. The process reward of each action is obtained by combining its action-level evaluation with the refined group-level evaluation. We further augment GRPO's outcome advantage with the proposed process rewards to provide finer-grained guidance for GUI
agent training. Experiments on process reward
benchmarks and downstream RL training demonstrate the effectiveness of the proposed framework.
Read the full abstract ▾
All authors Zirui Shang, Yang Liu, Xin Shu, Zhi Gao, Xinxiao Wu, Lifeng Fan
Artificial Intelligence · Cross-listed from cs.LG
Where Small Mistakes Matter: Quantifying State Criticality for Imitation Learning
Yusuf Umut Ciftci, Joonwon Kang, Ajay Suresha Sathya et al. (+1 more)
Imitation learning typically treats every demonstration state as equally important, optimizing a behavior-cloning objective uniformly across the
dataset. Yet not all states are created equal: in a small number of critical states, even a slight deviation from the expert action can lead to a failure, while in many other states such errors are recoverable and inconsequential. We formalize state criticality in imitation learning as the worst-case degradation in downstream value induced by a bounded perturbation of the expert action at a given state. We then propose SCRIM, a practical State CRIticality Measure that estimates this quantity by training an
adversarial disturbance policy and a value critic around a fixed imitation policy. SCRIM assigns each demonstration state a score reflecting how vulnerable the task outcome is to small, policy-relevant action errors. We show that these scores can be used to reweight behavior-cloning losses, improving imitation at consequential states and increasing overall task performance. We further show that SCRIM enables data curation by selecting compact, high-value subsets of demonstrations that preserve performance while substantially reducing the amount of training data. We evaluate SCRIM across various simulated and real-world robotic manipulation tasks, and demonstrate that SCRIM improves policy training, enables efficient data selection, and provides interpretable insights into which moments in a demonstration are most critical for task success. Project website: https://sia-lab-git.github.io/SCRIM/
Read the full abstract ▾
All authors Yusuf Umut Ciftci, Joonwon Kang, Ajay Suresha Sathya, Somil Bansal
Artificial Intelligence · Cross-listed from cs.CV
From Token Correction to Claim Admission: Training-Free Hallucination Mitigation for Large Vision-Language Models
Hyeonggeun Han, Taehyun Cho and Sangwoo Hong
Large
vision-
language models often exhibit object
hallucination, generating claims that are not supported by the input image. To mitigate this issue, we propose Evidence-Guided Visual Claim Admission (EGVCA), a training-free framework that admits a semantic claim only when it receives sufficient image-dependent support. EGVCA measures this support by comparing the claim likelihood under the observed image and a visual-null input. For captioning, it controls semantic expansion without altering
token generation. For binary visual question answering, it combines atomic visual support with the image-induced change in the model's native Yes–No margin. Experiments on CHAIR, POPE, and MME across three LVLM backbones show that EGVCA substantially reduces object
hallucination while preserving caption quality. It achieves the highest POPE F1 in eight of nine backbone–sampling settings and improves the native MME total score on all three backbones. These results demonstrate the effectiveness of claim-level admission as a simple alternative to
token-level distribution correction.
Read the full abstract ▾
Artificial Intelligence
A Node Embedding Framework for Model-Centric Conformance Checking in Process Mining
Mostafa Abbasi and Homayoun Najjaran
Evaluating the quality of process models discovered from event logs is a fundamental challenge in process mining. Traditional evaluation relies on conformance metrics such as fitness and precision, which are highly sensitive to noise and deviations in event logs and therefore often fail to give a consistent assessment of discovery
algorithms. We introduce a model-centric evaluation framework that combines node
embeddings with Procrustes
alignment to enable cross-graph comparability, since
embeddings derived from different graphs reside in distinct vector spaces. The proposed PetriNetGraph method transforms Petri net process models into graph representations compatible with
embedding algorithms. Comparing the node
embeddings of ground-truth and discovered models through a parameterized cosine distance yields a unified and bounded metric for evaluating process discovery across
datasets and methods. We evaluate the framework under static and context-aware scenarios to examine how prior knowledge of activity existence influences the assessment of structural similarity. The framework also integrates a compliance checking mechanism that localizes deviations at the activity level and an
entropy-regularized node distance aggregation function that quantifies global deviations across the model. Experiments on nine publicly available event logs show that the approach provides a reliable
embedding-based conformance indicator that reflects the behavior of fitness and precision. Experiments on synthetic logs with controlled noise levels confirm that it is substantially more robust to log deviations than traditional conformance metrics, PetriNet2Vec, and its dynamic-window and Procrustes-aligned variants, while remaining sensitive to process model degradation. All implementation details and
datasets are publicly available.
Read the full abstract ▾
Artificial Intelligence
Understanding Gene Expression-to-Image Learning: Spatial Structure and Information Fidelity
Xiaoqing Lian, Pei Liu, Jiahui Tan et al. (+3 more)
Single-
cell RNA sequencing (scRNA-seq) enables
cell-level analysis of biological heterogeneity, but learning effective representations from high-dimensional, unordered gene expression profiles remains challenging. Gene Expression-to-Image (GE2I) offers an effective learning strategy by arranging gene values on pixel grids for convolutional neural networks, but its underlying mechanisms remain unclear. We study GE2I on full-transcriptome data while keeping the network and training procedure fixed. Our results reveal a trade-off between spatial smoothness and gene-level fidelity. Structured mappings produce smooth, low-frequency patterns that support faster early optimization, whereas assigning multiple genes to the same pixel obscures expression differences and can reduce predictive performance. This trade-off explains why random mappings can compete with structured layouts when many genes are represented. One-to-one gene-to-pixel assignment improves prediction across the tested visual backbones even when image smoothness decreases. We further find that the benefits of pretraining and augmentation depend on the backbone and mapping. These findings provide practical guidance for pixel allocation and the transfer of
vision priors to gene expression data.
Read the full abstract ▾
All authors Xiaoqing Lian, Pei Liu, Jiahui Tan, Quan Zou, Chen Lin, Xiangxiang Zeng
Artificial Intelligence · Cross-listed from cs.LG
LeanPRM: Lean-Grounded Process Supervision for Natural Language Proof Verification
Rodney Lafuente-Mercado, Salman Rahman, Jingyan Shen et al. (+3 more)
AI systems now write long and difficult mathematical proofs, and checking their step-by-step validity is becoming a bottleneck. A learned verifier could check proofs cheaply, but training one requires a correctness label on every step, and such labels are hard to obtain for open-ended proofs. Existing methods take them from human annotators, which is costly, or derive them from final answers, which proofs do not have, and formalizing each proof in Lean requires expert effort. We introduce LeanPRM, a framework that uses the Lean proof assistant to create step-level labels for natural-
language proofs. A model writes a natural-
language proof together with a paired formal proof, without feedback from Lean. Lean then labels every step, and a second model discards failures caused only by the formal syntax, so that the negative labels mark errors in the mathematics. LeanPRM contains 10,634 proofs with 152K labeled steps and no human annotation. A Qwen3-4B verifier trained on LeanPRM raises exact step-label accuracy on a held-out set of 200 proofs (LeanPRM-Bench) from 48.2 to 74.7, as opposed to 60.3 when the same base model is trained on PRM800K. It also selects better proofs in best-of-N selection on IMO-level problems, and outperforms the PRM800K-trained verifier on three of four external verification
benchmarks. Training on LeanPRM improves verifiers at every size from 0.6B to 8B parameters on LeanPRM-Bench, Hard2Verify and IMO-GradingBench. Given the labels need no human annotation, LeanPRM can grow with the supply of formal statements, offering a path to step-level feedback on AI-generated proofs that are hard for humans to check.
Read the full abstract ▾
All authors Rodney Lafuente-Mercado, Salman Rahman, Jingyan Shen, James Shiffer, Saadia Gabriel, Pavel Izmailov
Artificial Intelligence · Cross-listed from cs.LG
zPocket: Better Pocket Finding with Frozen Co-Folding Features
Tally Portnoi, Allison M Keys, Benjamin R DiFrancesco et al. (+1 more)
Identifying
protein-ligand binding sites (pockets) is important for understanding
protein function and developing drugs. However, no public method has leveraged co-folding models for novel pocket prediction; furthermore, this task lacks a suitable
benchmark as existing
benchmarks are within the training distribution of co-folding models. We therefore developed PocketWatch,a curated
dataset of biologically relevant ligand pockets. The PocketWatch test set consists of unseen pockets stratified by sequence similarity, structural similarity, and crypticity to enable evaluation of generalization to novel and challenging pockets. Using this
dataset, we develop zPocket, a method that trains pocket-prediction heads on top of frozen features from co-folding models. We show that zPocket heads outperform baseline methods across all stratifications. Our best zPocket model achieves overall per-target AUPRC of 0.745 compared to 0.598 and 0.595 for the strongest baselines, VN-EGNN and UniSite-1D retrained on the PocketWatch split (0.559 and 0.531 when using the published weights); the widely used P2Rank reaches 0.477. We further show that zPocket can be used to outperform baseline methods on top-N+2 recall of predicted pocket centroids through clustering per-residue predictions or using zPocket to rescore centroids proposed by other models. Finally, we explore two applications of zPocket: crystallographic fragment screens and a proteome-scale scan for uncharacterized pockets on human
proteins. Together these results suggest that zPocket heads built on co-folding trunk features can greatly advance ligand binding site prediction.
Read the full abstract ▾
All authors Tally Portnoi, Allison M Keys, Benjamin R DiFrancesco, Nate Gruver
Artificial Intelligence · Cross-listed from cs.RO
HelpMeOut: A Neuropsychology-Grounded Benchmark for Error-Aware Monitoring of Household Task Execution
Haoran Wang, Jingwei Huang, Anqing Duan et al. (+2 more)
We introduce HelpMeOut, an embodied AI
benchmark for error-aware monitoring of household task execution. Existing embodied household
benchmarks typically assume that humans execute tasks correctly, but this assumption does not hold for cognitively impaired persons or older adults whose everyday activities produce structured execution errors. To address this gap, HelpMeOut operationalizes research on everyday action errors into 20000 paired activity episodes, covering nine neuropsychologically motivated error categories. In each episode,
agents observe a streaming human activity trajectory and must monitor whether the execution is unfolding correctly, diagnosing any structured errors as early as possible. We evaluate learned-monitor, symbolic, change-point, and frontier LLM prompting baselines. Results show that these methods perform poorly as error monitors, often missing when execution goes wrong. These results suggest a gap left by standard goal-inference and task-completion
benchmarks, making HelpMeOut a testbed for error-aware assistive
agents.
Read the full abstract ▾
All authors Haoran Wang, Jingwei Huang, Anqing Duan, Ho Seok Ahn, Bruce Macdonald