Sign in

Category: Other

  • Can Agents Forget When Asked? A Benchmark for Memory Unlearning in LLM Agents

    Can Agents Forget When Asked? A Benchmark for Memory Unlearning in LLM Agents

    arXiv:2610.18052v1 Announce Type: new Abstract: Long-term memory has become a core component of large language model (LLM) agents. As agents accumulate personal information over long-term use, users increasingly ask them to delete sensitive or outdated facts. A memory system should honor such requests. It should remove exactly what was requested and keep the rest of its memory intact. However, existing memory benchmarks evaluate only memory writing, retrieval, and organization, so whether agents can forget at the user's explicit request remains under-evaluated. To address this gap, we propose Bemula, the first benchmark dedicated to memory unlearning. It comprises 50 multi-session dialogue instances, 135 forget requests of six types, and 1,742 test questions. Each dialogue has a control version without the requests, so that only systems that have stored the target can earn credit for forgetting. Across the paired versions, five test suites measure storage, removal of the requested information, preservation of unrelated memories, relearning of similar facts, and resistance to extraction attacks. On Bemula, we evaluate six mainstream memory systems under three backbone LLMs, together with the Full Context LLM on two of them. The results are negative. Across all evaluated systems and backbones, no system passes more than 1.5% of forget requests end to end, and most pass none at all. These systems either leave the requested information extractable under simple attacks or delete far more than requested. Memory unlearning therefore remains an open challenge for agent memory design. We release our data and code at https://github.com/Nboxff/bemula-benchmark.

    Fallback brief based on the available RSS feed; no unsupported details have been added.

    Source: arXiv
    Original article: https://arxiv.org/abs/2610.18052

  • WorkRover: Scaling Long-Horizon Cowork Agent Training Via Recursive Environment Evolution

    WorkRover: Scaling Long-Horizon Cowork Agent Training Via Recursive Environment Evolution

    WorkRover: Scaling Long-Horizon Cowork Agent Training Via Recursive Environment Evolution

    arXiv:2610.18067v1 Announce Type: new Abstract: Scaling interactive environments is important for training long-horizon agents through reinforcement learning. These environments often require further testing and refinement after initial generation, and correcting defects in a task may also require updating its work context and verifier. However, existing construction pipelines offer limited support for such iterative refinement while keeping these components aligned. We introduce WorkRover, a framework for training long-horizon cowork agents through recursive environment evolution. Its harness-driven synthesis enables construction agents to jointly build and validate semantically aligned work contexts, executable tasks, and evidence-grounded verifiers, adapting their actions to workspace state and execution feedback rather than following a fixed construction workflow. To support environment evolution, we introduce Factorial Compatibility Replay (FCR), which uses rollout feedback to evaluate combinations of component revisions through dependency-closed replay and selects the smallest validated repair among tested candidates while preserving task requirements and evaluation constraints. To provide finer-grained training signals, we propose Verifier-to-Turn Credit Assignment (VTCA), which augments trajectory-level GRPO advantages with signals from deterministic workspace-progress checks and assigns a bounded share of positive-progress credit to prerequisite turns using recorded tool-output and artifact dependencies. Using WorkRover, we post-train Qwen3.5-35B-A3B to obtain WorkRover-35B-A3B and evaluate it on several cowork-agent benchmarks. Its reported scores exceed those of Qwen3.5-35B-A3B by 26.27 percentage points on JobBench, 29.32 percentage points on OfficeQA Pro, and 413.25 Elo points on GDPval v2. These results suggest that WorkRover offers a promising foundation for scalable training of long-horizon cowork agents.

    Fallback brief based on the available RSS feed; no unsupported details have been added.

    Source: arXiv
    Original article: https://arxiv.org/abs/2610.18067

  • PaceReasoner: Label-Free Learning to Answer Briefly from Long Reasoning

    PaceReasoner: Label-Free Learning to Answer Briefly from Long Reasoning

    arXiv:2610.17900v1 Announce Type: new Abstract: Extended chain-of-thought reasoning improves problem-solving performance but increases inference cost and latency, motivating more accurate answers with shorter reasoning. We introduce PaceReasoner, a label-free test-time reinforcement learning framework that uses a model's LONG responses to improve its SHORT-mode accuracy. Both modes share a trainable policy, creating a need for reliable supervision, sufficient SHORT training samples, and continued LONG responses to guide learning. PaceReasoner combines all-response and LONG-only answer consensus through progressive, confidence-weighted supervision. A behavior reward gradually shifts from encouraging SHORT exploration to rewarding agreement with LONG answers, while a ratio controller regulates the balance between modes. Across three model backbones and four benchmarks, PaceReasoner improves average SHORT accuracy over the baselines by 7.4–13.5 percentage points, with fewer than 25 reasoning tokens per response on average. Ablations support the key components, and cross-dataset results demonstrate transfer beyond the adaptation set.

    Fallback brief based on the available RSS feed; no unsupported details have been added.

    Source: arXiv
    Original article: https://arxiv.org/abs/2610.17900

  • Learning How to Remember: Memory Modality Selection for GUI Agents

    Learning How to Remember: Memory Modality Selection for GUI Agents

    Learning How to Remember: Memory Modality Selection for GUI Agents

    arXiv:2610.17928v1 Announce Type: new Abstract: Recent advances in vision-language models (VLMs) have substantially improved the capabilities of GUI agents, while memory augmentation has emerged as a promising approach for reusing knowledge from past interactions. However, existing memory augmented GUI agents typically adopt a fixed representation strategy, providing retrieved experience as a static modality. It remains unclear whether a single memory modality is consistently optimal, or how modality preference changes across interaction steps. In this work, we conduct a systematic study of memory modality in VLM based GUI agents. Across GUI benchmarks, we find that the preferred memory representation is strongly step dependent. Motivated by the finding, we introduce \textbf{SwitchMem}, a routing framework that dynamically selects between textual and visual memory representations at each step. Across three GUI benchmarks, SwitchMem outperforms memory augmented baselines that rely on static memory representations. Our findings validate our claim that memory modality is a step dependent decision rather than a fixed design choice. Code and project resources are available at https://txxnrd.github.io/switchmem

    Fallback brief based on the available RSS feed; no unsupported details have been added.

    Source: arXiv
    Original article: https://arxiv.org/abs/2610.17928

  • Seeing Depth but Choosing Cues in Vision-Language Models

    Seeing Depth but Choosing Cues in Vision-Language Models

    arXiv:2610.17976v1 Announce Type: new Abstract: Do vision-language models use depth information to judge which object is closer, or rely on image-plane cues? We investigate this question through controlled depth–cue conflicts, representation analysis, and interventions. Among the many image-plane cues relevant to depth perception, we focus on apparent size and vertical position. We compare depth judgments under cue-consistent and cue-conflict conditions in both rendered scenes and real-world photographs. Across model families and scales, depth judgments systematically shift toward misleading cues. Yet the correct depth order remains decodable from the queried objects' visual representations, including when the model answers incorrectly. Image and category controls support interpreting this signal as image-dependent depth information beyond the two target cues. Strengthening the model's own depth readout through object-level write-back can correct conflict decisions without updating model parameters or using ground-truth depth annotations. Interventions show that the effect of this correction depends on the direction and target tokens of the written signal, while its strength varies across architectures and domains. Together, these findings reveal a mismatch between a model's ability to represent depth and use this information when deciding the answer. VLMs can retain useful depth information while allowing competing image-plane cues to exert greater influence on their answers.

    Fallback brief based on the available RSS feed; no unsupported details have been added.

    Source: arXiv
    Original article: https://arxiv.org/abs/2610.17976

  • Learning Adaptive Deliberation Control for Reliable Recognition with Multi-Agent Language Models

    Learning Adaptive Deliberation Control for Reliable Recognition with Multi-Agent Language Models

    Learning Adaptive Deliberation Control for Reliable Recognition with Multi-Agent Language Models

    arXiv:2610.17840v1 Announce Type: new Abstract: Multi-agent deliberation can improve recognition by criticizing and revising candidate answers, but fixed controls cannot respond to changes in disagreement or reasoning quality. We present an adaptive multi-agent controller (ADMA) that learns continuous policies for proposal, challenge, arbitration, and coordination while keeping the task model frozen. Shared trace features describe quality, agreement, and progress, while role-specific features support decentralized control during inference. One controller trained on legal and financial reasoning is transferred without policy updates to four textual and multimodal benchmarks and two successive task-model versions. With Qwen3.5 held fixed, ADMA-Full improves accuracy by 6.2-14.2 percentage points over Direct and by 2.8-3.0 points over ADMA-Fixed. Paired bootstrap ranges for the Full-Fixed comparison are positive on three tasks. Outcome decompositions show that recoveries exceed introduced errors, while process assessment records fewer false-consensus events and more supported correct outcomes. Transfer to Qwen3.6 remains task dependent, which bounds the generality of the learned policy. Median token and latency ratios are 14.3-18.7 and 7.8-16.5 relative to Direct. These results show that adaptive deliberation can improve fixed-model recognition when its task-dependent gains justify the additional computation.

    Fallback brief based on the available RSS feed; no unsupported details have been added.

    Source: arXiv
    Original article: https://arxiv.org/abs/2610.17840

  • Socratic Skill Learning: Interleaving Teaching and Practice for Transferable Agent Skills

    Socratic Skill Learning: Interleaving Teaching and Practice for Transferable Agent Skills

    arXiv:2610.17860v1 Announce Type: new Abstract: Agent Skills improve LLM agents by making task knowledge reusable across sessions. Learning transferable Skills requires evidence about a procedure and its conditions of use, which a successful task attempt can leave untested. We introduce Socratic Skill Learning (SSL), which interleaves expert teaching with Student practice. An Educator guides investigation while the Student remains the sole environment operator and Skill author, able to question, test, and adapt advice. To test reuse beyond the learning task, we construct SkillTransferBench, with 35 task families and 408 executable cases, pairing public variation specifications with held-out evaluation in fresh solver sessions. On the main 22-family, 155-case cohort, Fixed-Window SSL reaches 0.801 utility, versus 0.723 without a Skill, 0.761 for adapted Trace2Skill (trajectory distillation), and 0.751 for adapted SKILL-KD (contrastive distillation). Across three model pairs on shared families, interleaved guidance outperforms expert authoring and post-hoc teaching. Process analysis links guidance to Student writing and package revision; a case study shows the Student testing and refining a proposed procedure for later reuse. As demand for new lessons falls, the cost of fixed-window review grows. Issue-Guided SSL tracks unresolved questions across Skill revisions to select and focus review, reaching 0.805 utility with 61.7% fewer Educator tokens and 16.9% fewer total acquisition tokens than Fixed-Window SSL on the main cohort.

    Fallback brief based on the available RSS feed; no unsupported details have been added.

    Source: arXiv
    Original article: https://arxiv.org/abs/2610.17860

  • ECMR: Evidence-Aware Deliberation Control for Multi-Agent LLM Reasoning

    ECMR: Evidence-Aware Deliberation Control for Multi-Agent LLM Reasoning

    arXiv:2610.17869v1 Announce Type: new Abstract: Multi-agent Large Language Model (LLM) systems typically commit to a deliberation protocol before inference. A fixed protocol cannot allocate computation differently to resolved and unresolved instances, and it may mistake repeated support for independent confirmation. We study this failure as semantic false consensus: a confident group answer supported by narrow, duplicated, or correlated rationales. We introduce ECMR, an evidence-aware controller over frozen role-conditioned LLMs. At each step, ECMR summarizes answer concentration, support diversity and independence, contradictions, role behavior, verification history, and remaining budget, then selects whether to propose, challenge, verify, arbitrate, diversify, correct a role, or stop. We formulate this decision as finite-horizon budgeted control and derive sufficient conditions under which state conditioning, risk-triggered verification, and role correction improve cost-adjusted utility. Across a declared held-out evaluation of 9,000 records from MedQA, CaseHOLD, and FinQA, ECMR-Full increases pooled accuracy from 62.1% to 84.9%, reduces false-consensus rate from 40.7% to 17.0%, and raises evidence-support rate from 58.0% to 88.7%. State shuffling loses 11.7 accuracy points with only 0.7 fewer rounds, while harder traces shift from early stopping toward arbitration. ECMR-Full uses the largest token budget, yielding the strongest absolute reliability rather than uniformly superior token efficiency.

    Fallback brief based on the available RSS feed; no unsupported details have been added.

    Source: arXiv
    Original article: https://arxiv.org/abs/2610.17869

  • Training LLMs for Multi-Agent Collaboration with Verifiable Information Rewards

    Training LLMs for Multi-Agent Collaboration with Verifiable Information Rewards

    Training LLMs for Multi-Agent Collaboration with Verifiable Information Rewards

    arXiv:2610.17893v1 Announce Type: new Abstract: Effective collaboration among large language model (LLM) agents in multi-agent systems requires sharing relevant evidence, requesting missing information, and incorporating teammates' contributions into decisions. Training these behaviors is challenging because final task outcomes provide limited feedback on the value of individual messages. We introduce CoSIR (Collaboration via Surprisal-based Information Rewards), a post-training approach that uses a simple, verifiable environment to teach collaboration behaviors that generalize to more complex, unseen tasks. We propose a Bayesian evaluator that scores shared information by its reduction in team surprisal, defined as the sum of the negative log probabilities assigned to the correct option given each agent's available evidence. Requests are scored by the potential reduction in the same quantity if the requested information were truthfully provided. Separate rewards encourage agents to use the received information in their private choices and calculations. We post-train Qwen3-4B, Qwen3-8B, and Gemma-3-4B-it through self-play and evaluate transfer to seven unseen natural-language collaboration tasks. CoSIR achieves the highest aggregate score, while its performance in general tasks remains competitive. Behavioral analyses show increased disclosure of private evidence and fewer judged failures to use teammates' input.

    Fallback brief based on the available RSS feed; no unsupported details have been added.

    Source: arXiv
    Original article: https://arxiv.org/abs/2610.17893

  • Agentic4PDM: Host-Governed Evidence Admissibility for Industrial Fault Diagnosis

    Agentic4PDM: Host-Governed Evidence Admissibility for Industrial Fault Diagnosis

    Agentic4PDM: Host-Governed Evidence Admissibility for Industrial Fault Diagnosis

    arXiv:2610.17786v1 Announce Type: new Abstract: 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.

    Fallback brief based on the available RSS feed; no unsupported details have been added.

    Source: arXiv
    Original article: https://arxiv.org/abs/2610.17786