Sign in

Category: Other

  • Monitoring latent reasoning in looped language models

    Monitoring latent reasoning in looped language models

    arXiv:2610.18127v1 Announce Type: new Abstract: Looped language models (LMs) reuse one block of layers several times per token generation, promising more latent computation at no additional storage cost. Despite their rising popularity, the analysis of looped LMs is still in its infancy: little is known about whether the iterative transformations actually improve their capabilities, or whether these models remain stable under prompt perturbation. We construct an inspection protocol rooted in Mechanistic Interpretability comprising five diverse lenses. We apply it to examine eight looped LMs from four families. Models differ in many aspects but the key one is whether the prompt is transmitted only within the looped state (carry loops: Ouro, LoopUS) or re-supplied at every iteration (re-read loops: Parcae, and Rec-OLMo & Huginn from the Raven family). The results of our study provide valuable insights concerning safety and efficient use of looped language models.

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

    Source: arXiv
    Original article: https://arxiv.org/abs/2610.18127

  • Mitigating Cross-Modal Hallucinations by Correcting Modality Misrouting in Omnimodal LLMs

    Mitigating Cross-Modal Hallucinations by Correcting Modality Misrouting in Omnimodal LLMs

    arXiv:2610.18141v1 Announce Type: new Abstract: Omnimodal large language models (OLLMs) are susceptible to cross-modal hallucinations under audio-visual interference. We find that, for a substantial fraction of incorrect joint predictions, the question-relevant unimodal branch can still recover the correct answer, suggesting that task-relevant evidence can remain recoverable from the relevant modality even when it is not reflected in the joint prediction. We refer to this recoverable failure pattern as \emph{modality misrouting}. We propose CaRe (Conflict-aware Residual Intervention), a training-free inference-time method for identifying and correcting modality misrouting. CaRe uses a text-only modality probe to identify a candidate modality-specific counterfactual branch, and flags potential misrouting when its prediction conflicts with the original joint prediction. For such cases, CaRe computes a residual direction from the discrepancy between the counterfactual and fused representations and uses it to steer the original multimodal state toward the relevant modality evidence, while retaining both modalities in the original audio-visual inference path. The intervention strength is adapted based on the confidence of the counterfactual branch. Experiments on CMM and AVHBench across two OLLMs show that CaRe consistently outperforms the evaluated inference-time hallucination-mitigation baselines.

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

    Source: arXiv
    Original article: https://arxiv.org/abs/2610.18141

  • AM-Bench: Understanding Agents under Task Underspecification across Models and Harnesses

    AM-Bench: Understanding Agents under Task Underspecification across Models and Harnesses

    arXiv:2610.18090v1 Announce Type: new Abstract: Ambiguous or incomplete task specifications complicate both execution and clarification for language-model agents. Yet agents' responses to these information gaps remain poorly characterized across models and execution harnesses. We present AM-Bench, a benchmark built from 48 tasks adapted from Terminal-Bench 2.0 and Harness-Bench. Each task includes a fully specified reference and six variants spanning ambiguous or missing goals, context, and constraints. We evaluate every pairing of five models and four harnesses over 20,160 runs. Our results reveal distinct execution deficits: goal gaps hinder completion, context gaps increase token use, and constraint gaps weaken compliance without necessarily preventing completion. Missingness lowers success more than ambiguity in all three domains. These effects also reshape system comparisons: advantages under complete information need not persist, and rankings depend on model $\times$ harness pairings and the evaluation criterion — completion, success, or repeat consistency. Estimates based on observed clarification requests and matched fully specified runs further suggest that clarification could recover unfinished work while leaving most constraint violations unresolved. Together, these findings motivate joint model-harness evaluation across information conditions and targeted clarification of unresolved requirements before dependent actions. To support future research on agents under task underspecification, we provide the AM-Bench project repository at https://github.com/s4-lab-cuhksz/AM-Bench.git.

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

    Source: arXiv
    Original article: https://arxiv.org/abs/2610.18090

  • LifeSearch: Benchmarking Deep Research Agents for Real-World Life and Productivity

    LifeSearch: Benchmarking Deep Research Agents for Real-World Life and Productivity

    arXiv:2610.18092v1 Announce Type: new Abstract: Deep research (DR) agents address open-ended information needs through multi-step reasoning, long-horizon web search, and evidence synthesis. However, existing benchmarks primarily focus on academic research or synthetic tasks, leaving DR agents' capabilities in real-world life and professional productivity settings insufficiently evaluated. To bridge this gap, we introduce LifeSearch, a challenging benchmark comprising 203 Chinese and English tasks derived from real-user query seeds across 7 concrete life and productivity domains. With more than 4,500 hours of human annotation, we construct over 4,000 expert-written, fine-grained rubrics, covering both report-content criteria for coverage and accuracy and concrete criteria specifying values, units, dates, and URLs. We conduct extensive experiments on 12 advanced DR agents under a unified evaluation harness, systematically analyzing their performance patterns and failure modes. We find that even the best-performing frontier agent, GPT-5.6 Sol, achieves a score of only 63.4%, leaving substantial room for improvement on realistic life and professional DR tasks. We select the grading configuration by comparing candidate LLM judges against human rubric labels, and a human ranking study shows strong alignment between aggregate benchmark scores and human judgments (Spearman's $\rho = 0.89$, Kendall's $\tau = 0.81$). LifeSearch provides a rigorous evaluation framework and foundation for advancing DR agents toward real-world life and productivity.

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

    Source: arXiv
    Original article: https://arxiv.org/abs/2610.18092

  • CompanionSafe: From Multi-turn Safety Evaluation to Guardrails for AI Companions

    CompanionSafe: From Multi-turn Safety Evaluation to Guardrails for AI Companions

    arXiv:2610.18095v1 Announce Type: new Abstract: AI companions provide users with emotional support and ongoing companionship, but their sustained relational interactions also introduce distinct safety risks. Prior work largely targets general harms or specific companion platforms and risk categories, while relying on manually collected conversations, limiting scalable and user-grounded evaluation and mitigation. To address this, we introduce CompanionSafe, a unified evaluation-to-mitigation framework for AI companion safety. Its evaluation component, CompanionEval, provides scalable multi-turn evaluation by constructing 1,300 relationally grounded settings from diverse personas, matched companion characters, and dialogue scenarios across four turn tiers. Its mitigation component, CompanionGuard, converts benchmark-exposed failures into turn-localized supervision for companion-specific risk detection. Our results show that even strong LLMs and existing guard models remain vulnerable to companion-specific relational harms, while both closed- and open-source models exhibit increasing safety risks as interactions become longer. Together, CompanionEval and CompanionGuard form a practical evaluation-to-mitigation loop for AI companion safety, turning relational safety failures exposed during multi-turn interaction into supervision for companion-specific guardrails.

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

    Source: arXiv
    Original article: https://arxiv.org/abs/2610.18095

  • AReaL-RSI: Adaptive Scaling and Coordination of Recursive Self-Improvement

    AReaL-RSI: Adaptive Scaling and Coordination of Recursive Self-Improvement

    AReaL-RSI: Adaptive Scaling and Coordination of Recursive Self-Improvement

    arXiv:2610.18083v1 Announce Type: new Abstract: Scaling recursive self-improvement requires additional computation to produce useful research progress in reaching persistent objectives. Intuitively, more researcher agents can explore more hypotheses, but early evaluation scores might misrepresent their promise, shared findings could lose their applicability conditions, and useful procedures could remain confined to completed investigations. In this paper, we present AReaL-RSI, a framework for organizing a persistent research team of agents without updating backbone LLM weights. We formulate the scaling problem in terms of evaluated outcomes and whole-system resource expenditure. Concretely, a leader agent selects task-appropriate research orientations and guides ongoing investigations; conditional memory sharing distinguishes unresolved problems from supported findings and enables recipient adaptation. During recursive evolution, after each campaign, evidence-based review revises researcher orientation, knowledge, and skills for later campaigns. Experiments compare AReaL-RSI with Codex-Goal on downstream harness optimization, GPU kernel optimization, and AI research tasks using two backbones. Under the reported resource allocations, AReaL-RSI improves Terminal Bench performance by 2.2 percentage points for each backbone and increases mean KernelBench speedup by 32.2-36.8%; further scalability comparisons favor the design of AReaL-RSI over native scaling: combining experience sharing with specialized researcher roles yields 1.9-27.5% lower kernel latency than independent exploration and 1.3-33.9% lower latency than sharing alone across all seven comparable task-backbone pairs.

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

    Source: arXiv
    Original article: https://arxiv.org/abs/2610.18083

  • ResearchFlow-Eval: Tracing the Execution Gap in End-to-End Multi-Claim Autoresearch

    ResearchFlow-Eval: Tracing the Execution Gap in End-to-End Multi-Claim Autoresearch

    ResearchFlow-Eval: Tracing the Execution Gap in End-to-End Multi-Claim Autoresearch

    arXiv:2610.18088v2 Announce Type: new Abstract: Autoresearch systems increasingly undertake entire research projects. In practice, scientific research requires systems to pursue multiple interdependent claims through a continuous, multi-stage workflow and revise experiments as evidence accumulates. Existing evaluations of autoresearch systems, however, typically score isolated tasks or final artifacts, leaving these process-level capabilities largely unmeasured. We therefore introduce ResearchFlow-Eval, a fine-grained framework for assessing continuous scientific execution and iteration at both the stage and claim levels. Each evaluation is grounded in a published anchor paper, from which we derive stage-specific rubrics that decompose each research stage into dimensions and separately scored rubric items. Using these rubrics, we score each research stage and examine experimental execution in detail, focusing on multi-claim completion and revisions across attempts. We apply the evaluation framework to general-purpose agent harnesses, skill-augmented harnesses, and systems with research-specific orchestration. Across all evaluated systems, experimental execution consistently lags behind design and planning. Within execution, systems struggle to produce high-quality results and meet claim requirements, and repeated attempts rarely yield measurable improvements. Moreover, neither skill augmentation nor research-specific orchestration reliably yields higher scores. ResearchFlow-Eval thus extends autoresearch evaluation beyond isolated, single-objective runs to continuous workflows in which systems pursue multiple claims and refine their work across iterations.

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

    Source: arXiv
    Original article: https://arxiv.org/abs/2610.18088

  • One-Sided Verification Under Limited Expert Review

    One-Sided Verification Under Limited Expert Review

    arXiv:2610.18089v1 Announce Type: new Abstract: AI has become increasingly helpful in scientific discovery, yet human expert review remains essential for those problems without reliable automated evaluation, posing a fundamental challenge as candidate generation scales beyond available review capacity. This paper studies verification under limited human effort, where rare valid solutions need to be prioritized while invalid candidates should be filtered out to reduce human workload. We adopt the one-sided verification objective that maximizes the rejection rate of invalid solutions (TNR) under a constraint on the false-rejection rate of valid ones (FNR), making human review cost an explicit term to minimize. Drawing on the intuition that verifying a specific error can be easier than discovering one, we introduce OSVerify, an algorithmic framework that decouples error proposal from error validation. The error proposer searches for errors in solutions across different granularities by hierarchical decomposition, while the validator distinguishes substantial errors from minor or hallucinated ones. Experiments on competition- and research-level benchmarks show that OSVerify reduces the number of human reviews of invalid solutions by 46% on average compared to voting baselines under the same empirical low FNR constraint. Our post-training of the validator further improves the reduction to 57%. As high-impact real-world use cases, we apply OSVerify to identify errors in published research papers that are subsequently confirmed by the original authors and help resolve three Langlands open conjectures that are confirmed by experts, demonstrating its utility to facilitate human-AI research collaboration.

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

    Source: arXiv
    Original article: https://arxiv.org/abs/2610.18089

  • SHELDON: Reasoning through Dual Search over Hypothesis and Observation Spaces

    SHELDON: Reasoning through Dual Search over Hypothesis and Observation Spaces

    SHELDON: Reasoning through Dual Search over Hypothesis and Observation Spaces

    arXiv:2610.18025v1 Announce Type: new Abstract: Test-time scaling has enabled LLMs to solve increasingly complex reasoning, discovery, and optimization tasks. However, existing approaches often gather observations while seeking evidence for current hypotheses, then generate new hypotheses conditioned on those hypotheses and their associated evidence. This couples observation discovery to existing hypotheses, favoring local refinements over exploration of unknown hypotheses regions. Inspired by the hypothetico-deductive method (Hempel, 1945) and dual-space models of scientific discovery (Klahr & Dunbar, 1988), we introduce SHELDON, a scientific reasoning harness that separately represents and jointly explores hypothesis and observation spaces. By actively seeking new observations along with new hypotheses, SHELDON can discover observations that its current hypotheses do not explain. These unexplained observations expose gaps in its understanding, motivate new investigations, and guide the generation of hypotheses beyond refinements of existing ones. Across diagnosis, abstract reasoning, and optimization benchmarks, SHELDON outperforms evaluated baselines by up to 26.7 points. Additional analysis shows that SHELDON generates up to 4.5x more novel solutions.

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

    Source: arXiv
    Original article: https://arxiv.org/abs/2610.18025

  • Beyond Black Boxes: Visual Grounding for Text Embeddings

    Beyond Black Boxes: Visual Grounding for Text Embeddings

    arXiv:2610.18047v1 Announce Type: new Abstract: In this paper, our goal is to represent text embeddings as sketches for three main reasons. First, to visualize text representation and to explore their potential their potential for AI explainability. Second, to investigate the potential benefits of the sketch-based representation for information retrieval. Third, to explore their potential for reasoning, drawing inspiration from the concept of mental imagery. We propose a sketch-based visual grounding framework that transforms text representations into visual topographic sketches. Our approach aims to emphasis the semantics content encoded in the text embeddings through the corresponding sketch. Evaluations are conducted on the MS-COCO dataset to examine the utility of these sketches for text retrieval. The comparative study of SBERT and Sketch-based method reveals that SBERT retains an advantage in strict top-1 retrieval accuracy while achieving comparable performance to the sketch-based method in top-5 retrieval. A cascaded approach combining SBERT and the sketch-based method outperforms SBERT alone, suggesting that the Sketch-based representation could offer significant potential for information retrieval if trained directly on text.

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

    Source: arXiv
    Original article: https://arxiv.org/abs/2610.18047