TodayNewsResearchFieldsStacksMarketAnalytics
⌘K

Research

New papers ranked by attention, with their code, models and discussion linked. Pick a field on the left.

WeekMonthQuarterAll
NewestMost relevant

Papers

Open problems

Rising research topics

Ask the research

Sample
ByteTrail · AI and developer-tools intelligence
NewsResearchStacksAPI
Fields · this week
All fields3622Multimodal565Agents540Frontier LLMs462Inference & serving276Image segmentation186Graph learning173Learning verifiable rewards1703D scene164Evals108Voice AI104Classifier & causal discovery89Forecasting time81Flow matching80Training & fine-tuning64Teacher policy distillation52All 32 fields

Open problems across fields

  • General in-context learning for embodied agents1 paper raises it · 0 address it

    Enables models to adapt to new tasks and environments without retraining, improving robustness in real-world deployment.

    • Has GPT-6-Astra Achieved Embodied Intelligence?raises
  • Cost and latency in embodied control loops1 paper raises it · 0 address it

    High computational and time costs limit real-time applicability of agentic systems in dynamic environments.

    • Has GPT-6-Astra Achieved Embodied Intelligence?raises
  • Physical-state verification and failure recovery1 paper raises it · 0 address it

    Agents must reliably detect and correct errors in physical interactions to avoid irreversible failures in real-world tasks.

    • Has GPT-6-Astra Achieved Embodied Intelligence?raises
  • Long-horizon task preservation in embodied agents1 paper raises it · 0 address it

    Maintaining progress over extended sequences is critical for complex, multi-step tasks in robotics and navigation.

    • Has GPT-6-Astra Achieved Embodied Intelligence?raises
  • Open-source stacks for generalist computer-use agents1 paper raises it · 1 addresses it

    Closed systems hinder reproducibility and systematic study of agent design for real-world computer tasks.

    • OpenGCUA: Toward a Fully Open Stack for Generalist Computer Useraises · addresses

Named by an AI from these papers' abstracts.

Rising research topics

Coming with more sources: more tagged papers
  • Federated learning51+37.8%
  • Agents540+3.4%
  • Quantum machine learning240.0%
  • Sensing communication150.0%
  • Frontier LLMs462−3.5%
  • Character recognition OCR17−5.6%
  • Image segmentation186−10.1%
  • Voice AI104−10.3%

Papers

  • arXiv cs.LGOct 19

    Graph-to-Table Interfaces Control Relational Generalisation

    Alessandro Cagiano, Lorenzo Molfetta, Gianluca Moro, Matteo Zignani, Pasquale Minervini

    Graph-to-table systems combine three design choices: an encoder that maps relational evidence to feature rows, a context constructor that selects labelled examples, and a tabular decoder. We investigate whether these components can be evaluated independently through matched comparisons that change one component while holding the rest of the pipeline and the evaluation constant. Across logistic regression, CATBOOST, and TABPFN-3 on CLUTRR, 57 GraphLog worlds, and 57 knowledge graphs, we show that conclusions about one component can change when the others change. On CLUTRR, absolute positional encodings maintain all distinctions among the evaluated queries and fit the short-path setting nearly perfectly; yet, they generalise worse than relation-count features because the supported prefix acts as a shortcut that breaks down on longer paths. On GraphLog, encoder preference depends on the decoder, while the relation-count representation degrades as CatBoost tree depth increases. Across different knowledge graphs, adding the frozen ULTRA score to local features is consistently useful, whereas adding local features to the score has a smaller and less stable effect. A pointwise TABPFN-3…

    PDF
  • arXiv cs.AIOct 19

    Map-Distribution Mixture-of-Experts for Multi-Agent Pathfinding

    Fumimaro Suzuki, Keisuke Okumura

    Designing capable neural policies for multi-agent pathfinding (MAPF), which map local observations to action distributions, represents an important challenge in multi-agent learning, with practical relevance to scalable collective automation problems such as warehouse logistics. In contrast to prior studies focusing primarily on individual policy design, this study explores a meta-level Mixture-of-Experts (MoE) approach to learning-based MAPF. Specifically, given a collection of compact yet high-performing experts specialised for different map distributions, our architecture learns a router that selectively fuses their outputs according to each agent's local situation. We instantiate and validate this MoE approach with a commonly used graph neural network-based policy as well as a newly developed recursive action-token refinement model. Combined with supervised and reinforcement learning fine-tuning of the experts, our experiments show that MoE generally improves upon the pretrained policy and outperforms existing leading methods. At the same time, our findings reveal that appropriately trained, parameter-matched monolithic models still outperform MoE, highlighting a nuanced role…

    PDF
  • arXiv cs.CROct 19

    NIOCIS: Typed-Decision Next-Hop Routing with Node-Conditioned Option Spaces for Tool-Use Agents

    Jin Han, Mingfeng Xin, Feng Liang, Jingtao Yu

    Tool-use agents pay per decision: at each hop a language model re-reads the state and thinks for seconds, though its actions are finite and decisions recur. We present NIOCIS, a routing layer that folds execution logs into a loop-collapsed action graph (forward transitions plus recovery back-edges) answering one typed question: which declared option at a state, plus stop, does the fleet take next? A small model reads a calibrated distribution over them in one pass, emitting no text. On 1,615 production security-operations episodes we measure what the layer replaces, returns and is bounded by. Replaces: the typed encoder matches the logged next hop on 32.2% of the 3,875 held-out decisions (34.9% within the declared options) in 10 ms of encoder time (19.5 ms for the typed-choice form), against 2.2 s per LLM hop; two feature readouts reach 32.8% and 32.3%, an ordering the paired test does not resolve, so the typed layer is chosen for cost, not a separated lead. Tuning: jpt-4b reaches 9.9% zero-shot and 31.9% fine-tuned, a gap an exact paired test does not resolve (p=0.68), at 244 ms. Returns little: the realised hop falls outside the declared options for 7.9% of decisions and…

    PDF
  • arXiv cs.CROct 19

    Auditor-Assisted Summary-Channel Verification for Hosted LLM Identity Substitution

    Ziyi Zhang, Ziyao Wang, Guoheng Sun, Ang Li, Jian Li

    Hosted LLM services increasingly expose model identity as a product claim, but external users and auditors often cannot inspect which model configuration served a request. We study an auditor-assisted regime in which a trusted auditor enrolls claimed identities and prepares verification material before deployment, while audit-time verification uses only the claimed identity and released output, without runtime access to model internals, inference logs, routing decisions, or provider metadata. We propose SUMMARK, a summary-channel watermarking framework that uses user-visible reasoning summaries as a keyed audit surface. During setup, SUMMARK constructs identity-specific vocabulary carriers, trains lightweight summary adapters, and calibrates per-identity thresholds. At deployment time, a keyed statistical test assesses whether the released summary is consistent with the claimed identity and, when needed, attributes the most likely enrolled identity. Across model families, scales, and task domains, SUMMARK reliably detects cross-family and cross-scale substitutions at low false-positive rates while preserving task-facing answer quality. We further study FP16->INT8/INT4…

    PDF
  • arXiv cs.AIOct 19

    ClueFlow: Learning Long-Horizon Search through Attributed Research-State Transitions

    Yicheng Wang, Wentao Tan, Yidan Huang, Yifei Liu, Qiong Cao

    Long-horizon search requires agents to acquire relevant evidence and integrate it into an evolving research state. Existing methods maintain research states to guide exploration or assign turn-level progress signals, yet grounding these signals in explicit, attributable state changes remains underexplored. We introduce ClueFlow, which learns long-horizon search from attributed research-state transitions. ClueFlow constructs Source-State-Final attribution chains that connect evidence-acquiring browser actions, Evidence and Candidate updates, and the final answer supported by those updates. During search, ClueFlow records typed state changes and potentially supporting browser actions, then applies gold-conditioned semantic validation and source tracing after execution. We use this attribution to guide both supervised fine-tuning and reinforcement learning. During SFT, attribution selects which decisions receive supervision with their original interaction contexts. During Turn-PPO, the same attribution augments outcome-based turn advantages with credit assigned along the Source-State-Final chains. Transition-level validation also recovers useful supervision from gold-consistent…

    PDF
  • arXiv cs.AIOct 19

    GraphEvoResearcher: Graph-Aware Training-Free Self-Reflective Reasoning for Cost-Bounded Multi-Hop Question Answering

    Suxing Liu

    Multi-hop question answering (QA) requires models to chain intermediate conclusions while remaining cost-aware. Existing training-free self-reflective protocols (generate -> critique -> revise) improve accuracy but operate on a flat token stream: revisions cannot identify which prior step is unreliable, and early stopping cannot exploit structural convergence. We introduce GraphEvoResearcher, a training-free protocol that lifts EvoResearcher's self-reflective meta-reward onto an explicit reasoning graph - nodes are intermediate conclusions/evidence and edges encode support, contradict, and depends_on. A graph-aware meta-reward combines correctness, efficiency, reflection, diversity, and four structural signals (connectivity, acyclicity, branch coverage, path convergence) to decide whether to revise, backtrack, or stop. A graph-convergence early-stop terminates when evidence branches converge on a single conclusion. On a real LLM (DeepSeek), over GSM8K, MATH, and BBH (n=50 each), GraphEvoResearcher reaches 98%, 92%, and 82% respectively, the highest of all baselines, with the largest gains on the hardest set (MATH: +24 pp over single-shot, +12 pp over flat reflection), while…

    PDF
  • arXiv cs.AIOct 19

    On the Benefits of Uncertainty Estimation for Species Classification: A Case Study on Optimizing Expert re-Annotation

    Kamenan N'Gadi, Martin Laviale, C{é}dric Pradalier, J{é}r{é}my Fix

    Automated identification of diatoms from microscopic images is a cornerstone of large-scale freshwater biomonitoring, yet the high diversity of species and strong class imbalance pose significant challenges for reliable classification. In this study, we develop a ResNet-18 baseline for a 759-class diatom dataset and investigate how calibrated confidence estimates support selective classification to reduce expert workload without sacrificing taxonomic integrity. While the initial model exhibits overconfidence with an Expected Calibration Error (ECE) of 0.117, post-hoc temperature scaling (T = 2.12) dramatically improves reliability, lowering the ECE to 0.055.By leveraging these calibrated probabilities within a triage framework, we demonstrate that a Selective Macro-F1 score of 99.01% can be maintained at 66.2% coverage (rejection threshold $τ$ = 0.934). Qualitative analysis reveals that the system effectively functions as an intelligent filter, consistently deferring rare taxa-such as AAMB and AASI-and ambiguous morphologies for expert review. Our findings, supported by the torch-uncertainty framework, highlight the potential of simple calibration techniques to make automated…

    PDF
  • arXiv cs.LGOct 19

    Correctness-Dependent Asymmetric Target Distributions for Self-Distillation Policy Optimization

    Suwan Yoon, Seongryong Jung, Changhee Lee

    Self-distillation policy optimization provides dense token-level supervision for LLM post-training through feedback-conditioned self-teachers. However, directly matching the self-teacher can disrupt successful behaviors on correct rollouts while providing insufficient correction on incorrect ones. We propose Asymmetric Policy Optimization via Self-Distillation (APSD), which constructs correctness-dependent targets by mixing student and self-teacher distributions: interpolation preserves successful behaviors on correct rollouts, while extrapolation beyond the self-teacher strengthens correction on incorrect ones. We analyze APSD through divergence decomposition, reverse-KL barycentric geometry, and gradient analysis, highlighting the importance of gradient flow through student-dependent targets. Experiments under reinforcement learning with verifiable rewards and rich feedback show that APSD achieves strong overall performance against reinforcement-learning and self-distillation baselines and matches SDPO performance with 2.6x fewer training steps on average across Qwen3 model scales.

    PDF
  • arXiv cs.AIOct 19

    GLOBE: Geometry-Led Online Behavioral Early Exit via Unit-Sphere Trajectories

    Xinyue Peng, Zhenlin Liang, Meng Cai, Hua Wang

    Chain-of-thought (CoT) reasoning can improve problem solving, but models often keep generating after the correct answer is already reachable; the extra steps raise serving costs and may replace a correct intermediate result with an incorrect one. We propose GLOBE (Geometry-Led Online Behavioral Early Exit), an online, training-free algorithm that terminates the model's CoT process early. GLOBE embeds each completed reasoning segment as a point on a unit sphere and reads the shape of the resulting semantic trajectory. GLOBE first applies a trial phase that generates short trial answers in a separate branch, stopping the main stream on an accepted trial after checking confidence against a threshold. If generation continues, a trajectory phase stops the stream once this path repeatedly reverses direction with little net progress. On five benchmarks including mathematical reasoning, tool calling, and agent memory, GLOBE cuts output tokens by 49.7% and active end-to-end wall time (E2E) by 51.0% across two models, and achieves a five-task average of 80.58%, comparable to Full CoT.

    PDF
  • arXiv cs.ROOct 19

    Reconstruction and Discrete-Event Simulation Assessment of an Analytical

    Mohsen Reda Mahmoud Moursi, Ahmed Stohy

    This article presents an analytical-DES benchmark for intra-aisle robotic picking in automated warehousing. The investigated cycle combines horizontal shuttle travel, tote handling and item picking at storage locations. Simulation results are compared with the analytical formulation of Lerher et al. under the same rack geometry, shuttle-motion, handling and picking conditions, and the same definitions of cycle time and derived item throughput. Reproducing the published analytical tables requires the distance interpretation dES = 1.5 m and dTB = 0 m. The analytical-DES benchmark comprises 180 scenarios formed from three rack lengths, two paired motion profiles and n = 1 to 30 visited picking locations, with ten simulation replications per scenario. The six n = 1 cases are reported separately because no travel-between component is present. Across the remaining 174 scenarios, the mean absolute relative cycle-time discrepancy is 0.8655%, the median is 0.6758%, and the maximum is 7.0370%. The mean absolute error is 2.411 s and the RMSE is 2.744 s. The simulated scenario-mean cycle time is below the analytical value in all 174 principal scenarios. The results therefore show close…

    PDF
  • arXiv cs.MAOct 19

    Behavioral Probes for Information Flow in LLM Swarms

    Junhui Chen, Yu Zhang, Lantian Li, Dong Wang

    Most existing approaches to LLM swarm optimization are utility-driven, focusing on final task utility while leaving the processing, integration, and reliance of information within individual interactions largely implicit. To address this, we study LLM swarm interactions from an information-flow-based view and introduce behavioral probes to quantify information flow patterns. Specifically, we repurpose External Context Score (ECS) and Parametric Knowledge Score (PKS)---originally designed for hallucination analysis---to measure a node's external-context dependence and parametric-knowledge dependence, respectively. Across controlled and realistic swarm settings, we observe consistent patterns: ECS increases with input relevance and distinguishes useful multi-source contributions, while PKS decreases as informative context accumulates. Building on this heuristic interpretation, we demonstrate how these probes can complement utility-driven structure optimization in two controlled applications. Probe-guided node pruning reduces redundant communication and token consumption, and probe-guided reasoning-path search accelerates convergence compared to utility-only baselines. Our empirical…

    PDF
  • arXiv cs.CVOct 19▲ 3

    Token-Set Choice Confounds POPE: A Systematic Audit of Yes/No Extraction in VLM Hallucination Evaluation

    Kesav Kumar Jayakumar, Karthigeyan Thilak

    We set out to reproduce a recent hallucination-mitigation result on the POPE benchmark. The LLaVA-1.5-7B baseline we measured, 82.21 F1 on the adversarial split, sat 1.21 to 8.67 points above the adversarial baselines we planned to compare against (81.00, 79.30, and 73.54). We looked at the evaluation code and found a readout choice that moves F1 on its own. A two-token logit readout decides yes versus no by comparing two vocabulary IDs, 3582 ("yes") and 1217 ("no"). Across 9,000 greedy-decode questions spanning all three splits, neither ID is generated even once. The model emits " Yes" (token 3869) and " No" (token 1939), because SentencePiece prepends a space byte after the prompt suffix "ASSISTANT:". Read with an eight-token lookup that covers the space-prefixed surface forms, LLaVA-1.5-7B scores F1 0.8221, 0.8498, and 0.8713 on the adversarial, popular, and random splits. That 6.13-point adversarial shift exceeds the adversarial gain reported by five of the six papers we surveyed. None of them states its readout, and our reference ran under 4-bit NF4 quantization, so we cannot say how much of any reported gain a matched evaluation would keep. That comparison stays unresolved…

    Code
  • arXiv cs.AIOct 19

    ABACUS: Program-Guided Multistep Reasoning over Frozen Judgment Models

    Yuhao Wang, Zelin Zang

    Judgment models answer semantic questions by scoring a finite set of candidate outcomes. Can reusable programs turn these local decisions into powerful multistep reasoning? We introduce \method, a framework that jointly constructs judgment schemas and composition programs for frozen judgment models. A generative teacher designs the procedure offline; the judgment model resolves local semantic questions online, and the saved program composes its decisions into an answer. We study three allocations of design effort between humans and the teacher, focusing on construction through a shared interface. We instantiate the framework with Kev. On three selected BIG-Bench Hard tasks, nine independently constructed programs solve all 450 executions of 150 development inputs. A separate deployment study freezes three programs after development-set reference-agreement refinement and evaluates them on 600 held-out questions. These programs achieve near-perfect 99.67\% macro accuracy, versus 64.00\% for direct Kev and 68.80\% for final-answer-only Qwen3.5-4B. They attain comparable observed accuracy to Qwen's unrestricted response policy (99.07\%) with an \textbf{8.43-fold online speedup}:…

    PDF
  • arXiv cs.ROOct 19

    PaceVLA: Adaptive Temporal Action Quantization in Vision-Language-Action Models

    Hojin Jeon, Jimin Lee, Taekwan Kim, Nayoung Oh, Taeyoung Kim +4

    Fast and reliable manipulation is crucial for practical robot deployment. Although Vision-Language-Action (VLA) models have recently shown remarkable progress as generalist robot policies, their execution often remains temporally inefficient. A key source of this inefficiency is that policies learn fine-grained temporal patterns from teleoperated demonstrations, requiring many low-level action steps. Temporal action quantization offers a simple way to accelerate execution by aggregating consecutive low-level actions into temporally coarser actions. However, applying action quantization without considering when fine-grained control is required introduces a speed-accuracy trade-off: accelerated actions may efficiently reduce redundant steps in some phases, while discarding critical motion details in precision-sensitive interactions. To address this, we propose PaceVLA, a unified framework for adaptive temporal execution in VLAs that integrates two coupled components: (1) mode-specific action decoders built on a shared action expert, supporting multiple temporal granularities and prediction horizons, and (2) a quantizability-guided mode selection scheme which decides whether coarse…

    PDF
  • arXiv cs.CLOct 19

    How to get the best and fairest performance out of your ASR system using activation steering

    Felix Herron, Alex Colagrande, Solange Rossato, François Portet, Alexandre Allauzen +1

    Activation steering for ASR systems is an underexplored technique in improving both ASR performance and demographic fairness. We investigate two forms of activation steering: paired activation subtraction, and supervised optimization. We find the former to be ineffective at ameliorating ASR performance whatsoever, while the latter is quite effective at deriving steering vectors (SVs) that improve at once overall ASR performance and demographic fairness along such diverse axes as gender, age, and dialect. We also explore what types of data---from the most to the least personal---are necessary for calculating or training SVs. First, we show significant performance in performance from training SVs using an eclectic group of speakers from the same dataset. Furthermore, we find that vectors trained using acoustically similar speakers leads to ASR performances that are competitive or superior to vectors trained on the same speaker, or speakers from the same labeled demographic group. This finding shows that we can harness activation steering for few-shot adaptation given access to a speaker's demography, or zero-shot adaptation to unseen speakers without the need for any labels at all.

    PDF
  • arXiv cs.CVOct 19

    HORIA: 4D Human and Object Reconstruction from a Monocular Video with Interaction-Aware Re-Rendering

    Hyeongjin Nam, Taeryung Lee, Daniel Sungho Jung, Kyoung Mu Lee

    Joint 4D reconstruction of a human and object from a monocular video is essential for understanding how people interact with their environment. While recent methods have made noticeable progress, capturing such human-object interactions remains difficult due to two main challenges. First, a video typically contains composite semantic context spanning multiple interaction phases, making it difficult to track the temporal changes of the interaction in the reconstruction. Second, under human-object occlusion, a single-view observation contains incomplete visual information about the interaction, resulting in geometrically inconsistent reconstructions. To address these challenges, we introduce HORIA, built upon two core designs. First, we decompose the entire input video into temporally grounded and semantically distinct interaction phases with motion-aware captioning, obtaining a specific text description for each phase. Second, conditioned on these text descriptions of the interaction, we propose an interaction-aware re-rendering that compensates for the limited single-view observation. Specifically, we render the initially reconstructed 4D human and object from novel viewpoints…

    PDF
  • arXiv cs.AIOct 19

    EmbodiedWorld-200K: Toward Embodied World Agents via Embodied-Planning Dataset and Interactive World Models

    X. Feng, J. Tang, Z. Lin, L. Chen, S. Shao +2

    Building embodied agents that can perceive, reason, and act across diverse 3D worlds is a central research direction toward artificial general intelligence. Yet most existing work remains confined to specific tasks in a single scene and transfers poorly to new environments, leaving general embodied agents for open-world settings under-explored. We refer to such agents as Embodied World Agents (EWAs), whose defining property is the ability to understand diverse visual environments and execute general actions in open-world conditions. To advance EWA research, we study open-world embodied navigation-planning and release EmbodiedWorld-200K, a large-scale dataset of over 200K samples spanning diverse scenes. Each example is equipped with multi-level annotations, ranging from low-level camera-motion trajectories to high-level semantic instructions. The dataset also provides unified evaluation splits and task-specific metrics, supporting offline pretraining and fair evaluation of EWAs. Beyond offline supervision, a defining characteristic of an EWA is its interaction with the environment; training solely on offline data is therefore insufficient, especially for generalizing to scenes…

    PDF
  • arXiv cs.AIOct 19

    Productive State-Space Exploration for Multi-turn RL in LLM Agents

    Mohammed Haroon Dupty, Yong Liang Goh, Song Guo, Wee Sun Lee

    Reinforcement Learning (RL) for Large Language Model (LLM) agents in multi-turn, long-horizon environments remains challenging due to inefficient action selection and repetitive behavioral patterns. In particular, agents often become trapped in high-confidence yet unproductive behaviors, repeatedly executing invalid actions or entering action loops that hinder task completion. We observe that these frequently violate environment preconditions, revealing a mismatch between the agent's representation of the internal state and the dynamics of the underlying environment. In addition, repetitive high-confidence actions lead to cyclical behaviors that provide little to no progress towards the goal. We argue that addressing these challenges requires more productive task-aligned exploration to improve the agent's understanding of environment dynamics. Motivated by intrinsic curiosity-driven exploration, we propose a conditional state-space exploration framework that balances task completion with intrinsic information-seeking behavior. Specifically, we introduce an intrinsic reward that penalizes actions whose observation duplicates prior state memory. This provides the benefit of…

    PDF
  • arXiv cs.AIOct 19

    CXBench: A Benchmark for Process-Compliant LLM Agents in Regulated Customer-Experience Workflows

    Boxi Yu, Yuzhong Zhang, Zhenfeng Su, Linfu Xi, Yinghan Yao +5

    Tool-using language agents increasingly perform regulated customer-service workflows, where a correct final state is insufficient: agents must also provide disclosures, obtain consent, and follow required procedures. Existing tool-agent benchmarks largely score final business states, accepting trajectories that reach correct outcomes through non-compliant processes. We introduce cxbench, a benchmark that evaluates outcome and process compliance separately across six regulated domains. Each task combines a customer request, a tool-based environment, and explicit process requirements. Rule cards link cited regulatory obligations to observable trace evidence. A hybrid grader combines deterministic checks for ordering and authority with an LLM judge for semantic requirements. We define a false-pass as an outcome-pass run that fails process checks. Across seven models and 120 tasks, 55.5% of the 840 retained executions are false-passes, representing 80.1% of outcome-passing runs; only 13.8% pass both checks. Process-inclusive evaluation changes the observed model ordering and exposes differences hidden by outcome-only scoring. cxbench makes these failures inspectable through…

    PDF
  • arXiv cs.CLOct 19▲ 28

    AdaExploreBench: Benchmarking LLM Agents for Proactive Exploration and Test-time Adaptation in Evolving Environments

    Rui Wang, Zishen Lai, Jiayu Liu, Cheng Qian, Jeonghwan Kim +13

    Large Language Model (LLM) agents are increasingly deployed in unfamiliar and evolving environments, requiring them to proactively explore, understand, and adapt to environmental dynamics. However, existing benchmarks rarely test whether agents can proactively discover how an environment works and adapt as it evolves. To address this gap, we introduce AdaExploreBench, a benchmark for proactive exploration and test-time adaptation in evolving environments. By instantiating environmental dynamics as hidden rules, AdaExploreBench requires agents to actively acquire evidence and infer the rules. Under implicit rule drift, the latent rule changes without announcement, requiring agents to detect from degraded performance that prior knowledge is stale and re-explore. Experiments on eight leading LLMs show that proactive and adaptive exploration remain challenging: GPT-6 Sol achieves only 61.9% calibrated accuracy, while providing sufficient evidence or removing rule drift improves average performance significantly by close to 10%. These results reveal a critical bottleneck in current LLM agents: they can often reason effectively from informative evidence once it is available, but…

    Code
Load more
PDF
PDF