LLM Agents

LLM: Large Language Model

Follow this topic Ask about this topic

Momentum

57 papers in the last four weeks, up 58% on the four weeks before. 0.6% of all new papers.

Jul 13Week of Sep 28

Latest papers 433

May 27, 2026cs.AI

LACUNA: Safe Agents as Recursive Program Holes

LLM agents increasingly act by writing code, yet a split persists between the runtime that drives the agent and the code the model writes. The runtime owns the loop, context, and control flow, and the model has little say over any of them. Letting model-written code shape the runtime itself would make agents more expressive, but it would also sharpen safety problems. A model can be diverted by a prompt injection, call the wrong tool, or fail partway and leave an inconsistent state, and each such failure reaches further when the code shapes the runtime than when it expresses a single action. We present LACUNA, a programming model for agents that closes this split while preserving safety. Each agent action is a typed call

\texttt{agent[T](task)}

that the LLM fills with code when execution reaches it, and the code is type-checked against the surrounding program before it runs. Because each action is accepted or rejected as a whole, a rejected one leaves the environment untouched, and its compiler diagnostics drive a retry. The same check also bounds which tools and data an action may use and how they flow. Our primitive expresses ReAct loops, sub-agents, skills, parallel decomposition, and multi-model planning as ordinary control flow. We evaluate LACUNA on a collection of test cases, BrowseComp-Plus, and

τ^2

-bench. On BrowseComp-Plus,

8.6\%

of generations are rejected before execution, with 0.7 retries per query on average, and the agent reaches

27.1\%

accuracy. On

τ^2

-bench, LACUNA solves

76.0\%

of

392

tasks across four domains with a capable model, on par with the baseline agent.

Yaoyu Zhao, Yichen Xu, Oliver Bračevac +3

EPFL, Lausanne, Switzerland

AI Agent Reliability LLM Agents LLM Agent Safety

May 27, 2026eess.AS

Audio-Mind: An Auditable Agentic Framework for Audio Understanding

Audio agents extend large audio-language models (LALMs) by decomposing audio questions into tool calls, intermediate evidence, and iterative reasoning steps. However, as LALMs become stronger, the key challenge shifts from enabling tool use to determining when agentic evidence acquisition genuinely benefits audio understanding. We propose Audio-Mind, an auditable and pluggable framework for conditional evidence acquisition in audio understanding. Audio-Mind dynamically combines a strong frontend with planner-guided tool use, preserving frontend judgment when initial evidence is sufficient while acquiring bounded external evidence for questions with unresolved evidence gaps. Experiments on MMAR and MSU-Bench show that Audio-Mind outperforms prior audio-agent baselines, reaching 80.4% accuracy on MMAR and 82.8% accuracy on MSU-Bench. A matched-backbone comparison highlights why this design matters: under strong audio frontends, agentic decomposition can become an orchestration bottleneck when the workflow does not preserve the frontend's holistic audio-grounded judgment. Beyond accuracy, Audio-Mind produces higher-quality, auditable reasoning traces that expose uncertainty, tool evidence, and answer rationales, offering a potential basis for more reliable audio-QA annotation and error analysis.

Yucheng Wang, Jing Peng, Hanqi Li +6

School of Intelligence Science and Technology, Nanjing University, China · X-LANCE Lab, School of Computer Science, Shanghai Jiao Tong University, China · School of Automation Science and Engineering, Xi’an Jiaotong University, China +1

Audio QA Audio Reasoning Audio Understanding Audio-Language Models LLM Agents

May 27, 2026cs.CL

Beyond One Path: Evaluating and Enhancing Divergent Thinking in Interactive LLM Agents

Divergent thinking is a core dimension of creativity, yet existing evaluations of Large Language Models (LLMs) treat them as single-turn text generations, failing to capture how an agent reasons through iterative interaction. To address this, we introduce MUTATE, an interactive benchmark designed to evaluate agentic divergent thinking at two levels: path-level, where an agent discovers multiple alternative paths to the same goal, and action-level, where individual actions require non-typical, mechanism-shifting object uses. Unlike success-only evaluations, MUTATE scores both completed paths and off-path attempts, capturing divergent reasoning that conventional success rates discard. Our experiments with frontier LLMs reveal a structural blind spot in existing frameworks: when exposed to immediate convergence pressure, they tend to fall into immediate action fixation, failing to improve action-level divergence. To overcome this, we propose ReDNA, which separates unconstrained divergent candidate generation from convergent constraint selection. ReDNA significantly outperforms prior methods across both divergence levels and generalizes effectively to an external creativity environment. We also confirm its success stems from a qualitative enhancement of resilient divergent reasoning rather than simple environmental exploration.

Jihyeong Park, Ingeol Baek, Jeonghyun Park +1

Chung-Ang University, Seoul, Korea

LLM Agent Evaluation AI Agent Benchmarks Computational Creativity LLM Agents

May 27, 2026cs.AI

When Does Memory Help Multi-Trajectory Inference for Tool-Use LLM Agents?

Multi-trajectory inference for tool-use LLM agents - generating multiple reasoning attempts and selecting among them - benefits from transferring knowledge across attempts so that later ones avoid the pitfalls of earlier ones. Existing cross-trajectory memory methods (trajectory-level reflection, atomic fact extraction, raw observation injection) are each evaluated under a single inference strategy on a single task, making it unclear whether reported gains reflect properties of the memory abstraction or of the inference method. We propose a unified framework that decomposes memory along two axes -- the scope of transfer (within an expansion vs. across trajectories) and the abstraction of the transferred content -- and evaluate four methods under three inference strategies (best-of-N, beam search, MCTS) on four tool-use benchmarks spanning SQL, knowledge-graph, and CLI environments, in a verifier-free setting that matches the deployment regime of practical agents. The experiment matrix identifies the inference method as a confound: the same memory method produces statistically distinct results under different inference strategies on the same examples. Reflection reaches significance only under MCTS (not under best-of-N); within-expansion injection (conditioning each candidate on prior siblings' outcomes) helps only diversity-starved beam search; and atomic fact extraction is accuracy-neutral but shortens trajectories by 19-26% on tasks with reusable environmental structure.

Xinzhe Li, Yaguang Tao

RMIT University

Inference-Time Search LLM Agent Memory LLM Agents

May 27, 2026cs.PL

Skill-as-Pseudocode: Refactoring Skill Libraries to Pseudocode for LLM Agents

Markdown skill libraries for LLM agents ship as free-form prose, forcing the agent to re-derive both the input schema and the concrete invocation syntax on every retrieval. This produces a "confused

\to

re-retrieve

\to

still confused" loop: the agent issues a partially-correct action, receives uninformative feedback, and re-retrieves the same prose. We propose Skill-as-Pseudocode (SaP), an automatic conversion of markdown skill libraries into typed pseudocode with deterministic quality control. From each cluster of similar procedural passages, SaP extracts a typed contract and filters it through a four-check deterministic verifier (coverage, binding, replacement, risk). Promoted contracts are inlined into a rewritten skill skeleton alongside restored action templates, giving the agent two complementary signals: a typed signature for what a skill does and a concrete template for how to invoke it. On the ALFWorld unseen split (134 games, gpt-4o-mini, three seeds), SaP wins 82/402 paired games versus 47/402 for the Graph-of-Skills (GoS) baseline (pooled McNemar

p = 8.2 \times 10^{-5}

), at

-22.8 \pm 6.4

% input tokens and

-14.5 \pm 4.1

% LLM calls per game. A bundle-component ablation attributes the gain to the pairing of typed contracts with concrete action templates: the contract alone falls below the prose baseline.

Xinze Li, Yuhang Zang, Yixin Cao +1

Nanyang Technological University · Shanghai AI Laboratory · Fudan University

Tool-Augmented Language Model Agents LLM Agent Skill Retrieval LLM Agents Agent Skill Learning

May 27, 2026cs.CL

Retrieval, Reward, and Training Protocols: What Matters in Training Search Agents?

Search agents powered by large language models can autonomously decompose queries, retrieve information, and synthesize answers through multi-step reasoning. However, the rapid growth of training methods has outpaced controlled comparison: existing works differ in retrieval corpora, reward designs, and training protocols, making it unclear what actually drives improvements. We present a controlled empirical study that isolates three under-explored dimensions of search agent training. First, we identify a critical data-coverage issue in the widely used Wikipedia 2018 corpus and show that correcting it alone yields larger gains than the differences between training algorithms. Second, we systematically compare outcome-based and process-based reward methods across three base models, finding that the simplest outcome-based approach achieves competitive or superior performance in most settings, and that process-level credit assignment can over-correct agent behavior. Third, we analyze training data diversity, off-policy data utilization, and search budget scaling, distilling practical guidelines for training effective search agents. Our code is available at https://github.com/YiboZhao624/SearchAgentReview.

Yibo Zhao, Zichen Ding, Jiayi Wu +2

School of Data Science and Engineering, East China Normal University · Shanghai AI Laboratory

LLM Agents Information Retrieval LLM Agent Training Reward Design for RL RL for LLM Agents

May 27, 2026cs.AI

A Query Engine for the Agents

The fastest-growing data in production today is unstructured text: agent traces, chat logs, reasoning chains, model outputs. People want to analyze it, and the questions worth asking ("show me where the agent got confused") cannot be answered by SQL alone, since text is not queryable without a model in the query path. The natural place this analysis is happening is the new class of AI applications (Claude Code, Cursor, Claude Desktop, in-browser agents) that run client-side and host both a human user and an LLM agent in the same process. These applications increasingly want to work with data, but the lakehouse read path has been hard to use from a JS runtime: Spark, Trino, and managed warehouses do not fit there. To build this new kind of AI data application, three properties of the engine become first-order: a JS-native distribution that drops into the runtime the application already runs in, a bundle small enough to ship inside a cold tab or per-turn agent sandbox, and a way to interleave analytic operators with model-based interpretation of text. We present Hyperparam, three open-source JavaScript libraries (Hyparquet, Squirreling, Icebird) totaling under 70 KB, that read Parquet and Apache Iceberg directly from object storage and meet the third property with per-cell, async-native SQL execution, so expensive cells fire only when downstream operators demand them. Squirreling runs LLM-shaped async UDFs over 300x faster than DuckDB-WASM on filter-bounded queries (and 192x on sort-bounded queries) and completes a ten-task agent analyst suite at two-thirds lower cost. We argue that data engineering as a discipline needs to update for the AI-native client applications now in production and the agents that work alongside their users.

Kenny Daniel

Hyperparam · Seattle, USA

May 27, 2026cs.AI

Diagnosing Live Within-Policy Instruction Conflicts in LLM Agents with Witnessed Resolution Profiles

LLM agents are governed by long-lived natural-language prompt policies, but individually reasonable standing rules can interact in uninspected ways. We study live intra-policy rule-conflict diagnosis: finding rule pairs inside a single prompt policy that can co-govern a realistic state, and measuring how models resolve that pressure in responses or tool actions. We introduce WIRE, a Witnessed Intra-policy Rule Evaluation pipeline. WIRE extracts source-grounded rules, encodes them as PyRule clauses, uses satisfiability checks to retain same-surface hard-collision candidates, realizes those candidates as concrete co-governance witnesses, and judges model outputs against the original source-rule text. Across six public prompt policies, WIRE extracts 276 source rules and 560 atomic clauses, classifies 30,944 within-policy clause-pair comparisons, retains 170 encoded hard-collision candidate source-rule pairs, and realizes them as 1,402 concrete witnesses. In policy-only evaluation, these witnesses yield 13,335 post- generation trials where both source rules govern and both compliance labels are judgeable. Only 35.4% fall in joint compliance; 64.6% violate at least one governed source rule. These profiles are conditional diagnostics for WIRE-selected candidates, not deployment-frequency or causal excess failure estimates, but they reveal distinct policy, model, and tool-action resolution patterns.

Lu Yan, Xuan Chen, Xiangyu Zhang

Purdue University

LLM Agent Evaluation LLM Agents LLM Agent Reliability

May 26, 2026cs.AI

Maat: The Agentic Legal Research Assistant for Competition Protection

Competition law experts conducting legal research must review extensive volumes of cases, decisions, and judicial reports to identify precedents and assess key elements in competition and merger cases. Although general research assistants such as Claude and ChatGPT and legal assistants such as SaulLM-7B and LegalGPT are increasingly used to assist legal research, they remain inadequate for competition law analysis: they lack specialized domain expertise, provide insufficient official citations, or hallucinate competition law cases. We propose Maat, a ReAct agent that orchestrates tools corresponding to different tasks of the research process. Designed iteratively with competition law experts, Maat grounds cases and findings in official sources using RAG for reliability, provides rich in-line citations, falls back to web search when database coverage is insufficient, and prompts the user for clarification when queries are ambiguous. Maat significantly outperforms all baseline assistants on case-specific tasks and performs within range of the top baseline on theoretical question tasks. The dataset used is available on GitHub.

Basant Mounir, Farida Madkour, Amira Abdelaziz +1

Cairo, Egypt

Legal IR Agentic Search LLM Agents Legal QA

May 26, 2026cs.AI

Learning to Act under Noise: Enhancing Agent Robustness via Noisy Environments

Recent advances in large language models (LLMs) have facilitated the widespread deployment of LLMs as interactive agents capable of reasoning, planning, and tool use. Despite strong performance on existing benchmarks, such agents often exhibit notable degradation when deployed in real-world settings, where environments are inherently stochastic and imperfect. We argue that this discrepancy arises from a fundamental mismatch between idealized training settings and real-world interaction dynamics, where current paradigms rely on carefully curated task instructions and stable, well-controlled environments. To address this gap, we propose NoisyAgent, an agentic training framework that explicitly incorporates environmental imperfections into the agent learning process. We identify two major sources of interaction noise in real-world scenarios: user noise, which captures ambiguity and variability in user interaction, and tool noise, which reflects failures and anomalies in tool execution. We introduce such perturbations into the training pipeline by modifying user interaction patterns and simulating tool execution results within the training environment. To stabilize training while encouraging agents to handle increasingly challenging imperfections, noise is applied to only a subset of rollouts and progressively increased in difficulty as the model adapts to the current noise level. Extensive experiments demonstrate that our approach consistently improves agent robustness under noisy and dynamic environments. Our analysis reveals that training under noise conditions also yields performance gains on idealized benchmarks, suggesting that controlled exposure to environmental noise promotes more generalizable reasoning and decision-making behaviors. Our findings highlight the importance of modeling interaction imperfections for bridging the gap between agent training and real-world deployment.

Yuxin Chen, Xiaodong Cai, Junfeng Fang +9

National University of Singapore · Meituan · Tsinghua University +2

LLM Agents LLM Agent Training Robust RL LLM Agent Reliability

May 26, 2026cs.LO

Automating Formal Verification with Agent-Guided Tree Search

Formal verification offers a path to provably correct software, but writing verified code remains expensive enough that the technique is rarely used in production. Recent large language models can accelerate this work, and recent benchmarks measure their ability to translate specifications into code and machine-checked proofs of correctness. This thesis evaluates the state of such LLM-driven verified-code generation ("vericoding") in Lean and develops search-based methods for improving verification performance. We first reproduce a subset of the vericoding-benchmark Lean leaderboard on a current cross-vendor model pool, finding that non-reasoning performance remains roughly steady on US closed-source models while open-weight models have slightly improved. We update the iterative methodology of vericoding-benchmark with an agentic loop equipped with mathlib search, finding that model performance greatly improves and scales with agent budget. GPT-5.4 nearly saturates the benchmark at 95.0% on 423 specs with

K=50

LLM calls. We then design two agent-directed tree-search formulations: a state-based orchestrator that branches on partial-proof states, and a context-based orchestrator that branches on full subagent contexts. Compared against the agent baseline, the context-based design solves a wider range of intermediate-difficulty specs at lower token cost, while the agent baseline retains an advantage on the hardest specs, where uninterrupted iteration matters most. We conclude that search structure has selective advantages over a strong agent baseline, and that more challenging benchmarks drawn from modern code are important to measure and drive further progress in automated formal verification. Code available upon request by contacting the author at [email protected].

Leo Yao

Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology

Code Generation LLM-Based Program Synthesis Formal Verification LLM Agents Code Generation Evaluation

May 26, 2026cs.AI

TADDLE: A Tool-Augmented Agent for Detecting Deficient LLM-Generated Peer Reviews

LLM-generated peer reviews are increasingly common at major venues, yet their deficiencies are hard to detect because they are uniformly fluent and well-structured. Existing work either classifies authorship without judging quality, or scores quality with features designed for human-written reviews; no prior system detects deficiencies in LLM-generated reviews at the level of individual defect types. To bridge the gap, we introduce TADDLE, a Tool-Augmented Agent for Detecting Deficient LLM-Generated Peer Reviews, together with the first expert-annotated benchmark for this task. Our benchmark comprises 1,800 reviews on 50 ICLR 2025 papers, multi-label-annotated by 18 domain experts against a taxonomy of six defect categories (plus a non-deficient label). TADDLE decomposes detection into four specialized analysis tools -- Verify, Correct, Complete, and Transform -- orchestrated by an agent; an integrator synthesizes their outputs into binary and multi-label classifications via two-stage semi-supervised learning. Extensive experiments show that TADDLE performs strongly on both binary detection and the multi-label classification task. We release the benchmark and code at https://github.com/AquariusAQ/TADDLE.

Hanqi Duan, Xiang Li

East China Normal University

Tool-Augmented Language Model Agents LLM Agents Automated Peer Review

May 26, 2026cs.AI

AGORA: Adapter-Grounded Observation-Action Retention for Inference-Free Prompt Compression in LLM Agents

The token-level extractive compressors widely used for general LM context are structurally inappropriate for LLM agents: across 17 (env, backbone, method) cells spanning two independent token-level method families, every cell collapses to mean reward <= 0.05 despite 1.3-13.3x realized compression. We name and characterize this failure mode as action-grammar destruction -- the tokens carrying action semantics (identifiers, brackets, action verbs) are exactly those self-information ranks lowest, so a general-purpose compressor reliably removes them and the environment rejects the residual. The diagnosis points to step-granularity compression. We introduce AGORA, an inference-free step-level compressor combining a structural prompt parser, an always-keep floor for format- and recency-critical content, and a 125M-parameter relevance scorer trained on counterfactual next-action-change labels (~2ms/step, zero per-step LLM toll). Across the compared inference-free and LLM-based methods, AGORA is the only one retaining >= 75% uncompressed performance in 8 of 9 cells (with the lone exception at 73%); a four-way component ablation isolates the structural floor as the dominant quality lever and the learned scorer as the source of 1.0-11.5x adaptive end-to-end compression from a single fixed keep ratio.

Haoran Zhang, Zhaohua Sun

AI Agent Technologies (Hong Kong) Limited · Department of Mechanical Engineering, The University of Hong Kong

LLM Compression LLM Agents Prompt Compression

May 25, 2026cs.CL

CRPO: Character-centric Group Relative Policy Optimization for Role-aware Reasoning in Role-playing Agents

Recent advancements in Reinforcement Learning (RL), particularly Group Relative Policy Optimization (GRPO), have significantly enhanced the reasoning capabilities of Large Language Models. However, applying these problem-centric optimization methods to role-playing agents often leads to a loss of character fidelity and style collapse, as they prioritize context-specific utility over persona alignment. To address this, we propose Character-Centric Group Relative Policy Optimization (CRPO), a framework designed to realign RL objectives with the role-playing task. CRPO improves character distinctiveness through three mechanisms: decoupling task logic from stylistic rewards to resolve gradient conflicts, dynamically adapting optimization constraints based on character complexity, and utilizing generic responses as negative baselines to prevent the model from reverting to a common distribution. Extensive experiments demonstrate that CRPO outperforms existing methods in consistency, emotion and others.

Yihong Tang, Kehai Chen, Liang Yue +2

Institute of Computing and Intelligence, Harbin Institute of Technology, Shenzhen, China · Shenzhen Loop Area Institute (SLAI), Shenzhen, China · The Chinese University of Hong Kong, Shenzhen, China

RL for Language Models Persona Consistency Personality Modeling in Language Models Group Relative Policy Optimization LLM Agents

May 25, 2026cs.CL

Retrieval as Reasoning: Self-Evolving Agent-Native Retrieval via LLM-Wiki

LLM agents require retrieval to behave less like one-shot context fetching and more like reasoning: searching, reading, traversing, and deciding when evidence is sufficient. Yet current Retrieval-Augmented Generation (RAG) systems organize external knowledge as flat chunks retrieved by embedding similarity, exposing a retrieval-as-lookup interface ill-suited to iterative reasoning agents. We propose LLM-Wiki, an agent-native retrieval system that operationalizes the Retrieval-as-Reasoning paradigm by treating external knowledge as a compilable, composable, and self-evolving structure rather than a static retrieval index. LLM-Wiki compiles documents into structured Wiki pages with bidirectional links, exposes search, read, and link-following operations through standard tool-calling interfaces, and introduces an Error Book for persistent structural and semantic self-correction. LLM-Wiki achieves state-of-the-art results on HotpotQA, MuSiQue, and 2WikiMultiHopQA, outperforming HippoRAG 2, LightRAG, and GraphRAG by 2.0-8.1 F1 points. On AuthTrace, LLM-Wiki achieves the best overall accuracy, with especially strong gains on multi-document structured queries, confirming that compilation-based retrieval generalizes beyond chain-style multi-hop reasoning.

Haoliang Ming, Feifei Li, Xiaoqing Wu +1

WeChat, Tencent Inc., Beijing, China

Multi-Hop QA Retrieval-Augmented Generation Tool-Augmented Language Model Agents Agentic Retrieval LLM Agents

May 25, 2026cs.AI

CODESKILL: Learning Self-Evolving Skills for Coding Agents

Coding agents produce rich trajectories while solving software-engineering tasks. To enable agent self-evolution, these trajectories can be distilled into reusable procedural skills that compactly encode experience to guide future behavior. However, existing skill construction and maintenance methods often rely on fixed prompts and heuristic update rules, leaving it unclear how knowledge should be selected, abstracted, and maintained to best serve downstream agents. We propose CODESKILL, an LLM-based framework that reformulates skill extraction and skill-bank maintenance as a learnable management policy. CODESKILL extracts multi-granularity procedural skills from coding-agent trajectories, evolves skills with new experience, and maintains a compact skill bank for future task solving. We train CODESKILL with reinforcement learning, using a hybrid reward that combines dense rubric-based skill-quality feedback with sparse verifiable execution feedback from the frozen downstream agent. Experiments on EnvBench, SWE-Bench Verified, and Terminal-Bench 2 show that CODESKILL improves average pass rate by 9.69 over the no-skill baseline and by 4.01 over the strongest prompt-based or memory baseline, while maintaining the skill bank at a stable size during iterative construction.

Yanzhou Li, Yiran Zhang, Xiaoyu Zhang +2

Nanyang Technological University · 2Zhejiang University

Coding Agents LLM Agent Skill Learning LLM Agents RL for LLM Agents Self-Evolving Agents

May 24, 2026cs.AI

Test-Time Deep Thinking to Explore Implicit Rules

With the continuous advancement of Large Language Models (LLMs), intelligent agents are becoming increasingly vital. However, these agents often fail in environments governed by implicit rules--hidden constraints that cannot be observed directly and must be inferred through interaction. This causes agents to fall into repetitive trial-and-error loops, ultimately leading to task failure. To address this challenge, we propose Test-Time Exploration (TTExplore), a framework where a thinker component analyzes interaction history to infer these implicit rules and guide an actor. Effective exploration in this setting critically depends on the reasoning ability of the thinker. However, evaluating deep reasoning trajectories is inherently unstable and difficult, which poses a major obstacle to effective training. To overcome this issue, we introduce a novel and stable reinforcement learning pipeline. The core idea is to use accurate task-level scores as indirect rewards to bypass the difficulty of evaluating intermediate reasoning, and to retain only a single thinking node per trajectory to alleviate reward sparsity. Using this pipeline, we train a specialized 7B model, Exp-Thinker. Experiments on five text-based embodied tasks show that TTExplore equipped with Exp-Thinker improves baseline agent performance by an average of

14

-

19

points, demonstrating the effectiveness of explicitly reasoning about implicit rules.

Wentong Chen, Xin Cong, Zhong Zhang +8

Renmin University of China Beijing, China · Department of Statistics and Data Science, Tsinghua University Beijing, China · School of Computer Science and Engineering, UESTC Chengdu, China +4

RL for Language Model Reasoning LLM Agents Embodied AI RL for LLM Agents

May 24, 2026cs.AI

PANDO: Efficient Multimodal AI Agents via Online Skill Distillation

Recent advances in multimodal web agents often rely on increased inference-time computation, including rollout search, verifier passes, offline skill discovery, and specialist model stacks. This raises a central question: can a web agent become more efficient as it accumulates experience, rather than more expensive? We first analyze trajectories from VisualWebArena and identify three recurring sources of inefficiency: repeat-action loops, hidden discovery costs, and low prompt-cache reuse. We then introduce PANDO, a single-rollout online skill-distillation framework that maintains a structured Skill Library and combines progress reflection, confidence-based skill demotion, hierarchical routing, visual compression, and cache-aware prompting. On the full set of 910 VisualWebArena tasks, PANDO achieves a 58.3% success rate, outperforming SGV (54.0%) and our WALT reproduction (45.2%), while using 58% fewer tokens than SGV and 61% fewer tokens than WALT, without any pre-evaluation discovery budget. A 300-task ablation further shows that rules and routines provide most of the success gains, while routing, compression, and cache-aware prompting convert the larger skill library into lower marginal token cost. Finally, we introduce three trajectory-level efficiency metrics -- Action Repetition Rate, Step Overhead Ratio, and Prompt Cache Utilization -- to make efficiency visible beyond terminal success.

Yubo Li, Yidi Miao, Yuntian Shen +1

LLM Agent Workflow Optimization LLM Agent Skill Learning LLM Agents Knowledge Distillation Web Agents

May 23, 2026cs.IR

How Many Tools Should an LLM Agent See? A Chance-Corrected Answer

Before an LLM agent can use a tool, a retrieval system must decide which candidate tools to show to the agent. How long should that shortlist be? Show too many tools and the model struggles to choose. Show too few and the correct tool may not appear. Most systems apply a fixed shortlist size to every query, but no standard metric exists to evaluate whether that size was appropriate. We treat the number of tools shown to an LLM agent as the object of evaluation and we apply Bits-over-Random (BoR), a chance-corrected metric that asks whether success at a given depth is better than what random selection would achieve at that same depth. We evaluate BoR across three tool-selection benchmarks, multiple scorers, and registries ranging from 20 to 3,251 tools. We then turn the same principle into a reinforcement learning (RL) reward for choosing tool shortlist depth per query. The RL agent is deliberately simple, serving as a probe of the metric rather than a proposed system. As the shortlist grows, random chance of including the correct tool rises, so the reward naturally decreases, reducing the need for an engineered depth penalty. On BFCL (370 tools), the learned policy nearly matches the coverage of showing 50 tools (

90.3\%

vs

90.8\%

) while presenting only 7 on average. On ToolBench (3,251 tools), a fixed shortlist of 5 tools achieves higher aggregate coverage (

64.7\%

vs

61.9\%

) but finds nothing on hard queries (correct tool ranked 6th-20th). The BoR agent finds

16.7\%

on those same queries by searching deeper. Downstream validation with Claude Sonnet 4.6 indicates that shorter adaptive lists also improve the LLM's ability to select the right tool:

93.1\%

versus

87.1\%

when always shown 5 tools, widening to

76.8\%

vs

60.9\%

on medium-difficulty queries where the correct tool is present but not ranked first.

Vyzantinos Repantis, Ameya Gawde, Harshvardhan Singh +1

Meta Platforms

Tool-Use Evaluation Tool-Augmented Language Model Agents Tool-Using Agents LLM Agents Tool Selection

May 22, 2026cs.LG

Agent-ToM: Learning to Monitor Autonomous LLM Agents via Theory-of-Mind Reasoning

Monitoring autonomous large language model (LLM) agents for covert malicious behavior is challenging due to delayed, context-dependent, and long-horizon attack patterns. Agents may pursue hidden objectives while maintaining superficially benign behavior, making detection difficult even with full trajectory access. Prior monitoring approaches improve scaffolding or ensemble aggregation, but treat each trajectory independently and do not learn from prior monitoring experience. Moreover, standard reasoning methods explain observed behavior without explicitly reasoning about agent beliefs, intentions, and goal alignment required to distinguish benign task execution from covert deviation. We propose \textbf{Agent-ToM}, a learning-to-monitor framework grounded in Theory-of-Mind (ToM) reasoning for security analysis of autonomous agents. Agent-ToM performs structured full-trajectory analysis by inferring beliefs, intent hypotheses with calibrated confidence, expected actions, and deviations from task-consistent behavioral baselines. At inference time, it employs a \textit{Reason-Verify-Refine} pipeline to construct and validate monitoring decisions. At training time, Agent-ToM distills critique signals into a persistent \textit{semantic guardrail memory}, enabling reusable belief- and intent-conditioned constraints across episodes. We evaluate Agent-ToM on adversarial agent monitoring benchmarks (SHADE-Arena and CUA-SHADE-Arena). Agent-ToM achieves strong precision-recall balance and outperforms state-of-the-art monitoring baselines, including ensemble methods, while using a coherent two-call reasoning pipeline. These results demonstrate that learning at the monitoring layer, combined with structured ToM reasoning and verification, provides an effective and deployable foundation for securing autonomous LLM agents.

Nesreen K. Ahmed, Nima Nafisi

Cisco Outshift

LLM Agent Security AI Agent Monitoring LLM Agents

May 21, 2026cs.SE

More Skills, Worse Agents? Skill Shadowing Degrades Performance When Expanding Skill Libraries

Skill libraries allow LLM agents to load task-specific instructions on demand, letting non-expert users solve domain-specific tasks through natural language without knowing which skills exist or how they work. However, performance degrades as libraries grow -- by up to 21% when scaling from a small set of helpful skills to a 202-skill library. In this work, we formulate this performance degradation as the pass rate drop between loading a library of known-helpful skills and the full library. Moreover, we propose to decompose the pass rate drop by conditioning on the skill(s) invocation -- which skills the agent selects during a trajectory -- into two effects: \emph{skill shadowing}, where the agent selects wrong skills more often as the library expands, and \emph{context overhead}, where the enlarged context degrades execution even when selection is correct. We derive upper bounds on both effects to characterize their magnitudes of impacts to the pass rate drop. Our empirical estimates of the effects and their upper bounds both show that the \emph{skill shadowing} effect grows with library size and significantly contributes to the performance degradation, whereas the \emph{context overhead} effect remains small and indistinguishable from zero. This observed asymmetry establishes that the skill selection failure, not the enlarged context, is the primary bottleneck when expanding the skill libraries.

Hongwen Song, Song Wei

Databricks Inc.

LLM Agent Evaluation LLM Agent Skill Learning LLM Agents LLM Agent Reliability

May 21, 2026cs.OS

DeltaBox: Scaling Stateful AI Agents with Millisecond-Level Sandbox Checkpoint/Rollback

LLM-powered AI agents require high-frequency state exploration (e.g., test-time tree search and reinforcement learning), relying on rapid checkpoint and rollback (C/R) of the complete sandbox state, including files and process state (e.g., memory, contexts, etc.). Existing mechanisms duplicate the entire state, causing hundreds of milliseconds to seconds of latency per C/R, which severely bottlenecks deep search and large-scale fan-outs. This paper observes that subsequent checkpoints in AI agents are highly similar. Therefore, instead of full duplication, a sandbox should only duplicate the changes between consecutive checkpoints (Key Insight). However, it is non-trivial to realize the idea, mainly due to the missing OS supports. This paper proposes a new OS-level abstraction, DeltaState, to enable the change-based transactional C/R for AI agents with two co-designed OS mechanisms. First, DeltaFS enables change-based filesystem C/R by organizing the file states into layers and dynamically freezing the writable layer and inserting a new one during checkpoint, reducing file updates to copy-on-write, and making rollback a simple layer switch. Second, DeltaCR enables change-based process state C/R using incremental dumps, and accelerates rollback by bypassing traditional pipelines to directly fork() from a frozen template process. We then present DeltaBox, a novel agent sandbox achieving millisecond level C/R through the two new mechanisms. Evaluations on SWE-bench and RL micro-benchmarks show DeltaBox completes checkpoint and rollback in millisecond-level latency (14ms and 5ms, respectively), empowering agents to explore substantially more nodes under fixed time budgets.

Yunpeng Dong, Jingkai He, Shiqi Liu +7

Institute of Parallel and Distributed Systems, Shanghai Jiao Tong University · Engineering Research Center for Domain-specific Operating Systems, Ministry of Education, China · Huawei Technologies Co., Ltd.

May 21, 2026cs.SE

Contractual Skills: A GovernSpec Design Framework for Enterprise AI Agents

Skills have become a practical packaging mechanism for agent instructions, workflows, scripts, and reference materials. In enterprise settings, however, a skill often needs to express more than task guidance: goals, input boundaries, permissions, human approval points, evidence requirements, output contracts, quality criteria, verification steps, and handoff rules. This paper proposes contractual skills, a GovernSpec-inspired design framework for organizing SKILL.md files as readable task contracts while preserving lightweight skill discovery and progressive loading. The framework clarifies the boundary between contractual skills, GovernSpec YAML contracts, Model Context Protocol (MCP) surfaces, tool adapters, runtime guardrails, tracing, and evaluation systems. We evaluate the framework with three offline empirical studies. The first text-generation experiment covers three enterprise skills, fifteen synthetic tasks, four instruction conditions, and eight generation models, producing 960 outputs and 1680 cross-judge score records. The second study is a public-skill A/B expansion: eight public skills are compared with contractual rewrites across forty-eight synthetic tasks, six generation models, two repeats, 1152 outputs, and two complete judge files. In this setting, contractual skills raise mean quality from 4.692 to 4.914 and reduce critical-error rate from 0.083 to 0.013. The third study is an offline tool-calling challenge with eight models and 192 simulated tool-call records. The results suggest that contractual skills are best understood as a governance layer that makes task intent, boundaries, and acceptance criteria explicit, not as a standalone safety mechanism.

Ting Liu

SymbolicLight Research Foshan, Guangdong, China

LLM Agents AI Agent Governance

May 21, 2026cs.AI

Adapting the Interface, Not the Model: Runtime Harness Adaptation for Deterministic LLM Agents

LLM agents are shaped not only by their language models, but also by the runtime harness that mediates observation, tool use, action execution, feedback interpretation, and trajectory control. While existing agent adaptation methods mainly update model parameters, many failures in deterministic, rule-governed domains stem from mismatches at the model--environment interface. We propose Life-Harness, a lifecycle-aware runtime harness that improves frozen LLM agents without changing model weights or evaluation environments. Life-Harness evolves from training trajectories by converting recurring interaction failures into reusable interventions across environment contracts, procedural skills, action realization, and trajectory regulation, and remains fixed for evaluation on unseen tasks. On seven deterministic environments from

τ

-bench,

τ^2

-bench, and AgentBench, Life-Harness improves 116 out of 126 model--environment settings across 18 model backbones, with an average relative improvement of 88.5%. Harnesses evolved only from Qwen3-4B-Instruct trajectories transfer to 17 other models, showing that Life-Harness captures reusable environment-side structure rather than model-specific behavior. These results position runtime interface adaptation as a complementary alternative to model-centric agent training. Code is available at https://github.com/Tianshi-Xu/Life-Harness.

Tianshi Xu, Huifeng Wen, Meng Li

Peking University

LLM Agents LLM Agent Harnesses Agentic AI

May 21, 2026cs.AI

Ratchet: A Minimal Hygiene Recipe for Self-Evolving LLM Agents

Self-evolving skill libraries, pioneered by Voyager, let frozen LLM agents accumulate reusable knowledge without weight updates, yet recent evaluation shows that LLM-authored skills deliver

+0.0

pp over no-skill baselines while human-curated ones deliver

+16.2

pp: the bottleneck is not skill authoring but lifecycle management. We introduce \textbf{Ratchet}, a single-agent loop in which a frozen LLM writes, retrieves, curates, and retires its own natural-language skills. Ratchet integrates four candidate hygiene mechanisms: outcome-driven retirement, a bounded active-cap, meta-skill authoring guidance, and pattern canonicalisation. On MBPP+ hard-100 with Claude Opus 4.7, Ratchet lifts held-out pass@1 from a

0.258 \pm 0.047

baseline to a late-window rolling mean of

0.584

(peak

0.658 \pm 0.042

) across 100 rounds and 3 seeds, a

+0.328 \pm 0.018

rolling-mean gain where the no-skill control drifts at

+0.002 \pm 0.005

; the same recipe transfers to an agentic solver on SWE-bench Verified (

+0.22

peak lift over 20 rounds). Eight ablations (A1--A8) reveal that the minimal working recipe is smaller than our design suggests: retirement and the meta-skill authoring prior are load-bearing, while explicit deduplication (canonicalisation, cover-guard) is subsumed by the meta-skill itself. A non-divergence proposition shows that bounded cap and retirement threshold together prevent expected performance from drifting below the no-skills floor.

Xing Zhang, Yanwei Cui, Guanghui Wang +4

AWS Generative AI Innovation Center · HSBC Holdings Plc., HSBC Technology Center, China

Continual Learning for LLM Agents LLM Agent Self-Improvement LLM Agent Skill Learning LLM Agents Self-Evolving Agents

May 21, 2026cs.CL

Diagnosis Is Not Prescription: Linguistic Co-Adaptation Explains Patching Hazards in LLM Pipelines

When a multi-module LLM agent fails, the module most responsible for the failure is not necessarily the best place to intervene. We demonstrate this Diagnostic Paradox empirically: causal analysis consistently identifies the routing module -- which selects which tool to call next -- as the primary bottleneck across three independent agent families. Yet injecting prompt-level correction examples into this module consistently degrades performance, sometimes severely. Patching an upstream query-rewriting module instead reliably improves outcomes. The effect holds with statistical significance on two agent families and directional consistency on a third; alternative repair strategies at the routing module (instruction rewriting, model upgrade) are neutral, confirming that the harm is specific to correction-injection patching. We explain this asymmetry through the Linguistic Contract hypothesis: each downstream module implicitly adapts to its upstream's characteristic error distribution, so correcting the bottleneck breaks this implicit alignment in a way that upstream corrections do not. We operationalize this via a per-agent co-adaptation measure, derived from diagnosis alone, and show it is consistently associated with patching harm across agent families: higher co-adaptation co-occurs with harm, lower with safety. This trend holds across all three agent families, providing preliminary support for the hypothesis beyond a single-agent observation.

Yoon Jeonghun, Kim Dongchan

KAIST (Korea Advanced Institute of Science and Technology), Republic of Korea · NAVER Corp., Seongnam, Republic of Korea · NAVER Corp., Bellevue, WA, USA

LLM Agents Causal Interventions in Language Models Tool-Using Language Agents LLM Agent Reliability

May 20, 2026cs.LG

APEX: Autonomous Policy Exploration for Self-Evolving LLM Agents

LLM agents have shown strong performance across a wide range of complex tasks, including interactive environments that require long-horizon decision making. But these agents cannot learn on the fly at test time. Self-evolving agents address this by accumulating memory and reflection across episodes rather than requiring model-weight updates. However, these agents often suffer from exploration collapse: as memory grows, behavior concentrates around familiar high-reward routines, reducing the chance of discovering better alternatives. To address this problem, we propose Autonomous Policy EXploration (APEX), which builds and maintains an explicit strategy space through a strategy map-a directed acyclic graph of milestones with prerequisite dependency edges. In APEX, Fork Discovery expands the map with evidence-grounded unexplored directions, while Policy Selection balances exploration and exploitation during planning. Evaluated on nine Jericho text-adventure games and WebArena, a realistic web interaction benchmark, APEX outperforms all baselines. Extensive ablations validate each component's contribution and demonstrate robustness across diverse settings, demonstrating APEX's effectiveness for sustained exploration in self-evolving agents.

Yibo Li, Jiashuo Yang, Zhi Zheng +5

1National University of Singapore · 2Beijing University of Posts and Telecommunications

LLM Agents Long-Horizon LLM Agents Self-Evolving Agents

May 20, 2026cs.AI

VBFDD-Agent for Electric Vehicle Battery Fault Detection and Diagnosis: Descriptive Text Modeling of Battery Digital Signals

With the rapid proliferation of electric vehicles, the safety and reliability of lithium-ion batteries have become critical concerns. Effective anomaly detection is essential for ensuring safe battery operation. However, as battery systems and operating scenarios become increasingly complex, battery fault diagnosis and maintenance require stronger cross-domain adaptability and human-AI collaboration. Traditional fault detection and diagnosis methods are usually designed for specific scenarios and predefined workflows, making them less effective in complex real-world applications. To address the scarcity of open-source battery fault report corpora and the lack of unified maintenance knowledge representation, this study proposes a descriptive text modeling approach for battery signal reports. Monitoring signals, statistical features, anomaly records, and state assessment results are transformed into structured and readable natural language descriptions, forming a language corpus for battery health diagnosis and maintenance. Based on this corpus, we propose VBFDD-Agent, a vehicle battery fault detection and diagnosis agent for automotive-grade battery systems. VBFDD-Agent integrates descriptive battery-state texts, historical case retrieval, local maintenance manuals, and large language model reasoning to generate structured diagnostic results and maintenance recommendations. Experiments show that the proposed framework can accurately perform anomaly monitoring based on descriptive textual representations and provide flexible, efficient, and actionable maintenance suggestions. Expert evaluation further confirms the practical value of the generated recommendations. Overall, VBFDD-Agent extends traditional battery diagnosis from label prediction to interpretable and maintenance-oriented decision support.

Joey Chan, Zhen Chen, Ershun Pan

Department of Industrial Engineering and Management, School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai 200240, China

Predictive Maintenance LLM Agents Anomaly Detection

May 19, 2026cs.AI

A Methodology for Selecting and Composing Runtime Architecture Patterns for Production LLM Agents

Production LLM agents combine stochastic model outputs with deterministic software systems, yet the boundary between the two is rarely treated as a first-class architectural object. This paper names that boundary the stochastic-deterministic boundary (SDB): a four-part contract among a proposer, verifier, commit step, and reject signal that specifies how an LLM output becomes a system action. We argue that the SDB is the load-bearing primitive of production agent runtimes. Around this primitive, we organize agent runtime design into three concerns: Coordination, State, and Control. We present a catalog of six runtime patterns that compose the SDB differently across conversational, autonomous, and long-horizon agents: hierarchical delegation, scatter-gather plus saga, event-driven sequencing, shared state machine, supervisor plus gate, and human in the loop. For each pattern, we trace its lineage to distributed-systems concepts and identify what changes when the worker is stochastic. The paper contributes a five-step methodology for selecting runtime patterns, a diagnostic procedure that maps production failures to pattern weaknesses, and a failure mode called replay divergence, in which LLM-based consumers of a deterministic event log produce different downstream outputs under model-version or prompt changes. A stylized reliability decomposition separates per-call model variance from architectural momentum, motivating the claim that as model variance decreases, pattern choice and SDB strength become increasingly important levers for long-run reliability. We apply the methodology to five workloads and provide one runnable reference implementation for a 90-day contract-renewal agent.

Vasundra Srinivasan

AI Architect, Independent Researcher · Stanford School of Engineering

LLM Agent Orchestration LLM Agents Long-Horizon LLM Agents LLM Agent Reliability

May 19, 2026cs.AI

Formal Skill: Programmable Runtime Skills for Efficient and Accurate LLM Agents

Large Language Model (LLM) agents increasingly act inside real workspaces, where tools and skills determine whether model reasoning becomes reliable action. Existing skills remain largely informal: Markdown skills and instruction packs encode procedures as long natural-language documents, while function calling, Model Context Protocol (MCP) servers, and framework tools structure individual actions but usually leave workflow state, policy enforcement, and completion discipline outside the skill itself. We introduce Formal Skill, a runtime-native abstraction that represents reusable capability with JSON metadata and action schemas, reliable Python executors, hook-governed control logic, Formal Skill routing, and skill-local runtime state. By moving reusable procedure from repeated prompt text into executable state machines and hook policies, Formal Skill gives agents a token-efficient and enforceable control surface. We implement the abstraction in FairyClaw, an open-source event-driven runtime for executable, observable, and composable Formal Skills. On Harness-Bench, FairyClaw obtains highly competitive average scores while using substantially fewer tokens, with especially strong results on tasks that expose the role of Formal Skill.

Xi Zhang, Meijun Gao, Yuntian Zhao +6

Tool-Using Agents LLM Agents