LLM Agent Reliability

LLM: Large Language Model

Ask about this topic

Momentum

90 papers in the last four weeks, up 109% on the four weeks before. 0.9% of all new papers.

Jul 13Week of Sep 28
View on map

Latest papers 558

All topics
CardsList

  1. Can LLMs Fix It Without Code? Toward Automated Verification of No-Code Bug Fixes

    Oct 8, 2026Utku Boran Torun, Veli Karakaya, Eray TüzünAutomated EvaluationLLM Agent Reliability

    Bilkent University, Ankara, Turkey

  2. One Skill Too Many: How Co-Installed Skills Conflict in Coding Agents

    Oct 8, 2026Chaoliang Yan, Zihao Xu, Yuekang Li +4Coding AgentsLLM Agent Reliability

    University of New South Wales, Australia · Griffith University, Australia · Nanyang Technological University, Singapore +1

  3. Constitutional Gating and Deterministic Recovery for Multi-Agent LLM Negotiation: Ablations Against a Stateful Adversarial Gatekeeper

    Oct 8, 2026Masaaki Nakatsu, Reno WangLLM Agent ReliabilityMulti-Agent Negotiation

    AO, Inc. / OrbLabs AG · AO, Inc.

  4. Evaluating Local Language Model Agents for Reproducible Data Engineering: An Empirical Software Engineering Study of Mobility Workflows

    Oct 8, 2026Jorge García-Carrasco, Javier Sanchis, Alejandro Reina-Reina +2LLM Agent EvaluationLLM Agent Reliability

    Lucentia Research, Department of Software and Computing Systems, University of Alicante, Ctra. de Sant Vicent del Raspeig s/n, 03690 Sant Vicent del Raspeig, Alicante, Spain

  5. ReCast: Attribution-Oriented Step Representation Learning for LLM-Based Agent Systems

    Oct 8, 2026Weilin Jin, Mingyu Wang, Taiyu Zhu +7Agent Failure AnalysisLLM Agent Reliability

    Peking University, Beijing, China · Joy Future Academy, Beijing, China · Tsinghua University, Beijing, China

  6. Cross-Provider Review as a Runtime Contract for Coding Agents: A Controlled Pilot and Fault-Injection Study

    Oct 7, 2026Bowen Xu, Boyu ChenCoding AgentsRuntime Enforcement for AI Agents

    Department of Biology, Stanford University, Stanford, CA, USA · Institute of Health Informatics, University College London, London, UK

  7. RunningTab: Direct Workspace Interaction with Environment-Side Tabs

    Oct 7, 2026Jinheon Baek, Soyeong Jeong, Yumin Choi +2LLM Agent ReliabilityLLM Agent Harnesses

    KAIST

  8. Why Software Engineering Is Indispensable in the Age of Coding Agents

    Oct 7, 2026Alfonso FuggettaSoftware EngineeringAI-Assisted Software Development

    Politecnico di Milano, Dipartimento di Elettronica, Informazione e Bioingegneria, Milan, Italy

  9. Loud Failures, Quiet Failures: Fault Detection and Recovery in Tool-Using Language Model Agents

    Oct 7, 2026Obada KraishanTool-Using AgentsLLM Agent Reliability

    College of Media and Communication Texas Tech University Lubbock, TX, USA

  10. The Confidence Game: Strategic Miscalibration in Human-AI Delegation

    Oct 7, 2026Raghu Arghal, Saswati Sarkar, Shirin Saeedi BidokhtiLLM Agent ReliabilityConfidence Estimation in Language Models

    Department of Electrical and Systems Engineering University of Pennsylvania Philadelphia, PA, USA

  11. Humanize: Judgement Engineering for Agentic Coding

    Oct 6, 2026Sihao Liu, Ligeng Zhu, Zijian Zhang +6Multi-Agent CodingLLM Agent Orchestration

    NVIDIA · UCLA · Tsinghua University +2

  12. Confidence Reasoning Graphs: Structured Confidence Estimation for LLM Agents

    Oct 6, 2026Brendan King, Farima Fatahi Bayat, Jean-Flavien Bussotti +2Probability CalibrationConfidence Estimation in Language Models

    University of California, Santa Cruz · Megagon Labs

  13. One Step at a Time: Trading LLM Autonomy for Process Predictability

    Oct 6, 2026Hans Schabert, Christoph PetersAI Agent AuditingBusiness Process Automation

    Amazon Web Services · University of the Bundeswehr Munich

  14. Do I Need the Cloud? Uncertainty-Aware Step-Level Handoff for Small Language Model Agents

    Oct 6, 2026Abolfazl YounesiSmall Language ModelsLLM Agents

    Department of Computer Engineering Sharif University of Technology Tehran, Iran

  15. Quantization Effects on Tool-Failure Recovery Vary Across Prompts and Evaluation Designs

    Oct 6, 2026Yuhe HuTool-Augmented Language Model AgentsLLM Agent Evaluation

    Duke University

  16. From Evidence to Action: How Tool-Using Agents Fail

    Oct 6, 2026Hongzhan Lin, Shidong Cao, Ziyang Luo +3Agent Failure AnalysisEvidence-Grounded Reasoning

    National University of Singapore · Hong Kong Baptist University · Amazon Web Services +1

  17. Selective Critique for Cost-Aware LLM Agents in Long-Horizon Decision Making

    Oct 5, 2026Heewon Park, Somin Im, Minhae KwonLong-Horizon LLM AgentsLLM Agent Reliability

    Department of Electrical and Computer Engineering, Sungkyunkwan University, Republic of Korea. · Soongsil University, Republic of Korea.

  18. HERA: Harness-Environment Co-Evolution for Reliable Agentic Abstention

    Oct 5, 2026Han Luo, Bingbing Wen, Guang Yang +3Agent Harness OptimizationLLM Agent Reliability

    University of Washington · University of Leeds · Carnegie Mellon University +2

  19. When to Remember, When to Abstain: Category-Conditioned Retention for Reliable Agent Memory

    Oct 5, 2026Olukunle Owolabi, Pulkit Gupta, Fei WangSelective PredictionLLM Agent Memory

    Meta AI

  20. Judged Useless, Queried Anyway: Tool-Using Agents Rarely Turn Their Own Evidence Judgments into Stopping Decisions

    Oct 5, 2026Chubin Zhang, Zhenglin Wan, Xingrui Yu +4LLM Agent EvaluationTool-Using Agents

    Nanyang Technological University, Singapore · National University of Singapore, Singapore · CFAR, Agency for Science, Technology and Research, Singapore +3

  21. Where Did the Repair First Go Wrong? Localizing the Origins of Silent Failures in Agentic Vulnerability Repair

    Oct 5, 2026Wenji Bai, Muhammad Waseem, Zeeshan Rasheed +2Agent Failure AnalysisAutomated Program Repair

    Tampere University, Tampere, Finland

  22. Attention Tax, Handoff Tax: A Stylised Model of When Multi-Agent LLM Systems Help

    Oct 5, 2026Akshit Anchan, Nayonika SenMulti-Agent LLM SystemsMulti-Agent Reasoning

    University of Amsterdam Amsterdam, The Netherlands · Northeastern University Boston, MA, United States of America

  23. Nexus: An Execution Fabric for AI Agents Across Cloud, Edge, and Devices

    Oct 5, 2026Cary Chang, Jialin ZhouLLM Agent ServingRuntime Enforcement for AI Agents

    Nexilume Research

  24. Disentangling Task Difficulty from Run-Level Failure in Agent Failure Prediction

    Oct 4, 2026Mohsen EsfandyariDoulabi, Lawrence Arkoh, Biruk Tadesse +4Agent Failure AnalysisLLM Agent Evaluation

    North Carolina State University, Raleigh, North Carolina, USA

  25. DelegationBench: Measuring When AI Agents Should Ask Before Acting

    Oct 4, 2026Shiva PochampallyLLM Agent EvaluationAI Agent Benchmarks

  26. When Agent Context Goes Stale: Incoherence in Volatile Agent Context

    Oct 4, 2026Yingying Liu, Junzhou Fang, Chenxiong QianLLM Context ManagementLLM Agent Reliability

    The University of Hong Kong Hong Kong SAR, China

  27. StateWise: Diagnosing and Repairing Persistent Operational State Before Agent Actions

    Oct 4, 2026Yongyuan Peng, Zhou Feng, Tongying Wu +5Agent Failure AnalysisSoftware Engineering Agents

    Xi’an Jiaotong University, China · Zhejiang University, Hangzhou, China

  28. WebFovea: When the Model Is Right but the Click Is Wrong -- Reliable Round Trips for Vision-Based Web Agents on Live Websites

    Oct 2, 2026Jiangang HanWeb AgentsTool-Using Vision-Language Agents

    Independent Researcher

  29. Harnessing LLMs as Agents: What Does It Cost?

    Oct 1, 2026Zelin Zhao, Xinyu Guo, Jingyuan Zhang +2LLM Agent HarnessesMemory-Augmented Language Model Agents

    Georgia Institute of Technology · Etude AI

  30. Counting Moves, Weighing Voices: Bayesian Dialectical Argumentation for Calibrated Multi-LLM Councils under Persistent Adversaries

    Oct 1, 2026Ionel Eduard Stan, Paolo NapoletanoLanguage Model CalibrationComputational Argumentation

    Department of Informatics, Systems and Communication (DISCo), University of Milano–Bicocca, Milan, Italy