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. Evaluating Bounded Autonomy in Regulated Agentic AI: A Diagnostic Harness with Constitutional Rewards, Escalation Labels, and Runtime Governance

    Sep 28, 2026Dipankar SarkarLLM GuardrailsAI Agent Evaluation

    Skelf Research

  2. One Readout, Many Repairs: Diffusion-Guided Hierarchical Search for Tool-Agent Repair

    Sep 28, 2026Xiang Xia, Cheng Yan, Wuyang Zhang +4LLM Agent Reliability

    University of Science and Technology of China, Hefei, China

  3. SGG-ReflAct: Sub-Goal Guided ReflAct with Structured Planning for Reliable Long-Horizon Reasoning

    Sep 28, 2026Jaeho Jung, Sung Hoon JungLLM AgentsLong-Horizon LLM Agents

    Independent Researcher Seoul, Republic of Korea · Department of Applied Artificial Intelligence Hansung University Seoul, Republic of Korea

  4. Learn Now, Use Next, Trust Later: Prequential Test-Time Learning for LLM Agents

    Sep 28, 2026Tong Zhao, Reed Li, Yuyang Hu +5Continual Learning for LLM AgentsTest-Time Training

    Renmin University of China · Tencent

  5. The Marathon of Scientific Reasoning: Robustness of Scientific Agents to Perturbations in Multi-Turn Interactions

    Sep 28, 2026Xiaoting Lyu, Xinbo Ma, Yufei Han +5AI Agent BenchmarksScientific Reasoning in Language Models

    Xi’an Jiaotong University, China · Inria, France · Agency for Science, Technology and Research (A*STAR), Singapore +1

  6. Commitment Hierarchies under Intent Revision: A Belief-Revision Account of Salvage in Tool-Use Agents

    Sep 28, 2026Spandan Ghose ChowdhuryBelief RevisionLLM Planning

    Georgia Institute of Technology, Atlanta, GA, USA

  7. ControlScope: Workflow Revision and Reliability in LLM Agents

    Sep 28, 2026Jingjie Ning, Xueqi Li, Yibo Kong +1LLM Agent EvaluationLLM Agent Reliability

    Carnegie Mellon University · Tsinghua University

  8. Same Winners, Different Success Rates: Evaluating How LLM Agents Recover from Failures

    Sep 28, 2026Dong Xu, Zhangfan Yang, Jiantao Wu +5LLM Agent EvaluationAI Agent Benchmarks

    School of Artificial Intelligence, Shenzhen University · EasternDawn · School of Computer Science, University of Nottingham Ningbo

  9. StateGuard: Analytical-State Management with Validity-Aware Intervention for Long-Horizon Data Agents

    Sep 28, 2026Wenle Liao, Zhao Wang, Jingchao Zhang +3LLM Agent VerificationGraph-Based Agent Memory

    Gaoling School of Artificial Intelligence Renmin University of China

  10. Maat: Independent Deterministic Contract-Based Governance for Multi-Agent LLM Workflows

    Sep 27, 2026Uliana ElinaMulti-Agent LLM SystemsLLM Agent Verification

    SynWe Group s.r.o.

  11. Designing Reliable LLM-as-a-Judge Measurement Systems for Multi-Turn Business Agents

    Sep 27, 2026Kaiwen Luo, Ming GaoLLM-as-a-JudgeLLM Agent Evaluation

    Meta

  12. Prospective Interpretation Risk: Principled Communication Control Between LLMs

    Sep 27, 2026Wanrong Yang, Rehan Deen, Julian Ma +7Multi-Agent LLM SystemsPragmatic Reasoning in Language Models

    University of Liverpool · Independent Researcher · University College London +1

  13. Identical Runs, Different Results: Benchmarking AI Coding Agents on Open-Weight Models

    Sep 27, 2026Eduardo Ariño de la Rubia, Szilard PafkaAI Coding AgentsLLM Agent Evaluation

    Central European University · Epoch

  14. When Do Agents Help? Embedding, LLM and Agentic Alignment of Classical Texts and Their Translations

    Sep 27, 2026Máté MetzgerLLM AlignmentLLM Agent Evaluation

    Independent Researcher

  15. HESP: Separating What to Probe from When to Stop in Local LLM Alert-Triage Agents

    Sep 27, 2026Zhuowen Liu, Zhixuan WangLLMs for CybersecurityLLM Agent Reliability

    Cybersecurity Lab Japan Advanced Institute of Science and Technology (JAIST) Nomi, Ishikawa, Japan · College of Fine Arts Liaoning Normal University Dalian, Liaoning, China

  16. Evaluating System One Models for Agent Security Decisions: Reliability, Calibration, and Selective Automation

    Sep 27, 2026Yixuan LiuProbability CalibrationSelective Prediction

    TraceStone and Nanyang Technological University, Singapore

  17. TraceDance: An Automated System for Building Agent Behavior Benchmarks from Real-World Agent Deployment Traces

    Sep 27, 2026Dehai Min, Daoan Zhang, Yiming Zeng +13Benchmark ConstructionLLM Agent Evaluation

    ByteDance Inc., USA · University of Illinois at Chicago

  18. LLM Parkinsonism: Executive-Control Failure, Token-Inefficient Persistence, and an Uncertainty-Aware Global Executive Control Architecture for Autonomous Language-Model Agents

    Sep 25, 2026Dongsheng Xiao, Zeyuan Wang, Xuzhe Xia +2Overthinking in Language ModelsLLM Agents

    Queensland Brain Institute, The University of Queensland, Brisbane, Queensland, Australia · School of Cyber Security, Northwestern Polytechnical University, Xi'an, Shaanxi, China · Department of Electrical and Computer Engineering, The University of British Columbia, Vancouver, British Columbia, Canada +2

  19. Coding Agents Aren't Enough! Evaluating an Enterprise Security Brain for Agentic Cloud Investigations

    Sep 24, 2026Leon Goldberg, Gal Engelberg, Eden Yavin +3AI Coding AgentsAI Agent Evaluation

    Sola Security, Tel Aviv, Israel

  20. The Last Human Gate: Forward Deployed Engineering for Governance Automation

    Sep 24, 2026Jeremy CanaleAI Agent GovernanceAI Governance

  21. Policy as Code: A Coroutine-Bridge Harness for Fast-Reasoning Reliability on CAR-bench

    Sep 24, 2026Ivan MatveevAgent Harness OptimizationAI Agent Benchmarks

    Proxima Ultra

  22. IndicBankBench: Evaluating Safety and Reliability of Language Model Assistants in Indian Retail Banking

    Sep 24, 2026Suvradip Paul, Chandra Bhushan, Harsh Sharma +4LLM Safety BenchmarksFinancial Services

    National Payments Corporation of India Mumbai, India

  23. Where Does Exactly-Once Live? Model, Harness, and Tool-Contract Effects on Duplicate Side Effects in LLM Agents

    Sep 24, 2026Jiapeng LiTool-Using AgentsRuntime Enforcement for AI Agents

    Microsoft

  24. MeshHeal: Two-Timescale Self-Healing for Gray Failures in Decentralized LLM Agent Networks

    Sep 24, 2026Keru Chen, Sen Lin, Yingbin Liang +2Multi-Agent LLM SystemsMulti-Agent Systems

    School of ECEE Arizona State University · Computer Science Department University of Houston · Department of ECE The Ohio State University +1

  25. Driving Epidemic Models with AI Agents: the Epydemix Agent Framework

    Sep 23, 2026Nicolò Gozzi, Ciro Cattuto, Alessandro VespignaniAI Agents for Scientific DiscoveryLLM Agent Harnesses

    ISI Foundation, Turin, Italy · Network Science Institute, Northeastern University, Boston, MA, USA

  26. Learning from Failures: Heterogeneous Graph Memory for Small Language Model Tool-Using Agents

    Sep 23, 2026Jiaxing Li, Lei Song, Rui Dong +1Graph-Based Agent MemoryLong-Horizon LLM Agents

    School of Computer Science and Engineering, Southeast University, Nanjing, China

  27. Where Cyber Agents Struggle: Bottleneck Analysis of Multi-Stage LLM Agents

    Sep 23, 2026Saeedeh Lohrasbi, Mohammad Mamun, Ahmed Yehia +2Agent Failure AnalysisLLM Agent Evaluation

    Cybersecurity, DTRC, National Research Council, Ottawa, Canada · University of Windsor, Windsor, Ontario, Canada

  28. Don't Read the Log: Execution Traces Contaminate Verifiers in Video-Generation Agents

    Sep 23, 2026Jian XuLLM-as-a-JudgeAI Agent Auditing

    RIKEN

  29. REFLEX with Jev for Efficient Selective Control in LLM Agents

    Sep 22, 2026Tiantong Wu, Wei Yang Bryan LimLLM Inference EfficiencyLLM Agent Evaluation

    Nanyang Technological University Singapore

  30. FIRE: Failure-Informed Runtime Engineering for Reliable Language-Model Agents

    Sep 22, 2026Nikita Agarwal, Nivedit JainRuntime Enforcement for AI AgentsLLM Agent Reliability

    Failproof AI