LLM Agent Reliability

LLM: Large Language Model

Overview

LLM agent reliability studies whether agents can complete tasks correctly, follow instructions and safety constraints, use evidence faithfully, and behave consistently across repeated or extended interactions. Common approaches combine structured harnesses and deterministic tool interfaces with state tracking, evidence checks, runtime monitoring, calibrated abstention, and recovery from failures; training methods also teach agents to verify actions or learn from execution feedback. Evaluations increasingly use interactive benchmarks, noisy or changing tools, repeated trials, and trajectory-level measures alongside final task success. A central tension is that added reasoning, delegation, memory, or orchestration can improve some tasks but also introduce new failure paths, so reliability depends on the model, harness, tools, and evaluation setting together.

Latest papers

CardsList

909 papers94 papers in the last four weeks, down 51% on the four weeks before. 0.7% of all new papers.

  1. MiroFlow: Towards High-Performance and Robust Open-Source Agent Framework for General Deep Research Tasks

    Feb 26, 2026Shiqian Su, Sen Xing, Xuan Dong +13Autonomous Research AgentsLLM Agent Orchestration

  2. Agents of Chaos

    Feb 23, 2026Natalie Shapira, Chris Wendler, Avery Yen +35AI Agent SecurityLLM Agent Security

  3. MAS-FIRE: Fault Injection and Reliability Evaluation for LLM-Based Multi-Agent Systems

    Feb 23, 2026Jin Jia, Zhiling Deng, Zhuangbin Chen +2Multi-Agent LLM SystemsLLM Agent Reliability

  4. OptiRepair: Closed-Loop Diagnosis and Repair of Supply Chain Optimization Models with LLM Agents

    Feb 23, 2026Ruicheng Ao, David Simchi-Levi, Xinshang WangSupply Chain OptimizationLarge Language Model-Guided Optimization

  5. Gecko: A Simulation Environment with Stateful Feedback for Refining Agent Tool Calls

    Feb 22, 2026Zeyu Zhang, Guohao Li, Zhenchang Xing +3LLM Tool UseLLM Agent Reliability

  6. Agentic Problem Frames: A Systematic Approach to Engineering Reliable Domain Agents

    Feb 22, 2026Chanjin ParkAI Agent ReliabilityLLM Agent Reliability

  7. Web Agents Should Use Typed Actions Instead of Click-Based Browsing

    Feb 19, 2026Linxi Jiang, Rui Xi, Zhijie Liu +3Web AgentsLLM Agent Reliability

  8. Wink: Recovering from Misbehaviors in Coding Agents

    Feb 19, 2026Rahul Nanda, Chandra Maddila, Smriti Jha +3LLM Agent ReliabilityAgent Reliability

  9. ReIn: Conversational Error Recovery with Reasoning Inception

    Feb 19, 2026Takyoung Kim, Jinseok Nam, Chandrayee Basu +5LLM AgentsConversational Agents

  10. AgentFixer: From Failure Detection to Fix Recommendations in LLM Agentic Systems

    Feb 18, 2026Hadar Mulian, Sergey Zeltyn, Ido Levy +3LLM Agent ReliabilityLLM Agents

  11. MMA: Multimodal Memory Agent

    Feb 18, 2026Yihao Lu, Wanru Cheng, Zeyu Zhang +1Multimodal AgentsMemory-Augmented Agents

  12. Atomix: Timely, Transactional Tool Use for Reliable Agentic Workflows

    Feb 16, 2026Bardia Mohammadi, Nearchos Potamitis, Lars Klein +2Tool UseTool-Using Agents

  13. Thinking Is Not Telling: Information Disclosure in User-Service LLM Agents

    Feb 8, 2026Jiatong Li, Changdae Oh, Hyeong Kyu Choi +2Human-AI InteractionLLM Agent Reliability

  14. Do Multi-Agents Dream of Electric Screens? Achieving 100% on AndroidWorld Through Task Decomposition

    Feb 8, 2026Pierre-Louis Favreau, Jean-Pierre Lo, Clement Guiguet +5Mobile GUI AgentsMulti-Agent LLM Systems

  15. When Is Enough Not Enough? Illusory Completion in Search Agents

    Feb 7, 2026Dayoon Ko, Jihyuk Kim, Sohyeon Kim +5AI Agent ReliabilityLLM Answer Verification

  16. ARTIS: Agentic Risk-Aware Test-Time Scaling via Iterative Simulation

    Feb 2, 2026Xingshan Zeng, Lingzhi Wang, Weiwen Liu +5LLM Agent ReliabilityTest-Time Scaling

  17. Beyond Single-shot Writing: Deep Research Agents are Unreliable at Multi-turn Report Revision

    Jan 19, 2026Bingsen Chen, Boyan Li, Ping Nie +3Deep Research AgentsLLM Agent Reliability

  18. LLMs Can't Play Hangman: On the Necessity of a Private Working Memory for Language Agents

    Jan 11, 2026Davide Baldelli, Ali Parviz, Amal Zouaq +1LLM Agent MemoryLLM Agent Reliability

  19. AOI: Context-Aware Multi-Agent Operations via Dynamic Scheduling and Hierarchical Memory Compression

    Dec 15, 2025Zishan Bai, Hanxuan Chen, Jiayi Gu +9Multi-Agent OrchestrationLLM Context Management

  20. Echo-CoPilot: A Multiple-Perspective Agentic Framework for Reliable Echocardiography Interpretation

    Dec 6, 2025Moein Heidari, Ali Mehrabian, Mohammad Amin Roohi +5Medical Visual Question AnsweringEchocardiography

  21. CXRAgent: Director-Orchestrated Multi-Stage Reasoning for Chest X-Ray Interpretation

    Oct 24, 2025Jinhui Lou, Yan Yang, Zhou Yu +4Chest X-Ray ClassificationLLM Agent Orchestration

  22. Proof-of-Use: Mitigating Tool-Call Hacking in Deep Research Agents

    Oct 13, 2025Shengjie Ma, Chenlong Deng, Jiaxin Mao +5LLM Agent ReliabilityRL for Tool Use

  23. Domain-Specific Agents for Cherenkov Telescope Array Control Software and Gamma-Ray Data Analysis

    Oct 1, 2025Dmitriy Kostunin, Elisa Jones, Vladimir Sotnikov +3High-Energy PhysicsLLM Agents

  24. Reasoning or Rambling? Exploring the Effect of Thinking on Agent Persuasion

    Sep 25, 2025Haodong Zhao, Jidong Li, Zhaomin Wu +4LLM AgentsPersuasion in Language Models