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. Designing Agent-Ready Websites for AI Web Agents: A Framework for Machine Readability, Actionability, and Decision Reliability

    Jul 13, 2026Said Elnaffar, Farzad RashidiE-CommerceWeb Agents

    Independent Researcher London, ON, Canada · UFR Informatique Université Paris Cité F-75013 Paris, France

  2. Agentic systems for breast cancer treatment recommendations

    Jul 13, 2026Vinicius Anjos de Almeida, Nícolas Henrique Borges, Leonardo Vicenzi +5Multi-Agent LLM SystemsClinical Decision Support

    Faculdade de Medicina, Universidade de S˜ao Paulo, Av. Dr. Arnaldo, 455, 01246-903, S˜ao Paulo, S˜ao Paulo, Brazil · Spesia · Laboratory of Artificial Intelligence Applied to Bioinformatics, SEPT, Universidade Federal do Paran´a (UFPR), Rua Alcides Vieira Arcoverde, 1225, 81520-260, Curitiba, Paran´a, Brazil +2

  3. Inference Economics of Enterprise Coding Agents: A Case Study of Cloud vs. On-Premise LLMs

    Jul 13, 2026Sheng-Wei Peng, Yi-Hsun Lin, Yi-Pei LeeLLM ServingSoftware Engineering Agents

    Pegatron Corporation Taipei, Taiwan

  4. AgentCheck: A Reproduce-Intervene-Mitigate Workbench for LLM Agents over MCP

    Jul 13, 2026Aritra Mazumder, Nusrat jahan LiaAI Agent ReliabilityLLM Agent Evaluation

    University of Utah · University of Dhaka

  5. Distributed Agent System: Fault-Tolerant Collaboration Among Embodied Agents

    Jul 12, 2026Kai Yu, Lu Chen, Hanqi LiMulti-Agent CollaborationMulti-Agent Systems

    X-LANCE Lab, School of Computer Science, Shanghai Jiao Tong University, Shanghai, 200240, China · Jiangsu Key Lab of Language Computing, Suzhou, 215028, China

  6. Confining Nondeterminism: AI-Driven Research Systems as DBMSs for Reliable, Non-Wasteful, Transparent, and Collaborative Research [Vision]

    Jul 11, 2026Kyoungmin Kim, Anastasia AilamakiAI Agent ReliabilityAutonomous Research Agents

    EPFL Lausanne, Switzerland

  7. Compaction as Epistemic Failure: How Agentic LLM Tools Fabricate Confirmed Results from Killed Processes

    Jul 11, 2026Hiroki TambaAI Agent ReliabilityLLM Agent Memory

    Independent Researcher

  8. AgentAbstain: Do LLM Agents Know When Not to Act?

    Jul 11, 2026Xun Liu, Yi Evie Zhang, Vira Kasprova +5AI Agent ReliabilityLLM Agent Evaluation

    University of Illinois Urbana-Champaign

  9. Failure as a Process: An Anatomy of CLI Coding Agent Trajectories

    Jul 10, 2026Xiangxin Zhao, Han Li, Shuaiting Li +4Agent Failure AnalysisCoding Agents

    University College London, London, United Kingdom · Nanjing University, Nanjing, China

  10. Scoped Verification for Reliable Long-Horizon Agentic Context Evolution under Distribution Shift

    Jul 10, 2026Dan C. Hsu, Luke LuAI Agent ReliabilityLong-Horizon Agent Evaluation

    RedMind Research, San Francisco, CA, USA · National Taiwan University, Taipei, Taiwan

  11. Eluna: An Agentic LLM System for Automating Warehouse Operations with Reasoning and Task Execution

    Jul 9, 2026Ning Liu, Kalle Kujanpää, Zhaoxuan Zhu +11Multi-Agent LLM SystemsLLM Agent Orchestration

    Amazon.com, Inc. Fulfillment Technologies and Robotics

  12. From Prompts to Contracts: Harness Engineering for Auditable Enterprise LLM Agents

    Jul 9, 2026Joongho Ahn, Moonsoo KimLLM AuditingLLM Guardrails

    AI Leadership Research Center

  13. Tool-Making and Self-Evolving LLM Agents in Low-Latency Systems

    Jul 9, 2026Kalle Kujanpää, Ning Liu, Shahnawaz Alam +4LLM Inference EfficiencyLLM Agent Self-Improvement

    Amazon, Fulfillment Technologies & Robotics

  14. Agent Delivery Engineering Predictive Reliability Framework

    Jul 8, 2026Dexing LiuAI Agent ReliabilityMulti-Agent LLM Systems

    Shanghai Qijing Digital Technology Co., Ltd · Shanghai Qijing Digital Technology Co., Ltd.

  15. Reason Less, Verify More: Deterministic Gates Recover a Silent Policy-Violation Failure Mode in Tool-Using LLM Agents

    Jul 8, 2026Vikas Reddy, Sumanth Reddy Challaram, Abhishek BasuAgent Failure AnalysisAI Agent Reliability

    Independent Researcher · Indian Institute of Technology Kharagpur Kharagpur, India · Massachusetts Institute of Technology Cambridge, USA

  16. Progressive Crystallization: Turning Agent Exploration into Deterministic, Lower-Cost Workflows in Production

    Jul 8, 2026Arun MalikCost-Aware InferenceAgentic Workflows

    Microsoft Azure Networking

  17. Reliable and Developer-Aligned Evaluation of Agents for Software Engineering

    Jul 7, 2026Razvan Mihai PopescuSoftware Engineering AgentsLLM Agent Evaluation

    Delft University of Technology Delft, The Netherlands

  18. Doomed from the Start: Early Abort of LLM Agent Episodes via a Recall-Controlled Probe Cascade

    Jul 7, 2026Kai Ruan, Zihe Huang, Ziqi Zhou +4LLM Inference EfficiencyEarly Stopping

    Gaoling School of Artificial Intelligence, Renmin University of China · Institute of Computing Technology, Chinese Academy of Sciences · Duke University +3

  19. Beyond the Leaderboard: A Synthesis of Tool-Use, Planning, and Reasoning Failures in Large Language Model Agents

    Jul 7, 2026Wael Albayaydh, Rui Zhao, Ivan FlechaisAI Agent ReliabilityLLM Agent Evaluation

    University of Oxford

  20. PatchOptic for Shared-State LLM Workflows with Projected Views and Verified Structured Updates

    Jul 6, 2026Zhaoyu Bai, Jiaqi CaiAgentic WorkflowsLLM Context Management

    Department of Particle Physics and Astrophysics, Weizmann Institute of Science, Rehovot, Israel, 7610001 · Department of Physics, Massachusetts Institute of Technology, Cambridge, MA, USA, 02139

  21. AgentGym2: Benchmarking Large Language Model Agents in De-Idealized Real-World Environments

    Jul 6, 2026Zhiheng Xi, Dingwen Yang, Jiaqi Liu +22LLM Agent EvaluationAI Agent Benchmarks

    Fudan University · Zhejiang University · Shanghaijiaotong University +1

  22. When Agents Lie: Premeditation, Persistence, and Exploitation in Repeated Games

    Jul 6, 2026Jerick Shi, Terry Jingcheng Zhang, Bernhard Schölkopf +2Multi-Agent LLM SystemsGame-Playing Agents

    Carnegie Mellon University, Pittsburgh, USA · Jinesis AI Lab, Vector Institute and University of Toronto, Toronto, Canada · EuroSafeAI +1

  23. ToolFailBench: Diagnosing Tool-Use Failures in LLM Agents

    Jul 6, 2026Harsh SoniAI Agent ReliabilityTool-Use Evaluation

    UC Berkeley

  24. Learning to Control LLM Agent Harnesses with Offline Reinforcement Learning

    Jul 5, 2026Haiwen Yi, Xinyuan SongOffline RLLLM Agent Harnesses

    University of Toronto · Emory University

  25. The "I Don't Know" Filter: Enhancing Agentic Reliability in Function Calling

    Jul 4, 2026Stefan Broecker, Mason del Rosario, Boris Selitser +1AI Agent ReliabilityLLM Agent Evaluation

    University of California, Davis, Department of Computer Science · Okareo, Inc. · University of California, Davis, Department of Mathematics

  26. The Remarkable Effectiveness of Providing AI Agents with Natural Language Tools: A Replication Study Validating NLT Performance Across 14 Models

    Jul 4, 2026Alexander Somma, Isabelle Plante, Fred PremjiAI Agent ReliabilityLLM Agent Evaluation

    Sage.is AI-UI

  27. Swarm-Driven Multi-Agent Reasoning for Smart City Security

    Jul 3, 2026Saeid Jamshidi, Kawser Wazed Nafi, Carol Fung +1Multi-Agent LLM SystemsCybersecurity

    Concordia Institute for Information Systems Engineering (CIISE), Concordia University, Montr´eal, QC, Canada · SWAT Laboratory, Polytechnique Montréal, Montréal, QC, Canada

  28. Evaluating Generative Agents with Actions Grounded in Socially Distributed Task Environments using Incognita

    Jul 3, 2026Dan C. Hsu, Luke LuLLM Agent EvaluationAI Agent Benchmarks

    RedMind Research, San Francisco, CA, USA · National Taiwan University, Taipei, Taiwan

  29. Reasoning effort, not tool access, buys first-try reliability in agentic code generation: an observational study

    Jul 2, 2026Achint MehtaAI Agent ReliabilityTest-Time Scaling

    TrendAI

  30. Grounded autonomous research: a fault-tolerant LLM pipeline from corpus to manuscript in frontier computational physics

    Jul 2, 2026Haonan HuangScientific DiscoveryAutonomous Research Agents

    Department of Physics, Princeton University, Princeton, NJ, USA.