LLM Agent Verification

LLM: Large Language Model

Ask about this topic

Overview

LLM agent verification studies how to establish that an agent did the right thing, followed required procedures, and has evidence for its claims—not merely that it produced a plausible answer. Common approaches include execution-grounded tests and replay, formal methods such as contracts and SMT checks, runtime policy monitors, and learned or independent verifiers that inspect trajectories and tool evidence. These methods are evaluated in settings such as coding and computer-use benchmarks, multi-step tool workflows, formal mathematics and hardware design, and high-stakes domains. A central tension is that checks can improve reliability but only for the requirements and evidence they cover; self-verification and LLM judges can miss errors, while stronger verification adds cost and still does not prove claims beyond its scope.

Latest papers

CardsList

148 papers50 papers in the last four weeks, up 163% on the four weeks before. 0.3% of all new papers.

  1. Think Before You Act: Decision Gate for LLM Agents

    Oct 28, 2026Iftach Shoham, Yuval David, Offer Akrabi +5LLM Agent VerificationRuntime Enforcement for AI Agents

    IBM SIL

  2. Beyond QASecClaw: Agent Scaling, Verifier Feedback, and Evidence Reliability in Software Assurance

    Oct 27, 2026S M Abdulla Al Mamun, Akif Islam, Mohd. Ruhul AmeenLLM Agent VerificationLLM Reliability

    Department of Computer Science, The University of Manchester, United Kingdom · Department of Computer Science and Engineering, University of Rajshahi, Bangladesh · Department of Computer Science and Engineering, Varendra University, Bangladesh

  3. Proof-of-Agentness: Towards Verifying Agents on the Web

    Oct 26, 2026Zuyao Xu, Xiang LiLLM Agent VerificationWeb Agents

    Nankai University, Tianjin, China

  4. From Questions to Queries to Insights: A Schema-Grounded Agentic Workflow for Natural-Language Crash Data Analysis

    Oct 26, 2026Jingwen Zhu, Keshu Wu, Steven T. Parker +2Data Analysis AgentsExecution-Guided Text-to-SQL

    Department of Civil and Environmental Engineering, University of Wisconsin–Madison, Madison, WI, United States

  5. AgentProofBench: Benchmarking Reusable Verifiers for Web Agents

    Oct 25, 2026Jingjie Ning, Xueqi Li, Yi Lu +1LLM Agent VerificationWeb Agent Benchmarks

  6. Rethinking Verification in Agent Harnesses

    Oct 25, 2026Zhengxin Zhang, Erkang Zhu, Yin Lin +3LLM Agent VerificationLLM Agent Harnesses

    Cornell University · Alibaba Group

  7. PASS Is a Claim, Not an Observation: Mechanical Re-verification of 10 Self-Asserted Fix Claims in a Live Multi-Agent Audit Layer

    Oct 24, 2026Lei Zhenbing, Lei ChangAI Agent AuditingLLM Agent Verification

  8. ProbeID: Verifying MCP Tool Identity for LLM Agents under Registry Drift

    Oct 24, 2026Guanxing Chen, Sining Zhang, Haohuai He +3LLM Agent VerificationAI Agent Security

    City University of Hong Kong (Dongguan), Dongguan, China · The Hong Kong Polytechnic University, Hong Kong SAR, China · Zhengzhou University, Zhengzhou, China +1

  9. Who Verifies the Tools? How Warped Formatters Mislead Agents and Their Verifiers

    Oct 23, 2026William JeffriesLLM Agent ReliabilityLLM Agent Verification

  10. When Is a Memory Safe Enough to Act On? Action-Conditioned Verification for Long-Lived Agents

    Oct 22, 2026Yiqi Wang, Yifei Wang, Jiaqi Zhang +4LLM Agent VerificationLLM Agent Safety

    University of Southern Queensland, Australia · Southern University of Science and Technology, Shenzhen, China · Jiangsu University, China +2

  11. Beyond Accuracy: Disentangling Decomposition from Typed-State Quality Assurance in Multi-Agent LLM Pipelines

    Oct 22, 2026Maria Gabriela Alves Zuppardo, Vinicius Cardoso GarciaMulti-Agent LLM SystemsLLM Agent Evaluation

    Centro de Informática, Universidade Federal de Pernambuco (UFPE), Recife, PE, Brazil

  12. Post-Audit Mirage: Identifiability Limits of Offline Agent Verification

    Oct 22, 2026Aman Behera, Payal PayalLLM Agent VerificationAI Agent Monitoring

    IIT Roorkee

  13. SWE-VERIFIER: Selective Verification for Cost-Efficient Coding Agents

    Oct 21, 2026Kaijian Zou, Vaibhav Chennareddy, Yunxiang Zhang +5Coding AgentsLLM Agent Verification

    University of Michigan · The University of Texas at Austin

  14. Recoverability and Verifier Strength: Two Measured Preconditions for Unattended Agent Self-Improvement

    Oct 20, 2026De Wang, Peng QiLLM Agent Self-ImprovementSelf-Improving Agents

    Uniphore

  15. On the LLM Verification for Argument Graph Generation

    Oct 19, 2026Jakub Bąba, Jarosław A. ChudziakLLM Agent VerificationComputational Argumentation

    Institute of Computer Science Warsaw University of Technology Warsaw, Poland

  16. VerifierBench: Benchmarking the Generation of Executable Verifiers for LLM Agents

    Oct 19, 2026Jianing Yin, Ziyi Chen, Hao Wang +4LLM Agent VerificationAI Agent Benchmarks

    University of Pennsylvania · University of Illinois at Urbana-Champaign · University of California, Berkeley +2

  17. AllPath: Layered Verification for a Deployed, Self-Revising LLM Trading Agent under Human-Gated and Autonomous Regimes

    Oct 19, 2026Tian Zhang, Meng LiLLM Agent VerificationLLM Agents

    Independent Researcher USA

  18. Agentic Orchestration of EDC Data Space Retrieval and Natural Language Driven Data Processing

    Oct 19, 2026Marla Grunewald, Fin Gentzen, Iulisloi Zacarias +1Multi-Agent OrchestrationTool Access Control for LLM Agents

    Institute of Computer and Network Engineering, Technische Universität Braunschweig, Germany

  19. Symbolic Constraint Agents: Mining Formal Tool-Call Constraints to Prevent Agent Errors

    Oct 18, 2026Jinu Lee, Shraddha BarkeLLM Agent VerificationRuntime Enforcement for AI Agents

    University of Illinois Urbana-Champaign · Microsoft Research

  20. When Code Becomes an LLM Call: An Empirical Study of Call-Site Contracts in Agentic Systems

    Oct 17, 2026Shihao Weng, Longtian Wang, Yang Feng +6LLM AgentsLLM Agent Verification

    Nanjing University, Nanjing, China · Xi’an Jiaotong University, Xi’an, China · Singapore Management University, Singapore +1

  21. VERAS: Verification-Guided Adaptive Search for Reliable Operations Research

    Oct 16, 2026Minbo Ma, Honglin Zhang, Bangtao Zhou +5Large Language Model-Guided OptimizationLLM Agent Verification

    Tsinghua University, Beijing, China · Meituan, Beijing, China · Shanghai Jiaotong University, Shanghai, China

  22. When Can You Trust an Agent's Own Verifier? Stress-Testing Counterfactual Rationale Verification Under Search Pressure and Oracle Access

    Oct 16, 2026Jonghyun Lee, Moonsu Kim, Sunghwan ParkLLM Agent VerificationAutomated Agent Evaluation

    Yonsei University

  23. Independent Data-Integrity Verification for LLM-Driven Functional Coverage Closure in Hardware Design

    Oct 15, 2026Venkata Krishna Kumar VedantamLLM Agent Verification

    Department of Electrical and Computer Engineering, Portland State University

  24. Trajectory-Level Speculation with Semantic Verification for Tool-Using Agents

    Oct 15, 2026Zilin Wang, Yinhong Liu, Chao Chen +2Tool-Using AgentsLLM Agent Verification

    LARK, HKUST (GZ) · Yinwang · University of Cambridge +1

  25. PRIME: Towards Verifiable Evidence-Grounded Reasoning in LLM Agents

    Oct 15, 2026Hamed Khosravi, Xiaoming HuoLLM Agent VerificationLLM Agent Reliability

    H. Milton Stewart School of Industrial and Systems Engineering Georgia Institute of Technology

  26. Same Claim, Different Interpretations: How LLM Agents Resolve Ambiguity in Scientific Claims

    Oct 14, 2026Delip Rao, Ahmed Muharram, Chris Callison-BurchLLM Agent VerificationScientific Claim Verification

    University of Pennsylvania

  27. Task-State Governance: A Virtual Machine for Verifiable and Recoverable GUI Agent Execution

    Oct 14, 2026Wenkui Yang, Yiming Hao, Kai Zhou +6GUI AgentsAI Agent Governance

    SAIS, University of Chinese Academy of Sciences, Beijing, China · Institute of Automation, Chinese Academy of Sciences, Beijing, China · Meituan, Beijing, China +2

  28. One Monitor Does Not Fit All: Formalism-Agnostic Runtime Verification for Agentic AI

    Oct 14, 2026Angelo FerrandoAI Agent MonitoringRuntime Enforcement for AI Agents

    University of Modena and Reggio Emilia, Modena, Italy

  29. Evidence-First Agentic Verification

    Oct 13, 2026Reza Sanayei, Razvan-Gabriel Dumitru, Sunjie Hou +7LLM Agent VerificationAI Agent Evaluation

    Scale AI · University of Arizona

  30. MENTOR: Procedural Shielding of Tool-Using LLM Agents

    Oct 12, 2026Ashwani Anand, Ivi Chatzi, Ritam Raha +1LLM GuardrailsTool-Using Agents

    Max Planck Institute for Software Systems, Kaiserslautern, Germany · TNO-ESI, Eindhoven, The Netherlands