LLM Agent Verification

LLM: Large Language Model

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

170 papers32 papers in the last four weeks, down 24% on the four weeks before. 0.2% of all new papers.

  1. From FIPS to FPGA with LLM Agents: Measuring What Tests and Reviews Miss in Post-Quantum Cryptographic Hardware

    Nov 19, 2026Jungmin Park, Eunha Kim, Wooseop Kim +2LLM Agent VerificationAI Agent Auditing

  2. Agent Verifiers in Counterfactual Analysis: A Pilot Study Benchmarking Agentic Heterogeneous Treatment Effects

    Nov 17, 2026Satiyabooshan Murugaboopathy, Entejar Alam, Adel Daoud +1LLM Agent VerificationCausal Inference

  3. Verifying Agents in Rubric-Graded Environments

    Nov 17, 2026Markus Dücker, Vaibhav Kumar, Yi Liu +4LLM Agent VerificationAI Agent Evaluation

  4. Turing Agent: Agentic Formal Verification for Mathematical Research

    Nov 16, 2026Yang Chen, Qianyi Wang, Ronghui Yang +13Formal VerificationLarge Language Model-Guided Theorem Proving

  5. FinVerify: A Verification Framework for Financial Agents

    Nov 16, 2026Mao Guan, Qian Chen, Ge Meng +1Claim VerificationLLM Agent Verification

  6. HydroMind: A Checkable Agent for Autonomous Hydrological Research

    Nov 15, 2026Zheng Fang, Yiqun Sun, Simin Qu +1LLM Agent HarnessesAutonomous Research Agents

  7. Agent-Guided Process Verification for Mathematical Self-Correction

    Nov 14, 2026Rui Zou, Mengqi Wei, Xin Zhao +1LLM Self-CorrectionMathematical Reasoning

  8. Soteria: Formally Verified Planning with Runtime Enforcement for Safe LLM Agents

    Nov 13, 2026Mike He, Ankush Desai, Sharad Malik +1LLM Agent SafetyLLM Agent Planning

  9. Verify by Doing: Co-Evolving Agent Execution and Evaluation without External Feedback

    Nov 11, 2026Yitong Lin, Jianda Chen, Yihao Hu +5LLM Agent VerificationSelf-Improving Agents

  10. Veritas: A Verifier Generation Harness for Agent Tasks

    Nov 9, 2026Daoan Zhang, Qinbo Bai, Dehai Min +3LLM Agent VerificationAutomated Agent Evaluation

  11. Agents Propose, Code Verifies, Humans Decide: Verified Agentic Ingestion of Heterogeneous Scientific Tables into Relational Databases

    Nov 8, 2026Bharatha Rankothge, Suzanne Hodgkins, Virginia Rich +1Data IntegrationLLM Agent Verification

  12. SMART: State-based Multi Agent Reasoning Traces for Verification-oriented Problem-Solving

    Nov 5, 2026Sai Vallurupalli, Francis FerraroMulti-Agent LLM SystemsLLM Agent Verification

  13. When the Consumer Is an Agent: Execution-Grounded Service-Level Agreements

    Nov 3, 2026Michal Orzechowski, Renata G. Slota, Jacek KitowskiLLM Agent VerificationLLM Agent Reliability

  14. Action Verification through Conjecture and Refutation for Language Model Agents

    Nov 2, 2026Minhyeon Oh, Chiyeong Heo, Geonwoo Noh +3LLM Agent VerificationReasoning Verification

  15. Agent4FreeFem: A Verification-Guided Framework for Autonomous Topology Optimization

    Oct 31, 2026Zhipu Cui, Helin Gong, Shengfeng ZhuTopology OptimizationNatural Language to Optimization Modeling

  16. 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

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

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

  18. 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

  19. Rethinking Verification in Agent Harnesses

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

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

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