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. HabitatAgent: An End-to-End Multi-Agent System for Housing Consultation

    Apr 1, 2026Hongyang Yang, Yanxin Zhang, Yang She +5AI-Assisted Decision MakingMulti-Agent LLM Systems

  2. Beyond Task Completion: A Verification-vs.-Conformance Gap in Tool-Evolving Agents

    Apr 1, 2026Alibek Kaliyev, Artem MaryanskyyAI Agent ReliabilityTool-Use Evaluation

  3. Marco DeepResearch: Unlocking Efficient Deep Research Agents via Verification-Centric Design

    Mar 30, 2026Bin Zhu, Qianghuai Jia, Tian Lan +6Deep Research AgentsLLM Agent Training

  4. SEVerA: Verified Synthesis of Self-Evolving Agents

    Mar 26, 2026Debangshu Banerjee, Changming Xu, Eugene Ie +5Agentic Code GenerationSelf-Evolving Agents

  5. UCAgent: An End-to-End Agent for Block-Level Functional Verification

    Mar 26, 2026Junyue Wang, Zhicheng Yao, Yan Pi +6LLM Agent VerificationAutomated Test Generation

  6. TopoPilot: Reliable Conversational Workflow Automation for Topological Data Analysis and Visualization

    Mar 26, 2026Nathaniel Gorski, Shusen Liu, Bei WangAgentic WorkflowsAI Agent Reliability

  7. Solver-Aided Verification of Policy Compliance in Tool-Augmented LLM Agents

    Mar 20, 2026Cailin Winston, Claris Winston, René JustTool Access Control for LLM AgentsLLM Agent Verification

  8. DualSpec: Accelerating Deep Research Agents via Dual-Process Action Speculation

    Mar 8, 2026Shuzhang Zhong, Baotong Lu, Qi Chen +3Deep Research AgentsLLM Inference Acceleration

  9. aCAPTCHA: Verifying That an Entity Is a Capable Agent via Asymmetric Hardness

    Mar 7, 2026Zuyao Xu, Xiang Li, Fubin Wu +3LLM Agent VerificationAI Agent Security

  10. Saarthi for AGI: Towards Domain-Specific General Intelligence for Formal Verification

    Mar 3, 2026Aman Kumar, Deepak Narayan Gadde, Luu Danh Minh +3SystemVerilog Assertion GenerationLLM Agent Verification

  11. Guideline-Grounded Evidence Accumulation for High-Stakes Agent Verification

    Mar 3, 2026Yichi Zhang, Nabeel Seedat, Yinpeng Dong +3LLM Agent VerificationAI Agent Reliability

  12. RIVA: Leveraging LLM Agents for Reliable Configuration Drift Detection

    Mar 2, 2026Sami Abuzakuk, Lucas Crijns, Anne-Marie Kermarrec +2LLM Agent ReliabilityLLM Agent Verification

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

    Feb 22, 2026Chanjin ParkAI Agent ReliabilityLLM Agent Reliability

  14. Verifiable Semantics for Agent-to-Agent Communication

    Feb 18, 2026Philipp Schoenegger, Matt Carlson, Chris Schneider +1Semantic Drift in Language ModelsMulti-Agent Communication

  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. Communication and Verification in LLM Agents towards Collaboration under Information Asymmetry

    Oct 29, 2025Run Peng, Ziqiao Ma, Amy Pang +5Multi-Agent LLM SystemsLLM Agent Verification