mlsanityData to 7 Oct 2026

Let the Trial Begin: A Mock-Court Approach to Vulnerability Detection using LLM-Based Agents

arXiv 2505.10961 ↗First posted 16 May 2025cs.SE cs.AIcited by 20

On the map: LLM agents and tool use → Agent threats, guardrails and governance

Abstract (arXiv)

Detecting vulnerabilities in source code remains a critical yet challenging task, especially when benign and vulnerable functions share significant similarities. In this work, we introduce VulTrial, a courtroom-inspired multi-agent framework designed to identify vulnerable code and to provide explanations. It employs four role-specific agents, which are security researcher, code author, moderator, and review board. Using GPT-4o as the base LLM, VulTrial almost doubles the efficacy of prior best-performing baselines. Additionally, we show that role-specific instruction tuning with small quantities of data significantly further boosts VulTrial's efficacy. Our extensive experiments demonstrate the efficacy of VulTrial across different LLMs, including an open-source, in-house-deployable model (LLaMA-3.1-8B), as well as the high quality of its generated explanations and its ability to uncover multiple confirmed zero-day vulnerabilities in the wild.

Key facts. Cited by 20 papers in the map (data through 7 Oct 2026). Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use. Builds on 36 of its 66 references that are in the map. First posted on arXiv 16 May 2025.

Builds on

36 of 66 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024EvalSVA: Multi-Agent Evaluators for Next-Gen Software Vulnerability Assessment11 Dec

Other references · 35

  1. 2024The Llama 3 Herd of Modelscited by 14,192
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  3. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
  4. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  5. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,582
  6. 2020CodeBERT: A Pre-Trained Model for Programming and Natural Languagescited by 1,286
  7. 2023Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debatecited by 995
  8. 2021CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generationcited by 890
  9. 2022UniXcoder: Unified Cross-Modal Pre-training for Code Representationcited by 355
  10. 2023ToolQA: A Dataset for LLM Question Answering with External Toolscited by 273
  11. 2023Large Language Models Empowered Agent-based Modeling and Simulation: A Survey and Perspectivescited by 253
  12. 2023Can Language Models Solve Graph Problems in Natural Language?cited by 249
23 more
  1. 2024LLM-Based Multi-Agent Systems for Software Engineering: Literature Review, Vision and the Road Aheadcited by 155
  2. 2020Deep Learning based Vulnerability Detection: Are We There Yet?cited by 142
  3. 2018Automated Vulnerability Detection in Source Code Using Deep Representation Learningcited by 114
  4. 2023DiverseVul: A New Vulnerable Source Code Dataset for Deep Learning Based Vulnerability Detectioncited by 98
  5. 2023LLMs Cannot Reliably Identify and Reason About Security Vulnerabilities (Yet?): A Comprehensive Evaluation, Framework, and Benchmarkscited by 94
  6. 2023Let the LLMs Talk: Simulating Human-to-Human Conversational QA via Zero-Shot LLM-to-LLM Interactionscited by 70
  7. 2024Vul-RAG: Enhancing LLM-based Vulnerability Detection via Knowledge-level RAGcited by 67
  8. 2024LLM4Vuln: A Unified Evaluation Framework for Decoupling and Enhancing LLMs' Vulnerability Reasoningcited by 57
  9. 2024POSIX: A Prompt Sensitivity Index For Large Language Modelscited by 56
  10. 2023Prompt-Enhanced Software Vulnerability Detection Using ChatGPTcited by 51
  11. 2023Large Language Model-Powered Smart Contract Vulnerability Detection: New Perspectivescited by 48
  12. 2024Large Language Model for Vulnerability Detection: Emerging Results and Future Directionscited by 44
  13. 2024Finetuning Large Language Models for Vulnerability Detectioncited by 39
  14. 2023Uncovering the Limits of Machine Learning for Automatic Vulnerability Detectioncited by 30
  15. 2024Multi-role Consensus through LLMs Discussions for Vulnerability Detectioncited by 19
  16. 2022Dataflow Analysis-Inspired Deep Learning for Efficient Vulnerability Detectioncited by 18
  17. 2024Harnessing Large Language Models for Software Vulnerability Detection: A Comprehensive Benchmarking Studycited by 17
  18. 2023Distinguishing Look-Alike Innocent and Vulnerable Code by Subtle Semantic Representation Learning and Explanationcited by 11
  19. 2024ChainLM: Empowering Large Language Models with Improved Chain-of-Thought Promptingcited by 8
  20. 2024Can Large Language Models Understand DL-Lite Ontologies? An Empirical Studycited by 4
  21. 2024Beyond ChatGPT: Enhancing Software Quality Assurance Tasks with Diverse LLMs and Validation Techniquescited by 4
  22. 2023Explaining Explanation: An Empirical Study on Explanation in Code Reviewscited by 3
  23. 2024Developing Guidelines for Functionally-Grounded Evaluation of Explainable Artificial Intelligence using Tabular Datacited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 5; 2026: 15.

20 papers.

Sort:

By area:

  1. 2025SecureVibeBench: Benchmarking Secure Vibe Coding of AI Agents via Reconstructing Vulnerability-Introducing Scenarioscited by 11
  2. 2025VulAgent: Hypothesis-Validation based Multi-Agent Vulnerability Detectioncited by 8
  3. 2025MAVUL: Multi-Agent Vulnerability Detection via Contextual Reasoning and Interactive Refinementcited by 6
  4. 2026Co-RedTeam: Orchestrated Security Discovery and Exploitation with LLM Agentscited by 6
  5. 2025VulInstruct: Teaching LLMs Root-Cause Reasoning for Vulnerability Detection via Security Specificationscited by 4
  6. 2026From SFT to RL: Demystifying the Post-Training Pipeline for LLM-based Vulnerability Detectioncited by 4
  7. 2025VULPO: Context-Aware Vulnerability Detection via On-Policy LLM Optimizationcited by 3
  8. 2026Measuring and Exploiting Contextual Bias in LLM-Assisted Security Code Reviewcited by 3
  9. 2026TitanCA: Lessons from Orchestrating LLM Agents to Discover 100+ CVEscited by 2
  10. 2026AEGIS: From Clues to Verdicts -- Graph-Guided Deep Vulnerability Reasoning via Dialectics and Meta-Auditingcited by 1
  11. 2026VulTriage: Triple-Path Context Augmentation for LLM-Based Vulnerability Detectioncited by 1
  12. 2026Three Heads Are Better Than One: A Multi-perspective Reasoning Framework for Enhanced Vulnerability Detectioncited by 1
8 more
  1. 2026Revelio: Cost-Efficient Agentic Memory Safety Vulnerability Detection For Repository-Scale Codebasescited by 1
  2. 2026Graph Is the Verifier: Agentic Reinforcement Learning for Interprocedural Vulnerability Detectioncited by 1
  3. 2026Refute-or-Promote: An Adversarial Stage-Gated Multi-Agent Review Methodology for High-Precision LLM-Assisted Defect Discoverycited by 0
  4. 2026Strategic Heterogeneous Multi-Agent Architecture for Cost-Effective Code Vulnerability Detectioncited by 0
  5. 2026ALIBI: Adaptive Agentic Attacks on LLM-Based Vulnerability Detectors via Adversarial Code Commentscited by 0
  6. 2026DART: A DAG-Based Reputation and Incentive Framework via Blockchain-Enabled Governance for Trustworthy LLM Multi-Agent Collaborationcited by 0
  7. 2026When Passing Tests Hides Vulnerabilities: An Empirical Study of Silent Failures in Agentic Systemscited by 0
  8. 2026A Function-Level Vulnerability Score Measures Flag Rate More Than the Model: Protocol Effects on Paired Benchmarkscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025VulnLLM-R: Specialized Reasoning LLM with Agent Scaffold for Vulnerability Detection
  2. 2025Benchmarking LLMs and LLM-based Agents in Practical Vulnerability Detection for Code Repositories
  3. 2025From LLMs to Agents: A Comparative Evaluation of LLMs and LLM-based Agents in Security Patch Detection
  4. 2024AutoSafeCoder: A Multi-Agent Framework for Securing LLM Code Generation through Static Analysis and Fuzz Testing
  5. 2026VulnGym: Benchmarking Coding Agents for Repository-Level Vulnerability Detection
  6. 2026A Multi-Agent Framework for Automated Exploit Generation with Constraint-Guided Comprehension and Reflection
  7. 2026Argus: Reorchestrating Static Analysis via a Multi-Agent Ensemble for Full-Chain Security Vulnerability Detection
  8. 2026Detecting Vulnerability-Inducing Commits via Multi-Stage Reasoning with LLM-Based Agents