mlsanityData to 7 Oct 2026

Multi-role Consensus through LLMs Discussions for Vulnerability Detection

arXiv 2403.14274 ↗First posted 21 Mar 2024cs.SE cs.AIcited by 19

Not on the map. Why?

Abstract (arXiv)

Recent advancements in large language models (LLMs) have highlighted the potential for vulnerability detection, a crucial component of software quality assurance. Despite this progress, most studies have been limited to the perspective of a single role, usually testers, lacking diverse viewpoints from different roles in a typical software development life-cycle, including both developers and testers. To this end, this paper introduces a multi-role approach to employ LLMs to act as different roles simulating a real-life code review process and engaging in discussions toward a consensus on the existence and classification of vulnerabilities in the code. Preliminary evaluation of this approach indicates a 13.48% increase in the precision rate, an 18.25% increase in the recall rate, and a 16.13% increase in the F1 score.

Key facts. Cited by 19 papers in the map (data through 7 Oct 2026). Builds on 7 of its 7 references that are in the map. First posted on arXiv 21 Mar 2024.

Builds on

7 of 7 references.

References · 7

  1. 2018SySeVR: A Framework for Using Deep Learning to Detect Software Vulnerabilitiescited by 91
  2. 2023Prompt-Enhanced Software Vulnerability Detection Using ChatGPTcited by 51
  3. 2023ChatGPT for Vulnerability Detection, Classification, and Repair: How Far Are We?cited by 44
  4. 2024Large Language Model for Vulnerability Detection: Emerging Results and Future Directionscited by 44
  5. 2024Chain-of-Thought Prompting of Large Language Models for Discovering and Fixing Software Vulnerabilitiescited by 31
  6. 2022Dataflow Analysis-Inspired Deep Learning for Efficient Vulnerability Detectioncited by 18
  7. 2024On the Effectiveness of Function-Level Vulnerability Detectors for Inter-Procedural Vulnerabilitiescited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 5; 2025: 11; 2026: 3.

19 papers.

Sort:

By area:

  1. 2024Large Language Model-Based Agents for Software Engineering: A Surveycited by 173
  2. 2024LLM-Based Multi-Agent Systems for Software Engineering: Literature Review, Vision and the Road Aheadcited by 155
  3. 2024When LLMs Meet Cybersecurity: A Systematic Literature Reviewcited by 70
  4. 2025LLMs in Software Security: A Survey of Vulnerability Detection Techniques and Insightscited by 44
  5. 2024Reinforcement Learning from Multi-role Debates as Feedback for Bias Mitigation in LLMscited by 22
  6. 2025Let the Trial Begin: A Mock-Court Approach to Vulnerability Detection using LLM-Based Agentscited by 20
  7. 2024Training Language Models to Win Debates with Self-Play Improves Judge Accuracycited by 16
  8. 2025A Contemporary Survey of Large Language Model Assisted Program Analysiscited by 10
  9. 2025Large Language Models for Security Operations Centers: A Comprehensive Surveycited by 9
  10. 2025VulAgent: Hypothesis-Validation based Multi-Agent Vulnerability Detectioncited by 8
  11. 2026LLM-Based Agentic Systems for Software Engineering: Challenges and Opportunitiescited by 7
  12. 2025CodeVisionary: An Agent-based Framework for Evaluating Large Language Models in Code Generationcited by 6
7 more
  1. 2025QLPro: Automated Code Vulnerability Discovery via LLM and Static Code Analysis Integrationcited by 6
  2. 2025MAVUL: Multi-Agent Vulnerability Detection via Contextual Reasoning and Interactive Refinementcited by 6
  3. 2026Evaluating LLM-Based 0-to-1 Software Generation in End-to-End CLI Tool Scenarioscited by 5
  4. 2025Towards Engineering Multi-Agent LLMs: A Protocol-Driven Approachcited by 4
  5. 2025Designing LLM-based Multi-Agent Systems for Software Engineering Tasks: Quality Attributes, Design Patterns and Rationalecited by 3
  6. 2025Automated detection of atomicity violations in large-scale systemscited by 0
  7. 2026SmartOracle -- An Agentic Approach to Mitigate Noise in Differential Oraclescited by 0