Three Heads Are Better Than One: A Multi-perspective Reasoning Framework for Enhanced Vulnerability Detection

• URL: http://arxiv.org/abs/2605.18153v1
• Date: Mon, 18 May 2026 09:57:22 GMT
• Title: Three Heads Are Better Than One: A Multi-perspective Reasoning Framework for Enhanced Vulnerability Detection
• Abstract summary: We propose ReasonVul, a novel multi-perspective reasoning framework that harnesses cognitive synergy among three specialized LLM agents.<n>The framework begins with independent analyses of the source code, followed by a structured debate mechanism to resolve conflicts.<n>We analyzed 542 conflict cases and found that 389 were correctly resolved, highlighting the framework's ability to uncover hidden vulnerabilities.
• Score: 17.33447267029733
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Automated vulnerability detection is crucial for enhancing software security by identifying potential flaws that attackers could exploit, thereby reducing the reliance on labor-intensive manual code audits. Recent advancements have shifted towards leveraging large language models (LLMs) for vulnerability detection, with techniques like Vul-RAG and VulnSage demonstrating progress through structured prompting and external knowledge integration. However, these approaches typically rely on a single reasoning paradigm, limiting their ability to address the complex and diverse nature of real-world vulnerabilities. To overcome these limitations, we propose ReasonVul, a novel multi-perspective reasoning framework that harnesses cognitive synergy among three specialized LLM agents, each embodying a distinct reasoning mode. The framework begins with independent analyses of the source code, followed by a structured debate mechanism to resolve conflicts through iterative rebuttal and revision, ultimately converging on a collaborative judgment. Evaluated on the PrimeVul dataset, ReasonVul achieves a PairAcc of 40.00% and an F1-score of 72.52%, surpassing the best baseline by 81.24% in PairAcc. Further tests on the JITVUL dataset confirm its generalizability, with a PairAcc of 28.67%. Additionally, we analyzed 542 conflict cases and found that 389 were correctly resolved, highlighting the framework's ability to uncover hidden vulnerabilities through the error-correction mechanism driven by the debate. This work emphasizes the importance of multi-perspective reasoning and collaborative validation in achieving robust and comprehensive vulnerability detection in real-world software systems.

Related papers

• CLEAR: Causal Context-Based Agentic Reasoning for Vulnerability Detection [3.2238600872149275]
  Causal Context-based Agentic Reasoning (CLEAR) is a novel multi-agent vulnerability detection framework integrated with a causal knowledge graph.<n>Four specialized agents, including the Collector, Claim, Critic, and Judge, collaboratively verify vulnerability hypotheses through retrieved causal contexts.<n>CLEAR improves Pair-Correct (P-C) performance by 130.7% and 71.56% over state-of-the-art approaches.
  arXiv  Detail & Related papers  (2026-08-04T05:03:11Z)
• DREA: Decoupled Reasoning and Exploration Agents for Repository-Level Vulnerability Detection [16.007199928732614]
  We present DREA, a hypothesis-driven framework for repository-level vulnerability detection.<n>Goal-directed context acquisition is the primary source of detection improvement in this design.<n>To support evaluation, we construct RepoPairBench, a repository-grounded benchmark of validated Python vulnerability-fix pairs from real-world projects.
  arXiv  Detail & Related papers  (2026-07-15T04:49:05Z)
• Detecting Vulnerability-Inducing Commits via Multi-Stage Reasoning with LLM-Based Agents [18.673118303783188]
  VIC-RAGENT is a multi-agent framework for effective and explainable vulnerability detection.<n>It uses specialized agents to provide complementary perspectives, including structural analysis, intent understanding, and vulnerability inspection.<n>It consistently outperforms baselines, including Direct, CoT, and CodeAgent.
  arXiv  Detail & Related papers  (2026-07-07T02:54:46Z)
• FuzzingBrain V2: A Multi-Agent LLM System for Automated Vulnerability Discovery and Reproduction [7.802658978010212]
  Software vulnerabilities pose critical security threats, with nearly 50,000 CVEs reported in 2025.<n>While Large Language Models (LLMs) show promise for automated vulnerability detection, three key challenges remain.<n>We present FuzzingBrain V2, a multi-agent system that addresses these gaps through four key contributions.
  arXiv  Detail & Related papers  (2026-05-20T22:17:14Z)
• Co-RedTeam: Orchestrated Security Discovery and Exploitation with LLM Agents [57.49020237126194]
  Large language models (LLMs) have shown promise in assisting cybersecurity tasks, yet existing approaches struggle with automatic vulnerability discovery and exploitation.<n>We propose Co-RedTeam, a security-aware multi-agent framework designed to mirror real-world red-teaming.<n>Co-RedTeam decomposes vulnerability analysis into coordinated discovery and exploitation stages, enabling agents to plan, execute, validate, and refine actions.
  arXiv  Detail & Related papers  (2026-02-02T14:38:45Z)
• FaithCoT-Bench: Benchmarking Instance-Level Faithfulness of Chain-of-Thought Reasoning [62.452350134196934]
  FaithCoT-Bench is a unified benchmark for instance-level CoT unfaithfulness detection.<n>Our framework formulates unfaithfulness detection as a discriminative decision problem.<n>FaithCoT-Bench sets a solid basis for future research toward more interpretable and trustworthy reasoning in LLMs.
  arXiv  Detail & Related papers  (2025-10-05T05:16:54Z)
• Eigen-1: Adaptive Multi-Agent Refinement with Monitor-Based RAG for Scientific Reasoning [53.45095336430027]
  We develop a unified framework that combines implicit retrieval and structured collaboration.<n>On Humanity's Last Exam (HLE) Bio/Chem Gold, our framework achieves 48.3% accuracy.<n>Results on SuperGPQA and TRQA confirm robustness across domains.
  arXiv  Detail & Related papers  (2025-09-25T14:05:55Z)
• Ensembling Large Language Models for Code Vulnerability Detection: An Empirical Evaluation [69.8237598448941]
  This study investigates the potential of ensemble learning to enhance the performance of Large Language Models (LLMs) in source code vulnerability detection.<n>We propose Dynamic Gated Stacking (DGS), a Stacking variant tailored for vulnerability detection.
  arXiv  Detail & Related papers  (2025-09-16T03:48:22Z)
• VulAgent: Hypothesis-Validation based Multi-Agent Vulnerability Detection [55.957275374847484]
  VulAgent is a multi-agent vulnerability detection framework based on hypothesis validation.<n>It implements a semantics-sensitive, multi-view detection pipeline, each aligned to a specific analysis perspective.<n>On average, VulAgent improves overall accuracy by 6.6%, increases the correct identification rate of vulnerable--fixed code pairs by up to 450%, and reduces the false positive rate by about 36%.
  arXiv  Detail & Related papers  (2025-09-15T02:25:38Z)
• SAVANT: Vulnerability Detection in Application Dependencies through Semantic-Guided Reachability Analysis [6.989158266868967]
  integration of open-source third-party library dependencies in Java development introduces significant security risks.<n>Savant combines semantic preprocessing with LLM-powered context analysis for accurate vulnerability detection.<n>Savant achieves 83.8% precision, 73.8% recall, 69.0% accuracy, and 78.5% F1-score, outperforming state-of-the-art SCA tools.
  arXiv  Detail & Related papers  (2025-06-21T19:48:13Z)
• Lie Detector: Unified Backdoor Detection via Cross-Examination Framework [68.45399098884364]
  We propose a unified backdoor detection framework in the semi-honest setting.<n>Our method achieves superior detection performance, improving accuracy by 5.4%, 1.6%, and 11.9% over SoTA baselines.<n> Notably, it is the first to effectively detect backdoors in multimodal large language models.
  arXiv  Detail & Related papers  (2025-03-21T06:12:06Z)
• Code Change Intention, Development Artifact and History Vulnerability: Putting Them Together for Vulnerability Fix Detection by LLM [13.278153690972243]
  VulFixMiner and CoLeFunDa focus solely on code changes, neglecting essential context from development artifacts.<n>We propose LLM4VFD, a novel framework that leverages Large Language Models (LLMs) enhanced with Chain-of-Thought reasoning and In-Context Learning.
  arXiv  Detail & Related papers  (2025-01-24T23:40:03Z)
• VulEval: Towards Repository-Level Evaluation of Software Vulnerability Detection [14.312197590230994]
  repository-level evaluation system named textbfVulEval aims at evaluating the detection performance of inter- and intra-procedural vulnerabilities simultaneously. VulEval consists of a large-scale dataset, with a total of 4,196 CVE entries, 232,239 functions, and corresponding 4,699 repository-level source code in C/C++ programming languages.
  arXiv  Detail & Related papers  (2024-04-24T02:16:11Z)
• Chain-of-Thought Prompting of Large Language Models for Discovering and Fixing Software Vulnerabilities [21.787125867708962]
  Large language models (LLMs) have demonstrated impressive potential in various domains. In this paper, we explore how to leverage LLMs and chain-of-thought (CoT) prompting to address three key software vulnerability analysis tasks. We show substantial superiority of our CoT-inspired prompting over the baselines.
  arXiv  Detail & Related papers  (2024-02-27T05:48:18Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.