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

arXiv: https://arxiv.org/abs/2605.18153 · HTML: https://mlsanity.com/paper/2605.18153/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 21 of its 76 references that are in the map.
- First posted on arXiv 18 May 2026.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)

## Builds on (most cited first, 21 of 21)

- [CodeBERT: A Pre-Trained Model for Programming and Natural Languages](https://mlsanity.com/paper/2002.08155/) (2020)
- [LooGLE: Can Long-Context Language Models Understand Long Contexts?](https://mlsanity.com/paper/2311.04939/) (2023)
- [jina-embeddings-v3: Multilingual Embeddings With Task LoRA](https://mlsanity.com/paper/2409.10173/) (2024)
- [IRIS: LLM-Assisted Static Analysis for Detecting Security Vulnerabilities](https://mlsanity.com/paper/2405.17238/) (2024)
- [Vul-RAG: Enhancing LLM-based Vulnerability Detection via Knowledge-level RAG](https://mlsanity.com/paper/2406.11147/) (2024)
- [LLMs in Software Security: A Survey of Vulnerability Detection Techniques and Insights](https://mlsanity.com/paper/2502.07049/) (2025)
- [Chain-of-Thought Prompting of Large Language Models for Discovering and Fixing Software Vulnerabilities](https://mlsanity.com/paper/2402.17230/) (2024)
- [Benchmarking LLMs and LLM-based Agents in Practical Vulnerability Detection for Code Repositories](https://mlsanity.com/paper/2503.03586/) (2025)
- [How Far Have We Gone in Vulnerability Detection Using Large Language Models](https://mlsanity.com/paper/2311.12420/) (2023)
- [IDEA: Enhancing the Rule Learning Ability of Large Language Model Agent through Induction, Deduction, and Abduction](https://mlsanity.com/paper/2408.10455/) (2024)
- [Let the Trial Begin: A Mock-Court Approach to Vulnerability Detection using LLM-Based Agents](https://mlsanity.com/paper/2505.10961/) (2025)
- [VulEval: Towards Repository-Level Evaluation of Software Vulnerability Detection](https://mlsanity.com/paper/2404.15596/) (2024)
- [To Err is Machine: Vulnerability Detection Challenges LLM Reasoning](https://mlsanity.com/paper/2403.17218/) (2024)
- [Everything You Wanted to Know About LLM-based Vulnerability Detection But Were Afraid to Ask](https://mlsanity.com/paper/2504.13474/) (2025)
- [VulnLLMEval: A Framework for Evaluating Large Language Models in Software Vulnerability Detection and Patching](https://mlsanity.com/paper/2409.10756/) (2024)
- [A Survey on Automated Software Vulnerability Detection Using Machine Learning and Deep Learning](https://mlsanity.com/paper/2306.11673/) (2023)
- [Reasoning with LLMs for Zero-Shot Vulnerability Detection](https://mlsanity.com/paper/2503.17885/) (2025)
- [VulDeePecker: A Deep Learning-Based System for Vulnerability Detection](https://mlsanity.com/paper/1801.01681/) (2018)
- [EvalSVA: Multi-Agent Evaluators for Next-Gen Software Vulnerability Assessment](https://mlsanity.com/paper/2501.14737/) (2024)
- [Retrieval Augmented Generation Integrated Large Language Models in Smart Contract Vulnerability Detection](https://mlsanity.com/paper/2407.14838/) (2024)
- [Can LLM Prompting Serve as a Proxy for Static Analysis in Vulnerability Detection](https://mlsanity.com/paper/2412.12039/) (2024)

## Built on by (most cited first, 1 of 1)

- [Transferable Self-Evolving Playbooks for Agentic Security Auditing](https://mlsanity.com/paper/2606.16420/) (2026)

## Abstract (arXiv)

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.