# MulVul: Retrieval-augmented Multi-Agent Code Vulnerability Detection via Cross-Model Prompt Evolution

arXiv: https://arxiv.org/abs/2601.18847 · HTML: https://mlsanity.com/paper/2601.18847/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Privacy and security of RAG, one of 15 directions in Retrieval-augmented generation.
- Builds on 16 of its 27 references that are in the map.
- First posted on arXiv 26 Jan 2026.

## Placed in

- Retrieval-augmented generation / [Privacy and security of RAG](https://mlsanity.com/rag/privacy-and-security-of-rag/)
- LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/)

## Builds on (most cited first, 16 of 16)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Large Language Models Are Human-Level Prompt Engineers](https://mlsanity.com/paper/2211.01910/) (2022)
- [Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate](https://mlsanity.com/paper/2305.19118/) (2023)
- [GraphCodeBERT: Pre-training Code Representations with Data Flow](https://mlsanity.com/paper/2009.08366/) (2020)
- [UniXcoder: Unified Cross-Modal Pre-training for Code Representation](https://mlsanity.com/paper/2203.03850/) (2022)
- [Devign: Effective Vulnerability Identification by Learning Comprehensive Program Semantics via Graph Neural Networks](https://mlsanity.com/paper/1909.03496/) (2019)
- [Deep Learning based Vulnerability Detection: Are We There Yet?](https://mlsanity.com/paper/2009.07235/) (2020)
- [Vulnerability Detection with Code Language Models: How Far Are We?](https://mlsanity.com/paper/2403.18624/) (2024)
- [ReACC: A Retrieval-Augmented Code Completion Framework](https://mlsanity.com/paper/2203.07722/) (2022)
- [SySeVR: A Framework for Using Deep Learning to Detect Software Vulnerabilities](https://mlsanity.com/paper/1807.06756/) (2018)
- [LLMs in Software Security: A Survey of Vulnerability Detection Techniques and Insights](https://mlsanity.com/paper/2502.07049/) (2025)
- [Domain Knowledge Matters: Improving Prompts with Fix Templates for Repairing Python Type Errors](https://mlsanity.com/paper/2306.01394/) (2023)
- [SCALE: Constructing Structured Natural Language Comment Trees for Software Vulnerability Detection](https://mlsanity.com/paper/2403.19096/) (2024)
- [iCodeReviewer: Improving Secure Code Review with Mixture of Prompts](https://mlsanity.com/paper/2510.12186/) (2025)
- [VISION: Robust and Interpretable Code Vulnerability Detection Leveraging Counterfactual Augmentation](https://mlsanity.com/paper/2508.18933/) (2025)
- [textttReMind: Understanding Deductive Code Reasoning in LLMs](https://mlsanity.com/paper/2511.00488/) (2025)

## Built on by (most cited first, 6 of 6)

- [Evolving Agents in the Dark: Retrospective Harness Optimization via Self-Preference](https://mlsanity.com/paper/2606.05922/) (2026)
- [DREA: Decoupled Reasoning and Exploration Agents for Repository-Level Vulnerability Detection](https://mlsanity.com/paper/2607.13439/) (2026)
- [Revisiting Vul-RAG: Reproducibility and Replicability of RAG-based Vulnerability Detection with Open-Weight Models](https://mlsanity.com/paper/2606.04739/) (2026)
- [P2RAG: Efficient Privacy-Preserving RAG Service Supporting Arbitrary Top-k Retrieval](https://mlsanity.com/paper/2603.14778/) (2026)
- [Strategic Heterogeneous Multi-Agent Architecture for Cost-Effective Code Vulnerability Detection](https://mlsanity.com/paper/2604.21282/) (2026)
- [Understanding Implicit Trust Errors in Core Carrier Networks through Multi-Agent Flaw Discovery and Analysis](https://mlsanity.com/paper/2607.10315/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) struggle to automate real-world vulnerability detection due to two key limitations: the heterogeneity of vulnerability patterns undermines the effectiveness of a single unified model, and manual prompt engineering for massive weakness categories is unscalable. To address these challenges, we propose MulVul, a retrieval-augmented multi-agent framework designed for precise and broad-coverage vulnerability detection. MulVul adopts a coarse-to-fine strategy: a Router agent first predicts the top-k coarse categories and then forwards the input to specialized Detector agents, which identify the exact vulnerability types. Both agents are equipped with retrieval tools to actively source evidence from vulnerability knowledge bases to mitigate hallucinations. Crucially, to automate the generation of specialized prompts, we design Cross-Model Prompt Evolution, a prompt optimization mechanism where a generator LLM iteratively refines candidate prompts while a distinct executor LLM validates their effectiveness. This decoupling mitigates the self-correction bias inherent in single-model optimization. Evaluated on 130 CWE types, MulVul achieves 34.79% Macro-F1, outperforming the best baseline by 41.5%. Ablation studies validate cross-model prompt evolution, which boosts performance by 51.6% over manual prompts by effectively handling diverse vulnerability patterns.