# R2Vul: Learning to Reason about Software Vulnerabilities with Reinforcement Learning and Structured Reasoning Distillation

arXiv: https://arxiv.org/abs/2504.04699 · HTML: https://mlsanity.com/paper/2504.04699/

## Key facts

- Cited by 7 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 33 of its 61 references that are in the map.
- First posted on arXiv 7 Apr 2025.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)
- LLM alignment / RLHF / preference optimisation / [Safety alignment and jailbreak attacks](https://mlsanity.com/alignment/safety-alignment-and-jailbreak-attacks/)
- Knowledge distillation / [Knowledge distillation for LLMs](https://mlsanity.com/distill/knowledge-distillation-for-llms/)

## Builds on (most cited first, 30 of 33)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [Towards A Rigorous Science of Interpretable Machine Learning](https://mlsanity.com/paper/1702.08608/) (2017)
- [Least-to-Most Prompting Enables Complex Reasoning in Large Language Models](https://mlsanity.com/paper/2205.10625/) (2022)
- [CodeBERT: A Pre-Trained Model for Programming and Natural Languages](https://mlsanity.com/paper/2002.08155/) (2020)
- [Qwen2.5-Coder Technical Report](https://mlsanity.com/paper/2409.12186/) (2024)
- [Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2307.15217/) (2023)
- [CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation](https://mlsanity.com/paper/2102.04664/) (2021)
- [WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct](https://mlsanity.com/paper/2308.09583/) (2023)
- [BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions](https://mlsanity.com/paper/2406.15877/) (2024)
- [Zephyr: Direct Distillation of LM Alignment](https://mlsanity.com/paper/2310.16944/) (2023)
- [Vulnerability Detection with Code Language Models: How Far Are We?](https://mlsanity.com/paper/2403.18624/) (2024)
- [LLMs Cannot Reliably Identify and Reason About Security Vulnerabilities (Yet?): A Comprehensive Evaluation, Framework, and Benchmarks](https://mlsanity.com/paper/2312.12575/) (2023)
- [Vul-RAG: Enhancing LLM-based Vulnerability Detection via Knowledge-level RAG](https://mlsanity.com/paper/2406.11147/) (2024)
- [SelfCodeAlign: Self-Alignment for Code Generation](https://mlsanity.com/paper/2410.24198/) (2024)
- [LLM4Vuln: A Unified Evaluation Framework for Decoupling and Enhancing LLMs' Vulnerability Reasoning](https://mlsanity.com/paper/2401.16185/) (2024)
- [CodeUltraFeedback: An LLM-as-a-Judge Dataset for Aligning Large Language Models to Coding Preferences](https://mlsanity.com/paper/2403.09032/) (2024)
- [Finetuning Large Language Models for Vulnerability Detection](https://mlsanity.com/paper/2401.17010/) (2024)
- [CodeDPO: Aligning Code Models with Self Generated and Verified Source Code](https://mlsanity.com/paper/2410.05605/) (2024)
- [Chain-of-Thought Prompting of Large Language Models for Discovering and Fixing Software Vulnerabilities](https://mlsanity.com/paper/2402.17230/) (2024)
- [Generalization-Enhanced Code Vulnerability Detection via Multi-Task Instruction Fine-Tuning](https://mlsanity.com/paper/2406.03718/) (2024)
- [Does RLHF Scale? Exploring the Impacts From Data, Model, and Method](https://mlsanity.com/paper/2412.06000/) (2024)
- [To Err is Machine: Vulnerability Detection Challenges LLM Reasoning](https://mlsanity.com/paper/2403.17218/) (2024)
- [Comparison of Static Application Security Testing Tools and Large Language Models for Repo-level Vulnerability Detection](https://mlsanity.com/paper/2407.16235/) (2024)
- [Transformer-based Vulnerability Detection in Code at EditTime: Zero-shot, Few-shot, or Fine-tuning?](https://mlsanity.com/paper/2306.01754/) (2023)
- [Security Vulnerability Detection with Multitask Self-Instructed Fine-Tuning of Large Language Models](https://mlsanity.com/paper/2406.05892/) (2024)
- [Investigating Large Language Models for Code Vulnerability Detection: An Experimental Study](https://mlsanity.com/paper/2412.18260/) (2024)

## Built on by (most cited first, 7 of 7)

- [VulInstruct: Teaching LLMs Root-Cause Reasoning for Vulnerability Detection via Security Specifications](https://mlsanity.com/paper/2511.04014/) (2025)
- [From SFT to RL: Demystifying the Post-Training Pipeline for LLM-based Vulnerability Detection](https://mlsanity.com/paper/2602.14012/) (2026)
- [VULPO: Context-Aware Vulnerability Detection via On-Policy LLM Optimization](https://mlsanity.com/paper/2511.11896/) (2025)
- [DREA: Decoupled Reasoning and Exploration Agents for Repository-Level Vulnerability Detection](https://mlsanity.com/paper/2607.13439/) (2026)
- [Themis: Training Robust Multilingual Code Reward Models for Flexible Multi-Criteria Scoring](https://mlsanity.com/paper/2605.00754/) (2026)
- [VulReaD: Knowledge-Graph-guided Software Vulnerability Reasoning and Detection](https://mlsanity.com/paper/2602.10787/) (2026)
- [Neuro-Symbolic Reasoning for Vulnerability Detection](https://mlsanity.com/paper/2607.03963/) (2026)

## Abstract (arXiv)

Large language models (LLMs) have shown promising performance in software vulnerability detection, yet their reasoning capabilities remain unreliable. We propose R2Vul, a method that combines reinforcement learning from AI feedback (RLAIF) and structured reasoning distillation to teach small code LLMs to detect vulnerabilities while generating security-aware explanations. Unlike prior chain-of-thought and instruction tuning approaches, R2Vul rewards well-founded over deceptively plausible vulnerability explanations through RLAIF, which results in more precise detection and high-quality reasoning generation. To support RLAIF, we construct the first multilingual preference dataset for vulnerability detection, comprising 18,000 high-quality samples in C#, JavaScript, Java, Python, and C. We evaluate R2Vul across five programming languages and against four static analysis tools, eight state-of-the-art LLM-based baselines, and various fine-tuning approaches. Our results demonstrate that a 1.5B R2Vul model exceeds the performance of its 32B teacher model and leading commercial LLMs such as Claude-4-Opus. Furthermore, we introduce a lightweight calibration step that reduces false positive rates under varying imbalanced data distributions. Finally, through qualitative analysis, we show that both LLM and human evaluators consistently rank R2Vul model's reasoning higher than other reasoning-based baselines.