Lune

ASE2025Top-tier venue

Vul-R2: A Reasoning LLM for Automated Vulnerability Repair

Xin-Cheng Wen, Zirui Lin, Yijun Yang, Cuiyun Gao, Deheng Ye

Abstract

The exponential increase in software vulnerabilities has created an urgent need for automatic vulnerability repair (AVR) solutions. Recent research has formulated AVR as a sequence generation problem and has leveraged large language models (LLMs) to address this problem. Typically, these approaches prompt or fine-tune LLMs to generate repairs for vulnerabilities directly. Although these methods show state-of-the-art performance, they face the following challenges: (1) Lack of highquality, vulnerability-related reasoning data. Current approaches primarily rely on foundation models that mainly encode general programming knowledge. Without vulnerability-related reasoning data, they tend to fail to capture the diverse vulnerability repair patterns. ( 2 ) Hard to verify the intermediate vulnerability repair process during LLM training. Existing reinforcement learning methods often leverage intermediate execution feedback from the environment (e.g., sandbox-based execution results) to guide reinforcement learning training. In contrast, the vulnerability repair process generally lacks such intermediate, verifiable feedback, which poses additional challenges for model training. To address these challenges, we propose to model the vulnerability repair task from a reasoning perspective and train a reasoning LLM termed Vulnerability Reasoner and Repair (Vul-R2) which consists of two key modules: (1) a domain-aware reasoning learning module, which comprises a reasoning answer construction component, a reasoning data filtering process, and a supervised fine-tuning process for learning vulnerability-related reasoning knowledge; and (2) a curriculum-based verifiable rewarded training module, which comprises dynamically reinforcement learning with verifiable rewards paradigms based on multiple-choice question answering in an easy stage and character-level matching in a hard stage. We evaluate Vul-R2 on the real-world C/C++ dataset PrimeVul to demonstrate its effectiveness in vulnerability repair. Specifically, Vul-R2 outperforms the best baseline by 11.27% for exact match (EM) and successfully repairs 49 additional vulnerabilities. Furthermore, we demonstrate the effectiveness of the proposed paradigm, finetuning Vul-R2 on PrimeVul leads to improved EM performance of 8.78% on a human curated dataset SVEN, even without additional training.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

2 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • VulRepair: a T5-based automated software vulnerability repair cites CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation
  • Repo2Run: Automated Building Executable Environment for Code Repository at Scale cites SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers2

  1. Repo2Run: Automated Building Executable Environment for Code Repository at ScaleRuida Hu, Chao Peng, Xinchen Wang, Junjielong Xu et al.NeurIPS 2025 · 49 citations
  2. SEER: Enhancing Chain-of-Thought Code Generation through Self-Exploring Deep ReasoningShuzheng Gao, Chaozheng Wang, Cuiyun Gao, Michael R. LyuICSE 2026 · 1 citation

Builds on24

  1. Training language models to follow instructions with human feedbackLong Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida et al.NeurIPS 2022 · 24,707 citations
  2. CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and GenerationYue Wang, Weishi Wang, Shafiq R. Joty, Steven C. H. HoiEMNLP 2021 · 1,224 citations
  3. SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software EvolutionYuxiang Wei, Olivier Duchenne, Jade Copet, Quentin Carbonneaux et al.NeurIPS 2025 · 291 citations
  4. VulRepair: a T5-based automated software vulnerability repairMichael Fu, Chakkrit Tantithamthavorn, Trung Le, Van Nguyen et al.FSE 2022 · 206 citations
  5. Data Quality for Software Vulnerability DatasetsRoland Croft, Muhammad Ali Babar, M. Mehdi KholoosiICSE 2023 · 138 citations

Related papers

  1. Boosting Vulnerability Detection of LLMs via Curriculum Preference Optimization with Synthetic Reasoning DataXin-Cheng Wen, Yijun Yang, Cuiyun Gao, Yang Xiao et al.ACL Findings 2025 · 2 citations
  2. VulKey: Automated Vulnerability Repair Guided by Domain-Specific Repair PatternsJia Li, Zhuangbin Chen, Yuxin Su, Michael R. LyuFSE 2026
  3. SeCuRepair: Semantics-Aligned, Curriculum-Driven, and Reasoning-Enhanced Vulnerability Repair FrameworkChengran Yang, Ting Zhang, Jinfeng Jiang, Xin Zhou et al.ACL 2026 · 2 citations
  4. Well Begun is Half Done: Location-Aware and Trace-Guided Iterative Automated Vulnerability RepairZhenlei Ye, Xiaobing Sun, Sicong Cao, Lili Bo et al.ICSE 2026
  5. Hit The Bullseye On The First Shot: Improving LLMs Using Multi-Sample Self-Reward Feedback for Vulnerability RepairRui Jiao, Yue Zhang, Jinku Li, Jianfeng MaASE 2025
Dusk over the sea between two cliffs drawn in fine vertical lines