SEJul 1

Knowledge-Enhanced Agentic Vulnerability Repair

arXiv:2607.0082015.4
Predicted impact top 20% in SE · last 90 daysOriginality Incremental advance
AI Analysis

For security practitioners, KeaRepair improves AVR effectiveness by grounding patch generation in verified program facts and prior fix knowledge, outperforming existing methods.

KeaRepair, a knowledge-enhanced agentic approach for Automated Vulnerability Repair (AVR), achieves an 83.64% repair rate on 55 C/C++ vulnerabilities using Gemini-3.1-Pro, fixing six unique vulnerabilities that no baseline can address and demonstrating strong cross-language generalizability.

Frontier foundation models have changed the math on vulnerability discovery, but the bigger challenge is how the remediation side keeps up. Despite recent progresses in Automated Vulnerability Repair (AVR), current solutions struggle to reliably identify the root causes of vulnerabilities, and insufficiently utilize the prior fix knowledge to guide the patch generation process, thus undermining their effectiveness in practice. To address this gap, we propose KeaRepair, a novel agentic AVR approach that grounds patch generation in verified program facts and high-level vulnerability knowledge. Specifically, KeaRepair first extracts multi-dimensional vulnerability knowledge from historical vulnerability-patch pairs from dual complementary views, and constructs dedicated retrieval knowledge bases. It then employs a tool-augmented agent that performs ReAct-style reasoning to collect verified program facts for vulnerability diagnosis. Finally, based on the diagnostic results, KeaRepair performs knowledge-level retrieval-augmented patch generation and iteratively refines patches through a closed-loop validation process involving compilation, PoC replay, and test-suite execution. Experimental results show that KeaRepair significantly outperforms existing AVR approaches on 55 reproducible C/C++ vulnerabilities. When paired with Gemini-3.1-Pro, KeaRepair successfully repairs 46 vulnerabilities, achieving a repair rate of 83.64%. Moreover, KeaRepair fixes six unique vulnerabilities that none of the baselines can address, and further demonstrates strong cross-language generalizability.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes