ExploreRepair agents patch vulnerabilities without full bug details
On PatchEval it scores 39.6% with GPT-5.6-Luna and 71.6% with DeepSeek-V4.1-Flash, above EvoRepair by 16.0 and 25.4 points.
Stories per day · 30 days
1 RSS
Relatedllm-agents2adversarial-testing1automated-patching1automated-program-repair1claude-code1p2patch1patcheval1vulnloc1
7 stories, newest first · one card per story
Stories tagged #vulnerability-repair
P2Patch: Exploit-Guided Vulnerability Repair
P2Patch forces LLM vulnerability repairs to block new same-bug exploits found by an adversarial agent.
EviRepair: Evidence-Driven Agents for Reliable Vulnerability Repair
EviRepair uses evidence review among LLM agents to improve repository-level vulnerability repair on PatchEval and SecBench.
Does AI Help Cyber Attackers or Defenders? Evidence from Nonpublic Vulnerabilities and Subsequent Attacks
AI attack and repair performance varies sharply on nonpublic vulnerabilities, and one fix often fails later tests.
Where Did the Repair First Go Wrong? Localizing the Origins of Silent Failures in Agentic Vulnerability Repair
SAGE traces where coding agents first abandon security while producing patches that still pass functional tests.
SecProbe: Adaptive Evaluation of Coding Agents on Cybersecurity Vulnerabilities
SecProbe adaptively tests coding agents on synthesized vulnerability repairs; frontier models peak at 28.33% success.
Metrics Failure in LLM-Based Code Vulnerability Repair: An Empirical Study and a Change-Aware Screen
Researchers show compile rate poorly measures LLM repairs of C/C++ vulnerabilities and propose a change-aware screen.