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.
2 stories, newest first · one card per story
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.
Specialized agents re-localize from failed patches and reject symptom-only fixes on real C/C++ bugs.
Today 2.1K readers · 11K views · 8.4K reads · all time 157K views