EvoRepair is the first experience-based self-evolving agent framework for automated vulnerability repair, reporting 90.46% overall success on PATCHEVAL and SEC-bench benchmarks.
Patcheval: A new benchmark for evaluating llms on patching real-world vulnerabilities,
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
years
2026 6representative citing papers
Refusal-ablated LLMs outperform aligned models on code-grounded localization and early executable patch generation, while aligned models retain advantages on shallow diagnostic tasks under neutral wording.
On 183 validated V8/SpiderMonkey vulnerabilities, the best coding agents verify at most 38.8% of instances, and crash-only grading would inflate judged successes by 43.6%.
MemRepair is a hierarchical memory-augmented agent framework that raises repository-level vulnerability repair rates to 58.0-58.2% on Python/Go/JS benchmarks and 30.58% on C++ by combining history, pattern, and refinement memories with iterative feedback.
KeaRepair achieves 83.64% repair rate on 55 C/C++ vulnerabilities by grounding patch generation in extracted historical knowledge and agent-collected program facts with closed-loop validation.
ContraFix uses contrastive runtime analysis plus a dual-track skill base to reach 92% resolution on SEC-Bench and 73.8% on PatchEval while improving semantic correctness of patches.
citing papers explorer
-
EvoRepair: Enhancing Vulnerability Repair Agents Through Experience-Based Self-Evolution
EvoRepair is the first experience-based self-evolving agent framework for automated vulnerability repair, reporting 90.46% overall success on PATCHEVAL and SEC-bench benchmarks.
-
Beyond Refusal: A Same-Lineage Study of Aligned and Abliterated LLMs for Vulnerability Analysis
Refusal-ablated LLMs outperform aligned models on code-grounded localization and early executable patch generation, while aligned models retain advantages on shallow diagnostic tasks under neutral wording.
-
SEC-bench Pro: Can Language Models Solve Long-Horizon Software Security Tasks?
On 183 validated V8/SpiderMonkey vulnerabilities, the best coding agents verify at most 38.8% of instances, and crash-only grading would inflate judged successes by 43.6%.
-
MemRepair: Hierarchical Memory for Agentic Repository-Level Vulnerability Repair
MemRepair is a hierarchical memory-augmented agent framework that raises repository-level vulnerability repair rates to 58.0-58.2% on Python/Go/JS benchmarks and 30.58% on C++ by combining history, pattern, and refinement memories with iterative feedback.
-
Knowledge-Enhanced Agentic Vulnerability Repair
KeaRepair achieves 83.64% repair rate on 55 C/C++ vulnerabilities by grounding patch generation in extracted historical knowledge and agent-collected program facts with closed-loop validation.
-
ContraFix: Skill-Enhanced Contrastive Runtime Analysis for Vulnerability Repair
ContraFix uses contrastive runtime analysis plus a dual-track skill base to reach 92% resolution on SEC-Bench and 73.8% on PatchEval while improving semantic correctness of patches.