LATIDIA · Ciberseguridad

EviRepair: agentes basados en evidencia para la reparación confiable de vulnerabilidades

arXiv:2610.13491v1 Anuncio Tipo: nuevo Resumen: Los recientes avances en modelos de lenguaje grandes (LLM) han permitido enfoques basados ​​en agentes para la reparación automatizada de vulnerabilidades (AVR) a nivel de repositorio, mostrando una capacidad de reparación prometedora.

La noticia

arXiv:2610.13491v1 Announce Type: new Abstract: Recent advances in large language models (LLMs) have enabled agent-based approaches for repository-level automated vulnerability repair (AVR), showing promising repair capabilities. However, an important issue has received limited attention: how can we ensure that the evidence generated during the repair process is reliable enough to support accurate vulnerability understanding and patch generation? In this paper, we propose EviRepair, an evidence-driven multi-agent framework for repository-level AVR. EviRepair introduces evidence review into the repair process by enabling agents to collaboratively collect vulnerability evidence, verify evidence consistency, and construct a reviewed vulnerability model for patch synthesis and validation. Extensive experiments on PatchEval and SecBench benchmarks with multiple agent