PoC-Adapt: Semantic-Aware Automated Vulnerability Reproduction with LLM Multi-Agents and Reinforcement Learning-Driven Adaptive Policy

Phan The Duy, Khoa Ngo-Khanh, Nguyen Huu Quyen +1

While recent approaches leverage large language models (LLMs) and multi-agent pipelines to automatically generate proof-of-concept (PoC) exploits from vulnerability reports, existi…