2 papers
cs.CR2026
Root-Cause-Driven Automated Vulnerability Repair
Hulin Wang, Zion Leonahenahe Basque, Jie Hu +13
Recent LLM-based systems have made automated vulnerability repair increasingly practical, but two challenges remain. First, without strong signals about where a bug originates, rep…
cs.SE2025
BuildBench: Benchmarking LLM Agents on Compiling Real-World Open-Source Software
Zehua Zhang, Ati Priya Bajaj, Divij Handa +13
Automatically compiling open-source software (OSS) projects is a vital, labor-intensive, and complex task, which makes it a good challenge for LLM Agents. Existing methods rely on…