code reasoning 1exploration agents 1large language models 1repository analysis 1vulnerability detection 1
From the 1 of 2 linked papers with an AI index.
2 papers
cs.CR2026
DREA: Decoupled Reasoning and Exploration Agents for Repository-Level Vulnerability Detection
Mingyang Sun, Guozhu Meng
The paper introduces DREA, a system that separates reasoning and exploration into two agents to improve vulnerability detection across entire code repositories using large language…
cs.SE2026
KAT-Coder-V2.5 Technical Report
Bo Huang, Fengxiang Li, Hao Xu +50
We present KAT-Coder-V2.5, a coding-focused agentic model trained to act autonomously inside real, executable repositories rather than as a single-turn code generator. Its capabili…