Training Long-Context, Multi-Turn Software Engineering Agents with Reinforcement Learning Paper • 2508.03501 • Published Aug 5 • 57
SWE-rebench: An Automated Pipeline for Task Collection and Decontaminated Evaluation of Software Engineering Agents Paper • 2505.20411 • Published May 26 • 90
Code Graph Model (CGM): A Graph-Integrated Large Language Model for Repository-Level Software Engineering Tasks Paper • 2505.16901 • Published May 22 • 48