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 • 89
Cramming 1568 Tokens into a Single Vector and Back Again: Exploring the Limits of Embedding Space Capacity Paper • 2502.13063 • Published Feb 18 • 72
