SWE-rebench: An Automated Pipeline for Task Collection and Decontaminated Evaluation of Software Engineering Agents Paper • 2505.20411 • Published May 26, 2025 • 92
TOUCAN: Synthesizing 1.5M Tool-Agentic Data from Real-World MCP Environments Paper • 2510.01179 • Published Oct 1, 2025 • 25