RRSI: Regularized Recursive Self-Improvement of Agent Harnesses Paper • 2609.24972 • Published 4 days ago • 187
Repo-To-Skill: Distilling GitHub Repositories Into AI4AI Skills Paper • 2609.02749 • Published 23 days ago • 402
BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent Paper • 2508.06600 • Published Aug 8, 2025 • 44