AgentSWE: Can Coding Agents Build the Agent You Actually Want? Paper • 2610.13361 • Published Oct 9 • 57
AREX-2: Advancing Self-Improving Agents through Long-Horizon Reflective Tasks Paper • 2609.38288 • Published Sep 29 • 89
Repo-To-Skill: Distilling GitHub Repositories Into AI4AI Skills Paper • 2609.02749 • Published Sep 2 • 148