BaseRSI: Recursive Self-Improvement of a Base Vision-Language Model via Training-Free Harness Internalization Paper • 2611.24578 • Published 4 days ago • 1
ScienceClaw: Benchmarking Continual Self-Evolution of AI-for-Science Agents Across the Natural and Social Sciences Paper • 2610.08691 • Published Oct 6
R$^2$ Flow: Recursive Self-Improvement via Recursive Skill Evolution Paper • 2609.33867 • Published Oct 22
CollabFlow: Recursive Self-Improvement of Agent Collaboration Paper • 2609.38662 • Published Oct 22 • 1
Probing Spatial State Representations in Visual Foundation Models Paper • 2610.40636 • Published 24 days ago • 22
R^2Orch: Recursive Self-Improvement for Agent Orchestration via Self-Play within a Skill-Internalization Loop Paper • 2610.22740 • Published Oct 22 • 50
JusticeAxis: Benchmarking Legal Judgment between Rigid Rule Application and Ungrounded Discretion Paper • 2610.00353 • Published Sep 30 • 2