RRSI: Regularized Recursive Self-Improvement of Agent Harnesses Paper • 2609.24972 • Published 5 days ago • 205
SpatialBlock: Enhancing Spatial Intelligence in LVLMs via Synthetic Block-Stacking Problem Paper • 2609.07064 • Published 19 days ago • 146
WHALE: A Simple Recipe for Joint Harness-Weight Optimization Paper • 2609.00196 • Published 26 days ago • 37
WHALE: A Simple Recipe for Joint Harness-Weight Optimization Paper • 2609.00196 • Published 26 days ago • 37
J-Zero: Unified Challenger--Solver--Judge Co-Evolution from Zero Data Paper • 2608.26582 • Published about 1 month ago • 41
TRIAGE: Dialectical Reasoning for Explainable Risk Prediction on Irregularly Sampled Medical Time Series with LLMs Paper • 2606.09030 • Published Jun 8 • 30
Who Should Lead Decoding Now? Tracking Reliable Trajectories for Ensembling Masked Diffusion Language Models Paper • 2606.16281 • Published Jun 15 • 33
CollabVR: Collaborative Video Reasoning with Vision-Language and Video Generation Models Paper • 2605.08735 • Published May 9 • 72