SWE-Pruner Pro: The Coder LLM Already Knows What to Prune Paper • 2607.18213 • Published 7 days ago • 76
RESOURCE2SKILL: Distilling Executable Agent Skills from Human-Created Multimodal Resources Paper • 2606.29538 • Published 11 days ago • 140
SWE-Explore: Benchmarking How Coding Agents Explore Repositories Paper • 2606.07297 • Published Jun 5 • 122
Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability Paper • 2604.06628 • Published Apr 8 • 329
UniG2U-Bench: Do Unified Models Advance Multimodal Understanding? Paper • 2603.03241 • Published Mar 3 • 88