Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills Paper • 2607.22529 • Published Jul 24 • 47
LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget Paper • 2607.14952 • Published Jul 16 • 212
AnyGroundBench: A Specialized-Domain Benchmark for Video Grounding in Vision-Language Models Paper • 2607.02269 • Published Jul 2 • 9
Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputs Paper • 2605.30611 • Published May 28 • 253
Reflective Prompt Tuning through Language Model Function-Calling Paper • 2605.21781 • Published May 20 • 9