OpenART: Scaling Agent Red Teaming via Open-Ended Environment Evolution Paper • 2608.00677 • Published 14 days ago • 252
SkillZip: Evaluation-Free Skill Compression for Self-Evolving Agents by Discovering Reusable Structure Paper • 2608.11079 • Published 4 days ago • 16
A Hybrid Nested Harness for Decoupling Structure and Parameters in LLM-Driven Optimization Paper • 2608.08156 • Published 7 days ago • 9
Interpretable MEG Decoding of Perceived Speech: Cortical Sources and the Stimulus Features That Drive Retrieval Paper • 2608.01481 • Published 13 days ago • 69
GST-Bench: Can VLMs Develop Global Spatial Awareness from Video? Paper • 2608.05747 • Published 9 days ago • 46
HauhauCS/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive Image-Text-to-Text • 35B • Updated Apr 17 • 2.33M • 3.43k