huihui-ai/Huihui-Qwen3.8-27B-abliterated-GGUF Image-Text-to-Text • 27B • Updated about 24 hours ago • 1.36M • 406
OpenART: Scaling Agent Red Teaming via Open-Ended Environment Evolution Paper • 2608.00677 • Published 27 days ago • 262
HarnessOpt-Bench: Evaluating LLMs at Harness Optimization Paper • 2608.06301 • Published 22 days ago • 35
From RLVR to RLSVR: Task Transformation Induces Self-Verifiable Rewards for Open-Ended LLM Self-Improvement Paper • 2607.23802 • Published Jul 26 • 106