SkillClaw: Let Skills Evolve Collectively with Agentic Evolver Paper • 2604.08377 • Published 8 days ago • 276
Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability Paper • 2604.06628 • Published 9 days ago • 310
mradermacher/gemma-4-31B-it-Mystery-Fine-Tune-HERETIC-UNCENSORED-Thinking-i1-GGUF 31B • Updated 8 days ago • 10.8k • 3
arithmetic-circuit-overloading/Llama-3.3-70B-Instruct-v2-3d-4M-400K-0.1-reverse-padzero-99-256D-3L-2H-1024I Text Generation • 3.16M • Updated 12 days ago • 1.29k • 1
MonitorBench: A Comprehensive Benchmark for Chain-of-Thought Monitorability in Large Language Models Paper • 2603.28590 • Published 17 days ago • 22