BigCodeArena: Unveiling More Reliable Human Preferences in Code Generation via Execution Paper • 2510.08697 • Published Oct 9, 2025 • 39
Kimi-K2 Collection Moonshot's MoE LLMs with 1 trillion parameters, exceptional on agentic intellegence • 5 items • Updated 8 days ago • 167
Spark: Strategic Policy-Aware Exploration via Dynamic Branching for Long-Horizon Agentic Learning Paper • 2601.20209 • Published 7 days ago • 22