AI Dynamics

Global AI News Aggregator

About

LUFFY Framework Boosts LLM Math Reasoning by Seven Points

LLMs still struggle with deep reasoning LUFFY is a new framework bridging imitation and exploration by injecting off-policy guidance (like DeepSeek-R1) into zero-RL Boosts math reasoning by 7 points Improves weaker base models like Llama and Qwen Trending on alphaXiv

→ View original post on X — @askalphaxiv