Toward Skill-Native LLMs: Skill Entropy for Benchmarking and Training Long-Horizon Reasoning
By Yinghui He · Paper · cs.CL
Long-horizon reasoning in recent LLMs demands that the model switch between distinct skills inside a reasoning chain, such as first doing a math derivation, then using the result to plan a schedule. We call such problems cross-skill long-horizon tasks: multi-step tasks whose step