Knowing What to Solve Before How: Preplan Empowered LLM Mathematical Reasoning 事件

Knowing What to Solve Before How: Preplan Empowered LLM Mathematical Reasoning arXiv:2605.30245v1 Announce Type: new Abstract: Current plan-based reasoning methods improve large language models (LLMs) by inserting a planning stage before execution, giving rise to the question $\rightarrow$ plan $\rightarrow$ cot paradigm. While effective, a closer examination reveals an inherent paradigm-level gap: both the planning and its execution stages decide how to solve a problem, while the prior questio