Plan Then Action:High-Level Planning Guidance Reinforcement Learning for LLM Reasoning

ArXi:2510.01833v2 Announce Type: replace Large language models (LLMs) nstrate strong reasoning abilities via Chain-of-Thought (CoT), but their token-level generation encourages local decisions and lacks global planning, often leading to redundant or inaccurate reasoning. Existing methods, such as tree-based search and reinforcement learning (RL), attempt to address this issue but incur high computational costs and still struggle to produce reliable reasoning trajectories.