Extracting Search Trees from LLM Reasoning Traces Reveals Myopic Planning

ArXi:2605.06840v1 Announce Type: new Large language models (LLMs), especially reasoning models, generate extended chain-of-thought (CoT) reasoning that often contains explicit deliberation over future outcomes. Yet whether this deliberation constitutes genuine planning, how it is structured, and what aspects of it drive performance remain poorly understood. In this work, we