# Extracting Search Trees from LLM Reasoning Traces Reveals Myopic Planning

arXiv: https://arxiv.org/abs/2605.06840 · HTML: https://mlsanity.com/paper/2605.06840/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 13 of its 36 references that are in the map.
- First posted on arXiv 7 May 2026.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)

## Builds on (most cited first, 13 of 13)

- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines](https://mlsanity.com/paper/2310.03714/) (2023)
- [Measuring Faithfulness in Chain-of-Thought Reasoning](https://mlsanity.com/paper/2307.13702/) (2023)
- [From System 1 to System 2: A Survey of Reasoning Large Language Models](https://mlsanity.com/paper/2502.17419/) (2025)
- [Measuring Progress on Scalable Oversight for Large Language Models](https://mlsanity.com/paper/2211.03540/) (2022)
- [NATURAL PLAN: Benchmarking LLMs on Natural Language Planning](https://mlsanity.com/paper/2406.04520/) (2024)
- [Competitive Programming with Large Reasoning Models](https://mlsanity.com/paper/2502.06807/) (2025)
- [Learning to Combat Compounding-Error in Model-Based Reinforcement Learning](https://mlsanity.com/paper/1912.11206/) (2019)
- [Mastering Board Games by External and Internal Planning with Language Models](https://mlsanity.com/paper/2412.12119/) (2024)
- [Premise-Augmented Reasoning Chains Improve Error Identification in Math reasoning with LLMs](https://mlsanity.com/paper/2502.02362/) (2025)
- [LLMs Can Plan Only If We Tell Them](https://mlsanity.com/paper/2501.13545/) (2025)
- [ChessArena: A Chess Testbed for Evaluating Strategic Reasoning Capabilities of Large Language Models](https://mlsanity.com/paper/2509.24239/) (2025)
- [Disentangling generalization and memorization in large language models using chess](https://mlsanity.com/paper/2601.16823/) (2026)

## Built on by (most cited first, 2 of 2)

- [Communicating Chess Strategies in Natural Language](https://mlsanity.com/paper/2607.11486/) (2026)
- [Self-Play Search Distillation for Large Language Model Reasoning](https://mlsanity.com/paper/2609.30936/) (2026)

## Abstract (arXiv)

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 introduce a new method to characterize LLM planning by extracting and quantifying search trees from reasoning traces in the four-in-a-row board game. By fitting computational models on the extracted search trees, we characterize how plans are structured and how they influence move decisions. We find that LLMs' search is shallower than humans', and that performance is predicted by search breadth rather than depth. Most strikingly, although LLMs expand deep nodes in their traces, their move choices are best explained by a myopic model that ignores those nodes entirely. A causal intervention study where we selectively prune CoT paragraphs further suggests that move selection is driven predominantly by shallow rather than deep nodes. These patterns contrast with human planning, where performance is driven primarily by deep search. Together, our findings reveal a key difference between LLM and human planning: while human expertise is driven by deeper search, LLMs do not act on deep lookahead. This dissociation offers targeted guidance for aligning LLM and human planning. More broadly, our framework provides a generalizable approach for interpreting the structure of LLM planning across strategic domains.