# Mastering Board Games by External and Internal Planning with Language Models

arXiv: https://arxiv.org/abs/2412.12119 · HTML: https://mlsanity.com/paper/2412.12119/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- First posted on arXiv 2 Dec 2024.

## Placed in

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

## Built on by (most cited first, 30 of 31)

- [Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRs](https://mlsanity.com/paper/2503.01307/) (2025)
- [Towards System 2 Reasoning in LLMs: Learning How to Think With Meta Chain-of-Thought](https://mlsanity.com/paper/2501.04682/) (2025)
- [Agentic Large Language Models, a survey](https://mlsanity.com/paper/2503.23037/) (2025)
- [A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agents](https://mlsanity.com/paper/2601.12538/) (2026)
- [Position: Stop Anthropomorphizing Intermediate Tokens as Reasoning/Thinking Traces!](https://mlsanity.com/paper/2504.09762/) (2025)
- [Generative to Agentic AI: Survey, Conceptualization, and Challenges](https://mlsanity.com/paper/2504.18875/) (2025)
- [Inference-Time Computations for LLM Reasoning and Planning: A Benchmark and Insights](https://mlsanity.com/paper/2502.12521/) (2025)
- [Code World Models for General Game Playing](https://mlsanity.com/paper/2510.04542/) (2025)
- [Agents of Change: Self-Evolving LLM Agents for Strategic Planning](https://mlsanity.com/paper/2506.04651/) (2025)
- [BoxingGym: Benchmarking Progress in Automated Experimental Design and Model Discovery](https://mlsanity.com/paper/2501.01540/) (2025)
- [World Modelling Improves Language Model Agents](https://mlsanity.com/paper/2506.02918/) (2025)
- [TurnBench-MS: A Benchmark for Evaluating Multi-Turn, Multi-Step Reasoning in Large Language Models](https://mlsanity.com/paper/2506.01341/) (2025)
- [AI Testing Should Account for Sophisticated Strategic Behaviour](https://mlsanity.com/paper/2508.14927/) (2025)
- [Cardiverse: Harnessing LLMs for Novel Card Game Prototyping](https://mlsanity.com/paper/2502.07128/) (2025)
- [Baba is LLM: Reasoning in a Game with Dynamic Rules](https://mlsanity.com/paper/2506.19095/) (2025)
- [Look-ahead Reasoning with a Learned Model in Imperfect Information Games](https://mlsanity.com/paper/2510.05048/) (2025)
- [Exploring Human-AI Conceptual Alignment through the Prism of Chess](https://mlsanity.com/paper/2510.26025/) (2025)
- [Mixing Expert Knowledge: Bring Human Thoughts Back To the Game of Go](https://mlsanity.com/paper/2601.16447/) (2026)
- [Extracting Search Trees from LLM Reasoning Traces Reveals Myopic Planning](https://mlsanity.com/paper/2605.06840/) (2026)
- [Feedback-Induced Performance Decline in LLM-Based Decision-Making](https://mlsanity.com/paper/2507.14906/) (2025)
- [Ludax: A GPU-Accelerated Domain Specific Language for Board Games](https://mlsanity.com/paper/2506.22609/) (2025)
- [Causal Masking on Spatial Data: An Information-Theoretic Case for Learning Spatial Datasets with Unimodal Language Models](https://mlsanity.com/paper/2510.27009/) (2025)
- [Reasoning Capabilities of Large Language Models. Lessons Learned from General Game Playing](https://mlsanity.com/paper/2602.19160/) (2026)
- [AgentSociety: Incentivizing Agentic Social Intelligence](https://mlsanity.com/paper/2605.26203/) (2026)
- [A Close Look At World Model Recovery In Supervised Fine-Tuned LLM Planners](https://mlsanity.com/paper/2606.03685/) (2026)
- [Planning with Transformers: Chain of Computation and Structured Context Windows](https://mlsanity.com/paper/2607.17710/) (2026)
- [SAGE: Structured Strategic Reasoning for Efficient LLM Game Playing](https://mlsanity.com/paper/2609.34342/) (2026)
- [Finding the Move Is Not Winning the Game: XiangqiBench for Closed-Loop Evaluation of LLM Agents](https://mlsanity.com/paper/2610.02425/) (2026)
- [Language Models that Play Chess and Explain Their Moves](https://mlsanity.com/paper/2610.03695/) (2026)
- [Representation-Aligned Auxiliary Supervision for Language Model Adaptation](https://mlsanity.com/paper/2610.04098/) (2026)

## Abstract (arXiv)

Advancing planning and reasoning capabilities of Large Language Models (LLMs) is one of the key prerequisites towards unlocking their potential for performing reliably in complex and impactful domains. In this paper, we aim to demonstrate this across board games (Chess, Fischer Random / Chess960, Connect Four, and Hex), and we show that search-based planning can yield significant improvements in LLM game-playing strength. We introduce, compare and contrast two major approaches: In external search, the model guides Monte Carlo Tree Search (MCTS) rollouts and evaluations without calls to an external game engine, and in internal search, the model is trained to generate in-context a linearized tree of search and a resulting final choice. Both build on a language model pre-trained on relevant domain knowledge, reliably capturing the transition and value functions in the respective environments, with minimal hallucinations. We evaluate our LLM search implementations against game-specific state-of-the-art engines, showcasing substantial improvements in strength over the base model, and reaching Grandmaster-level performance in chess while operating closer to the human search budget. Our proposed approach, combining search with domain knowledge, is not specific to board games, hinting at more general future applications.