This repository is a comprehensive, curated bibliography of research papers on Monte Carlo Tree Search (MCTS), a powerful algorithmic technique for decision-making in complex domains. It targets researchers, engineers, and practitioners seeking to understand and implement MCTS, providing direct links to papers and, where available, their corresponding code implementations. The primary benefit is a centralized, organized resource for exploring the evolution and application of MCTS across various AI fields.

How It Works

The project functions as an "awesome list," meticulously compiling and categorizing MCTS-related academic publications. Papers are organized by year and the conference or journal in which they were published, spanning major venues in machine learning, computer vision, natural language processing, robotics, and artificial intelligence. This structured approach allows users to easily navigate the landscape of MCTS research, from foundational concepts to cutting-edge advancements, and discover associated implementations for practical application.

Quick Start & Requirements

This repository is a curated list of research papers and does not contain executable code or require installation. Users can directly access the listed papers and code repositories via the provided links.

Highlighted Details

• Extensive coverage from 1988 to 2025, including upcoming AAAI 2025 and ICML 2025 publications.
• Includes papers from a wide array of top-tier conferences and journals across AI, ML, CV, NLP, and Robotics.
• Many entries link directly to associated code implementations, facilitating practical adoption and experimentation.
• Features papers exploring MCTS applications in diverse areas such as game playing, mathematical reasoning, robotics, LLM agents, and optimization.

Maintenance & Community

The README does not provide specific details on maintenance frequency, active contributors, or community channels (e.g., Discord, Slack). It appears to be a static, curated list.

Licensing & Compatibility

The repository is licensed under CC0 Universal, which dedicates the work to the public domain. This license imposes no restrictions on use, modification, or distribution, making it fully compatible with commercial and closed-source applications.

Limitations & Caveats

As a curated list, its comprehensiveness is dependent on the curator's ongoing efforts. The inclusion of "code" links is not guaranteed for every paper, and the quality or maintenance status of external code repositories is beyond the scope of this list. The list focuses solely on MCTS papers and does not include tutorials or introductory materials.