Monte Carlo Tree Diffusion for System 2 Planning
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908794837008384 |
|---|---|
| author | Yoon, Jaesik Cho, Hyeonseo Baek, Doojin Bengio, Yoshua Ahn, Sungjin |
| author_facet | Yoon, Jaesik Cho, Hyeonseo Baek, Doojin Bengio, Yoshua Ahn, Sungjin |
| contents | Diffusion models have recently emerged as a powerful tool for planning. However, unlike Monte Carlo Tree Search (MCTS)-whose performance naturally improves with inference-time computation scaling-standard diffusion-based planners offer only limited avenues for the scalability. In this paper, we introduce Monte Carlo Tree Diffusion (MCTD), a novel framework that integrates the generative strength of diffusion models with the adaptive search capabilities of MCTS. Our method reconceptualizes denoising as a tree-structured process, allowing partially denoised plans to be iteratively evaluated, pruned, and refined. By selectively expanding promising trajectories while retaining the flexibility to revisit and improve suboptimal branches, MCTD achieves the benefits of MCTS such as controlling exploration-exploitation trade-offs within the diffusion framework. Empirical results on challenging long-horizon tasks show that MCTD outperforms diffusion baselines, yielding higher-quality solutions as inference-time computation increases. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_07202 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Monte Carlo Tree Diffusion for System 2 Planning Yoon, Jaesik Cho, Hyeonseo Baek, Doojin Bengio, Yoshua Ahn, Sungjin Artificial Intelligence Machine Learning Diffusion models have recently emerged as a powerful tool for planning. However, unlike Monte Carlo Tree Search (MCTS)-whose performance naturally improves with inference-time computation scaling-standard diffusion-based planners offer only limited avenues for the scalability. In this paper, we introduce Monte Carlo Tree Diffusion (MCTD), a novel framework that integrates the generative strength of diffusion models with the adaptive search capabilities of MCTS. Our method reconceptualizes denoising as a tree-structured process, allowing partially denoised plans to be iteratively evaluated, pruned, and refined. By selectively expanding promising trajectories while retaining the flexibility to revisit and improve suboptimal branches, MCTD achieves the benefits of MCTS such as controlling exploration-exploitation trade-offs within the diffusion framework. Empirical results on challenging long-horizon tasks show that MCTD outperforms diffusion baselines, yielding higher-quality solutions as inference-time computation increases. |
| title | Monte Carlo Tree Diffusion for System 2 Planning |
| topic | Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2502.07202 |