July 21, 2025
The GIST New AI method boosts reasoning and planning efficiency in diffusion models
Lisa Lock
scientific editor
Andrew Zinin
lead editor
Editors' notes
This article has been reviewed according to Science X's editorial process and policies. Editors have highlighted the following attributes while ensuring the content's credibility:
fact-checked
preprint
trusted source
proofread

Diffusion models are widely used in many AI applications, but research on efficient inference-time scalability, particularly for reasoning and planning (known as System 2 abilities) has been lacking. In response, a research team has developed a new technology that enables high-performance and efficient inference for planning based on diffusion models.
This technology demonstrated its performance by achieving a 100% success rate on a giant maze-solving task that no existing model had succeeded in. The results are expected to serve as core technology in various fields requiring real-time decision-making, such as intelligent robotics and real-time generative AI.
The research team led by Professor Sungjin Ahn in the School of Computing has developed the new technology that significantly improves the inference-time scalability of diffusion-based reasoning through joint research with Professor Yoshua Bengio of the University of Montreal, a world-renowned scholar in deep learning. This study was carried out as part of a collaboration between KAIST and Mila (Quebec AI Institute) through the Prefrontal AI Joint Research Center.
This technology is gaining attention as a core AI technology that, after training, allows the AI to efficiently utilize more computational resources during inference to solve complex reasoning and planning problems that cannot be addressed merely by scaling up data or model size. However, current diffusion models used across various applications lack effective methodologies for implementing such scalability, particularly for reasoning and planning.
To address this, Professor Ahn's research team collaborated with Professor Bengio to propose a novel diffusion model inference technique based on Monte Carlo Tree Search. This method explores diverse generation paths during the diffusion process in a tree structure and is designed to efficiently identify high-quality outputs even with limited computational resources. As a result, it achieved a 100% success rate on the "giant-scale maze-solving" task, where previous methods had a 0% success rate. The work is published on the arXiv preprint server.
In the follow-up research, also posted to arXiv, the team succeeded in significantly improving the major drawback of the proposed method—its slow speed. By efficiently parallelizing the tree search and optimizing computational cost, they achieved results of equal or superior quality up to 100 times faster than the previous version. This is highly meaningful as it demonstrates the method's inference capabilities and real-time applicability simultaneously.
Professor Sungjin Ahn said, "This research fundamentally overcomes the limitations of existing planning method based on diffusion models, which required high computational cost," adding, "It can serve as core technology in various areas such as intelligent robotics, simulation-based decision-making, and real-time generative AI."
More information: Jaesik Yoon et al, Monte Carlo Tree Diffusion for System 2 Planning, arXiv (2025). DOI: 10.48550/arxiv.2502.07202
Jaesik Yoon et al, Fast Monte Carlo Tree Diffusion: 100x Speedup via Parallel Sparse Planning, arXiv (2025). DOI: 10.48550/arxiv.2506.09498
Journal information: arXiv Provided by The Korea Advanced Institute of Science and Technology (KAIST) Citation: New AI method boosts reasoning and planning efficiency in diffusion models (2025, July 21) retrieved 22 July 2025 from https://techxplore.com/news/2025-07-ai-method-boosts-efficiency-diffusion.html This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no part may be reproduced without the written permission. The content is provided for information purposes only.
Explore further
AI cloud infrastructure gets faster and greener: NPU core improves inference performance by over 60% 1 shares
Feedback to editors