Compositional Monte Carlo Tree Diffusion for Extendable Planning

NeurIPSSpotlight2025

Authors
Jaesik Yoon, Hyeonseo Cho, Sungjin Ahn
Venue
NeurIPS 2025
Track
Spotlight

TL;DR

Monte Carlo Tree Diffusion (MCTD) integrates diffusion models with structured tree search to enable effective trajectory exploration through stepwise reasoning…

Opening excerpt from the authors’ abstract. source

Read the paper

Topics

exploration diffusion reasoning planning

Related NeurIPS papers

← All NeurIPS 2025 Spotlight papers · Browse the whole archive