mlsanityData to 14 Oct 2026

Compositional Monte Carlo Tree Diffusion for Extendable Planning

arXiv 2510.21361 ↗First posted 24 Oct 2025cs.LGcited by 2

On the map: Diffusion models → Diffusion and flow policies for robotics

Abstract (arXiv)

Monte Carlo Tree Diffusion (MCTD) integrates diffusion models with structured tree search to enable effective trajectory exploration through stepwise reasoning. However, MCTD remains fundamentally limited by training trajectory lengths. While periodic replanning allows plan concatenation for longer plan generation, the planning process remains locally confined, as MCTD searches within individual trajectories without access to global context. We propose Compositional Monte Carlo Tree Diffusion (C-MCTD), a framework that elevates planning from individual trajectory optimization to reasoning over complete plan compositions. C-MCTD introduces three complementary components: (1) Online Composer, which performs globally-aware planning by searching across entire plan compositions; (2) Distributed Composer, which reduces search complexity through parallel exploration from multiple starting points; and (3) Preplan Composer, which accelerates inference by leveraging cached plan graphs.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in Diffusion and flow policies for robotics, one of 14 directions in Diffusion models. Builds on 23 of its 35 references that are in the map. First posted on arXiv 24 Oct 2025.

Builds on

23 of 35 references.

Closest ancestors · 8

Same direction, newest first

  1. 2025Generative Trajectory Stitching through Diffusion Composition7 Mar
  2. 2025What Makes a Good Diffusion Planner for Decision Making?1 Mar
  3. 2025Monte Carlo Tree Diffusion for System 2 Planning11 Feb
  4. 2024Diffusion Model Predictive Control7 Oct
  5. 2024Stitching Sub-Trajectories with Conditional Diffusion Model for Goal-Conditioned Offline RL11 Feb
  6. 2024Simple Hierarchical Planning with Diffusion5 Jan
  7. 2022Is Conditional Generative Modeling all you need for Decision-Making?28 Nov
  8. 2022Diffusion Policies as an Expressive Policy Class for Offline Reinforcement Learning12 Aug

Other references · 15

  1. 2020Denoising Diffusion Implicit Modelscited by 9,781
  2. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  3. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  4. 2022Classifier-Free Diffusion Guidancecited by 5,847
  5. 2019Dream to Control: Learning Behaviors by Latent Imaginationcited by 1,653
  6. 2018World Modelscited by 1,513
  7. 2022Planning with Diffusion for Flexible Behavior Synthesiscited by 1,061
  8. 2024Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusioncited by 681
  9. 2024OGBench: Benchmarking Offline Goal-Conditioned RLcited by 238
  10. 2025Inference-Time Scaling for Diffusion Models beyond Scaling Denoising Stepscited by 234
  11. 2022TransDreamer: Reinforcement Learning with Transformer World Modelscited by 143
  12. 2024DiffuserLite: Towards Real-time Diffusion Planningcited by 42
3 more
  1. 2025Inference-Time Text-to-Video Alignment with Diffusion Latent Beam Searchcited by 41
  2. 2024DiffStitch: Boosting Offline Reinforcement Learning with Diffusion-based Trajectory Stitchingcited by 36
  3. 2024PlanDQ: Hierarchical Plan Orchestration via D-Conductor and Q-Performercited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Plan First, Diffuse Later: Extrinsic Graph Guidance for Long-Horizon Diffusion Planningcited by 0
  2. 2026ChronoForest: Closed-Loop Multi-Tree Diffusion Planning for Efficient Bridge Search and Route Compositioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Fast Monte Carlo Tree Diffusion: 100x Speedup via Parallel Sparse Planning
  2. 2026Refining Compositional Diffusion for Reliable Long-Horizon Planning
  3. 2026Coarse-to-Fine Compositional Diffusion for Long-Horizon Planning
  4. 2025Train-Once Plan-Anywhere Kinodynamic Motion Planning via Diffusion Trees
  5. 2025Tree-Guided Diffusion Planner
  6. 2026Compositional Visual Planning via Inference-Time Diffusion Scaling
  7. 2026M2-PALE: A Framework for Explaining Multi-Agent MCTS--Minimax Hybrids via Process Mining and LLMs
  8. 2025MALinZero: Efficient Low-Dimensional Search for Mastering Complex Multi-Agent Planning