mlsanityData to 7 Oct 2026

Monte Carlo Tree Diffusion for System 2 Planning

arXiv 2502.07202 ↗First posted 11 Feb 2025cs.AI cs.LGcited by 33

On the map: LLM reasoning → Diffusion reasoning and test-time scaling

also in 1 more
Abstract (arXiv)

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.

Key facts. Cited by 33 papers in the map (data through 7 Oct 2026). Placed in Diffusion reasoning and test-time scaling, one of 17 directions in LLM reasoning. Builds on 23 of its 30 references that are in the map. First posted on arXiv 11 Feb 2025.

Builds on

23 of 30 references.

References · 23

  1. 2020Denoising Diffusion Implicit Modelscited by 9,655
  2. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  3. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  4. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  5. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,155
  6. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 2,994
  7. 2019Mastering Atari, Go, Chess and Shogi by Planning with a Learned Modelcited by 1,327
  8. 2022Planning with Diffusion for Flexible Behavior Synthesiscited by 1,023
  9. 2024Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusioncited by 634
  10. 2022Diffusion Policies as an Expressive Policy Class for Offline Reinforcement Learningcited by 543
  11. 2022Is Conditional Generative Modeling all you need for Decision-Making?cited by 504
  12. 2024ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Searchcited by 338
11 more
  1. 2025rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinkingcited by 308
  2. 2024OGBench: Benchmarking Offline Goal-Conditioned RLcited by 216
  3. 2024Accessing GPT-4 level Mathematical Olympiad Solutions via Monte Carlo Tree Self-refine with LLaMa-3 8Bcited by 156
  4. 2025Towards System 2 Reasoning in LLMs: Learning How to Think With Meta Chain-of-Thoughtcited by 108
  5. 2022Deep Hierarchical Planning from Pixelscited by 96
  6. 2024Simple Hierarchical Planning with Diffusioncited by 71
  7. 2024Diffusion Model Predictive Controlcited by 35
  8. 2020Sub-Goal Trees -- a Framework for Goal-Based Reinforcement Learningcited by 27
  9. 2024VerMCTS: Synthesizing Multi-Step Programs using a Verifier, a Large Language Model, and Tree Searchcited by 13
  10. 2024Dr. Strategy: Model-Based Generalist Agents with Strategic Dreamingcited by 6
  11. 2024PlanDQ: Hierarchical Plan Orchestration via D-Conductor and Q-Performercited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 15; 2026: 18.

33 papers.

Sort:

By area:

  1. 2025Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Modelscited by 381
  2. 2025Inference-time Scaling of Diffusion Models through Classical Searchcited by 48
  3. 2026A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agentscited by 47
  4. 2025Diffusion Tree Sampling: Scalable inference-time alignment of diffusion modelscited by 31
  5. 2026Why Reasoning Fails to Plan: A Planning-Centric Analysis of Long-Horizon Decision Making in LLM Agentscited by 22
  6. 2025ScalingNoise: Scaling Inference-Time Search for Generating Infinite Videoscited by 12
  7. 2025State-Covering Trajectory Stitching for Diffusion Plannerscited by 11
  8. 2025Local Manifold Approximation and Projection for Manifold-Aware Diffusion Planningcited by 8
  9. 2025Fast Monte Carlo Tree Diffusion: 100x Speedup via Parallel Sparse Planningcited by 6
  10. 2025Controllable Graph Generation with Diffusion Models via Inference-Time Tree Search Guidancecited by 5
  11. 2026Chain-of-Goals Hierarchical Policy for Long-Horizon Offline Goal-Conditioned RLcited by 5
  12. 2026Action Hallucination in Generative Vision-Language-Action Modelscited by 5
21 more
  1. 2025Scaling Test-Time Inference with Policy-Optimized, Dynamic Retrieval-Augmented Generation via KV Caching and Decodingcited by 4
  2. 2025Tree-Guided Diffusion Plannercited by 4
  3. 2026Compositional Planning with Jumpy World Modelscited by 4
  4. 2026Diffusion ReRoll: Revisable Denoising for Robotic Sequential Predictioncited by 4
  5. 2025Risk-Guided Diffusion: Toward Deploying Robot Foundation Models in Space, Where Failure Is Not An Optioncited by 3
  6. 2025Diffusion Language Model Inference with Monte Carlo Tree Searchcited by 3
  7. 2025Monte Carlo Tree Diffusion with Multiple Experts for Protein Designcited by 2
  8. 2025Compositional Monte Carlo Tree Diffusion for Extendable Planningcited by 2
  9. 2026UnMaskFork: Test-Time Scaling for Masked Diffusion via Deterministic Action Branchingcited by 2
  10. 2026Compositional Visual Planning via Inference-Time Diffusion Scalingcited by 2
  11. 2026Refining Compositional Diffusion for Reliable Long-Horizon Planningcited by 2
  12. 2026Inference-Time Scaling in Diffusion Models through Iterative Partial Refinementcited by 2
  13. 2026Diffusion Large Language Models for Black-Box Optimizationcited by 1
  14. 2026Can I Have Your Order? Monte-Carlo Tree Search for Slot Filling Ordering in Diffusion Language Modelscited by 1
  15. 2026Improving Diffusion Planners by Self-Supervised Action Gating with Energiescited by 1
  16. 2026NoiseRater: Meta-Learned Noise Valuation for Diffusion Model Trainingcited by 1
  17. 2026X-DiffVLA: X-Embodied Diffusion Action Heads for Vision-Language-Action Modelscited by 1
  18. 2025When Diffusion Breaks Constraints: Sequential Autoregressive Generation with RL and MCTScited by 0
  19. 2026ChronoForest: Closed-Loop Multi-Tree Diffusion Planning for Efficient Bridge Search and Route Compositioncited by 0
  20. 2026MA-WAM: Multi-Agent World-Action Model for Test-Time Planningcited by 0
  21. 2026PreviewDiff: Multimodal Critic-Guided Search over Diffusion Latentscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Chain-of-Trajectories: Unlocking the Intrinsic Generative Optimality of Diffusion Models via Graph-Theoretic Planning
  2. 2024Diffusion Model for Planning: A Systematic Literature Review
  3. 2026Plan First, Diffuse Later: Extrinsic Graph Guidance for Long-Horizon Diffusion Planning
  4. 2025Path Planning for Masked Diffusion Model Sampling
  5. 2026DiRecT: Safe Diffusion-Based Planning via Receding-Horizon Denoising
  6. 2026P3: Persistent Particle Planning for Constrained Diffusion Control
  7. 2026Amortizing Trajectory Diffusion with Keyed Drift Fields
  8. 2025TR2-D2: Tree Search Guided Trajectory-Aware Fine-Tuning for Discrete Diffusion