Plan First, Diffuse Later: Extrinsic Graph Guidance for Long-Horizon Diffusion Planning

• URL: http://arxiv.org/abs/2605.16863v1
• Date: Sat, 16 May 2026 07:53:04 GMT
• Title: Plan First, Diffuse Later: Extrinsic Graph Guidance for Long-Horizon Diffusion Planning
• Abstract summary: Compositional diffusion models offer a promising route to long-horizon planning.<n>But enforcing local behavior over long chains is often insufficient for a coherent global structure to emerge.<n>Recent works tackle this limitation through intrinsic search, which explores multiple paths during the denoising process.
• Score: 44.52185127499181
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Compositional diffusion models offer a promising route to long-horizon planning by denoising multiple overlapping sub-trajectories while ensuring that together they constitute a global solution. However, enforcing local behavior over long chains is often insufficient for a coherent global structure to emerge. Recent works tackle this limitation through intrinsic search, which explores multiple paths during the denoising process. While intrinsic search improves global coherence, it comes at the cost of repeated evaluations of an already compute-heavy model. In this work, we argue that extrinsic search, performed outside the denoising process, offers a more effective mode of exploration for long-horizon planning while naturally enabling the use of classical algorithms to solve unseen combinatorial tasks at test time. Our eXtrinsic search-guided Diffuser (XDiffuser) first computes a plan over a state-space graph -- serving as a lightweight local connectivity oracle for the diffusion model. The plan is then used to guide denoising for a single trajectory, effectively offloading the burden of exploration. XDiffuser outperforms diffusion-based baselines on long-horizon tasks, with particularly large gains in the low-quality data regime and on unseen tasks beyond goal-reaching, including multi-agent coordination and TSP-style reasoning. Project website: https://yanivhass.github.io/XDiffuser-site/

Related papers

• Surprise Forcing: What to Remember, When to Skip in Long Video Generation [65.0022589149937]
  Streaming autoregressive diffusion makes minute-scale video synthesis practical, but its bounded context and fixed denoising schedule allocate resources uniformly.<n>We introduce Surprise Forcing, a training-free framework that treats both limitations as online resource-allocation problems.<n> Experiments on VBench, VBench-Long, and VBench-2.0 show that the proposed allocation strategy improves long-horizon consistency and visual quality while retaining real-time streaming throughput.
  arXiv  Detail & Related papers  (2026-07-20T18:37:58Z)
• Compositional Visual Planning via Inference-Time Diffusion Scaling [41.86377754505579]
  Diffusion models excel at short-horizon robot planning, yet scaling them to long-horizon tasks remains challenging due to computational constraints and limited training data.<n>We propose that the key to stable compositional generation lies in enforcing boundary agreement on the estimated clean data.<n>Our method formulates long-horizon planning as inference over a chain-structured factor graph of overlapping video chunks, where pretrained short-horizon video diffusion models provide local priors.
  arXiv  Detail & Related papers  (2026-03-03T06:24:06Z)
• Compositional Diffusion with Guided Search for Long-Horizon Planning [25.850015543620128]
  We propose Compositional Diffusion with Guided Search (CDGS) for compositional generative models.<n>Our method explores diverse combinations of local modes through population-based sampling, prunes infeasible candidates using likelihood-based filtering, and enforces global consistency through iterative resampling.<n>The approach generalizes across domains, enabling coherent text-guided panoramic images and long videos through effective local-to-global message passing.
  arXiv  Detail & Related papers  (2025-12-31T22:03:19Z)
• SparseD: Sparse Attention for Diffusion Language Models [98.05780626106555]
  diffusion language models (DLMs) offer a promising alternative to autoregressive models (ARs)<n>Existing open-source DLMs suffer from high inference latency.<n>We propose SparseD, a novel sparse attention method for DLMs.
  arXiv  Detail & Related papers  (2025-09-28T18:10:10Z)
• Tree-Guided Diffusion Planner [31.664192839205608]
  Planning with pretrained diffusion emerged as a promising approach for test-time guided control problems.<n>We propose a zero-time test-time planning framework that balances exploration and exploitation through structured trajectory generation.
  arXiv  Detail & Related papers  (2025-08-29T17:27:44Z)
• Inference-time Scaling of Diffusion Models through Classical Search [90.77272206228946]
  We propose a general framework that orchestrates local and global search to efficiently navigate the generative space.<n>We evaluate our approach on a range of challenging domains, including planning, offline reinforcement learning, and image generation.<n>These results show that classical search provides a principled and practical foundation for inference-time scaling in diffusion models.
  arXiv  Detail & Related papers  (2025-05-29T16:22:40Z)
• Extendable Long-Horizon Planning via Hierarchical Multiscale Diffusion [62.91968752955649]
  This paper tackles a novel problem, extendable long-horizon planning-enabling agents to plan trajectories longer than those in training data without compounding errors.<n>We propose an augmentation method that iteratively generates longer trajectories by stitching shorter ones.<n>HM-Diffuser trains on these extended trajectories using a hierarchical structure, efficiently handling tasks across multiple temporal scales.
  arXiv  Detail & Related papers  (2025-03-25T22:52:46Z)
• Dynamic Search for Inference-Time Alignment in Diffusion Models [87.35944312589424]
  We frame inference-time alignment in diffusion as a search problem and propose Dynamic Search for Diffusion (DSearch)<n>DSearch subsamples from denoising processes and approximates intermediate node rewards.<n>It also dynamically adjusts beam width and tree expansion to efficiently explore high-reward generations.
  arXiv  Detail & Related papers  (2025-03-03T20:32:05Z)
• Diffusion Meets Options: Hierarchical Generative Skill Composition for Temporally-Extended Tasks [12.239868705130178]
  We propose a data-driven hierarchical framework that generates and updates plans based on instruction specified by linear temporal logic (LTL) Our method decomposes temporal tasks into chain of options with hierarchical reinforcement learning from offline non-expert datasets. We devise a determinantal-guided posterior sampling technique during batch generation, which improves the speed and diversity of diffusion generated options.
  arXiv  Detail & Related papers  (2024-10-03T11:10:37Z)
• Dynamic Graph Learning Based on Hierarchical Memory for Origin-Destination Demand Prediction [12.72319550363076]
  This paper provides a dynamic graph representation learning framework for OD demands prediction. In particular, a hierarchical memory updater is first proposed to maintain a time-aware representation for each node. Atemporal propagation mechanism is provided to aggregate representations of neighbor nodes along a randomtemporal route. An objective function is designed to derive the future OD demands according to the most recent node.
  arXiv  Detail & Related papers  (2022-05-29T07:52:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.