# Compositional Diffusion with Guided Search for Long-Horizon Planning

arXiv: https://arxiv.org/abs/2601.00126 · HTML: https://mlsanity.com/paper/2601.00126/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Dec 2025.

## Built on by (most cited first, 8 of 8)

- [Refining Compositional Diffusion for Reliable Long-Horizon Planning](https://mlsanity.com/paper/2605.03075/) (2026)
- [PaperFit: Vision-in-the-Loop Typesetting Optimization for Scientific Documents](https://mlsanity.com/paper/2605.10341/) (2026)
- [Asynchronous Multimodal Diffusion Policy Composition via Latency-Aware Guidance Fusion](https://mlsanity.com/paper/2607.17257/) (2026)
- [Delta-K: Boosting Multi-Instance Generation via Cross-Attention Augmentation](https://mlsanity.com/paper/2603.10210/) (2026)
- [Plan First, Diffuse Later: Extrinsic Graph Guidance for Long-Horizon Diffusion Planning](https://mlsanity.com/paper/2605.16863/) (2026)
- [Coarse-to-Fine Compositional Diffusion for Long-Horizon Planning](https://mlsanity.com/paper/2606.00837/) (2026)
- [ChronoForest: Closed-Loop Multi-Tree Diffusion Planning for Efficient Bridge Search and Route Composition](https://mlsanity.com/paper/2606.06618/) (2026)
- [Terminal Symmetry as a Carrier of Asymmetric Process Knowledge: Statewise Refinement for Anytime Verified Construction](https://mlsanity.com/paper/2608.11318/) (2026)

## Abstract (arXiv)

Generative models have emerged as powerful tools for planning, with compositional approaches offering particular promise for modeling long-horizon task distributions by composing together local, modular generative models. This compositional paradigm spans diverse domains, from multi-step manipulation planning to panoramic image synthesis to long video generation. However, compositional generative models face a critical challenge: when local distributions are multimodal, existing composition methods average incompatible modes, producing plans that are neither locally feasible nor globally coherent. We propose Compositional Diffusion with Guided Search (CDGS), which addresses this mode averaging problem by embedding search directly within the diffusion denoising process. 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 between overlapping segments. CDGS matches oracle performance on seven robot manipulation tasks, outperforming baselines that lack compositionality or require long-horizon training data. The approach generalizes across domains, enabling coherent text-guided panoramic images and long videos through effective local-to-global message passing. More details: https://cdgsearch.github.io/