用外部图搜索指导扩散模型，提升长时序规划的效率与泛化能力。
Plan First, Diffuse Later: Extrinsic Graph Guidance for Long-Horizon Diffusion Planning
- 先在状态图上做外置搜索生成计划，再引导扩散过程
- 在低质量数据和新任务上性能显著优于基线
- 适合需要泛化能力的复杂规划场景
组合式扩散模型通过去噪多个重叠子轨迹来实现长时序规划，但仅靠局部行为难以形成连贯全局结构。现有方法采用内在搜索，在去噪过程中探索多条路径，虽提升全局一致性，却需重复计算高成本模型。本文提出外置搜索机制，即在扩散过程外构建状态空间图并生成计划，作为轻量级局部连接参考。该计划用于引导单条轨迹的去噪，有效分担探索负担。XDiffuser在长时序任务中表现更优，尤其在低质量数据和未见任务（如多智能体协作、旅行商问题式推理）上提升显著。
原文摘要 · Abstract (English)
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/
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。