让规划模型全局思考，实现更长、更智能的路径生成
Compositional Monte Carlo Tree Diffusion for Extendable Planning
- 通过全局搜索计划组合，突破单条路径的局部限制
- 支持多起点并行探索，降低复杂度，提升效率
- 利用缓存计划图加速推理，适合长序列规划任务
蒙特卡洛树扩散（MCTD）将扩散模型与结构化树搜索结合，通过逐步推理实现有效轨迹探索。然而，MCTD在训练轨迹长度上存在根本局限。虽然周期性重规划可拼接轨迹生成更长计划，但规划过程仍局限于局部，因MCTD仅在单条轨迹内搜索，缺乏全局上下文。我们提出组合式蒙特卡洛树扩散（C-MCTD），将规划从单条轨迹优化提升至对完整计划组合的推理。C-MCTD引入三个互补组件：(1) 在线组合器，通过跨完整计划组合进行全局感知规划；(2) 分布式组合器，通过多起点并行探索降低搜索复杂度；(3) 预规划组合器，通过利用缓存的计划图加速推理。
原文摘要 · Abstract (English)
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.
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。