[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tag-hierarchical-planning":3},{"tag":4,"articles":11},{"id":5,"name":6,"slug":7,"article_count":8,"description_zh":9,"description_en":10},"c8a7ecde-73c8-4d7e-9f30-bf278d24dc70","hierarchical planning","hierarchical-planning",3,"階層式規劃把長時序任務拆成多層決策，常見於世界模型、機器人控制與多模態代理。重點在降低搜尋成本、提升穩定性，並讓模型在複雜環境中更容易做出一致的長期行動。","Hierarchical planning breaks long-horizon tasks into layered decisions, often in latent world models, robot control, and agentic web generation. It matters because it can reduce search cost, improve stability, and make long-term actions more consistent in complex environments.",[12],{"id":13,"slug":14,"title":15,"summary":16,"category":17,"image_url":18,"cover_image":18,"language":19,"created_at":20},"5e1d7109-dea2-4002-8e74-bf6331f46c05","hierarchical-planning-latent-world-models-en","Hierarchical Planning Cuts World-Model Search Cost","A hierarchical latent world-model planner improves long-horizon control and cuts planning compute, with zero-shot gains on real robots.","research","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1775455787999-4nzg.png","en","2026-04-06T06:09:31.947292+00:00"]