arXiv cs.AI· Changbai Li, Sirui Li, Yichen Yang, Tongfei Chen, Zichao Feng, Shuwei Shao, Huobin Tan·· 10 天前AI 评分22
世界模型规划需要多少搜索预算？SufficientPlan 如何减少搜索与计算
How Much Planning Is Enough? Reducing Search and Computation in World-Model Planning
AI 导读
SufficientPlan 是一个无需修改预训练世界模型或规划器的部署框架，通过 Paired Sequential Budget Certification（PSBC）为每个模型—任务对搜索并认证一个更小的规划预算，并用 Static-Context Reuse（SCR）跨搜索迭代缓存观测与目标表示。
正文 · 原文
Abstract:Visual world models enable goal-directed control through decision-time action search, but their deployment efficiency is often limited by conservatively large planning budgets. We show that competitive task performance can be achieved without agreement with the Full-budget action, that sufficient budgets vary across model--task pairs, and that iterative planners repeatedly encode solve-invariant context. To address these inefficiencies, we propose {SufficientPlan}, a simple deployment framework that requires no modification to pretrained world models or planner updates. Its {Paired Sequential Budget Certification (PSBC)} component uses paired closed-loop evidence to search for and certify a reduced model--task-specific budget within a predefined Full-performance tolerance. Its {Static-Context Reuse (SCR)} component caches observation and goal representations across search iterations while preserving candidate-dependent planning and selected actions. Experiments across multiple world-model backbones and visual-control tasks show that SufficientPlan substantially reduces search budgets and planning latency while maintaining competitive control performance.
| Subjects: | Robotics (cs.RO); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.08350 [cs.RO] |
| (or arXiv:2610.08350v1 [cs.RO] for this version) | |
| https://doi.org/10.48550/arXiv.2610.08350 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Changbai Li [view email]
[v1]
Tue, 6 Oct 2026 13:40:44 UTC (792 KB)
来源：arXiv cs.AI · arxiv.org