How Much Planning Is Enough? Reducing Search and Computation in World-Model Planning

2026-10-06

AI Summary

This study addresses the high computational overhead and low deployment efficiency caused by conservative budgets in visual world model planning by proposing SufficientPlan, a training-free framework. The core innovations include Pairwise Sequential Budget Certification (PSBC), which dynamically identifies task-varying sufficient budgets through closed-loop evidence, and Static Context Reuse (SCR), which enables cross-iteration caching to eliminate redundant computation. Together, these mechanisms adaptively reduce search budgets without modifying pretrained models. Experiments demonstrate that the proposed approach significantly decreases search costs and inference latency across multiple backbones and control tasks while maintaining highly competitive control performance.

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.

Problem

• visual world models
• planning budget
• deployment efficiency
• iterative planners
• computational redundancy

Innovation

• World-Model Planning
• Budget Certification
• Static-Context Reuse
• Visual Control
• Planning Efficiency