SCOPE: Evolving Symbolic World for Planning in Open-Ended Environments

2026-06-21

AI Summary

In open-world settings, symbolic world representations derived from perception are often incomplete, severely limiting the performance of long-horizon plans generated by conventional symbolic planners. To address this challenge, this work proposes SCOPE, a novel framework that, for the first time, enables joint online co-evolution of symbolic planning and environmental representation. SCOPE integrates a symbolic execution simulator with an adaptive symbolic memory module, allowing action plans to be dynamically refined and the world model continuously improved through real execution feedback. This approach establishes a closed-loop system encompassing perception, planning, feedback, and evolution, substantially enhancing the completeness of symbolic representations, boosting planning success rates under perturbations, and enabling cross-task knowledge transfer and strong generalization capabilities.

Abstract

Recent works have explored integrating Vision-Language Models (VLMs) with classical planners that rely on symbolic representations of planning problems to generate long-horizon plans for complex embodied tasks. However, in open-ended environments, these symbolic representations obtained from perception are often incomplete, leading to suboptimal performance. To address this, we introduce SCOPE, a self-adaptive symbolic planning framework that supports refining action plans and evolving the symbolic world, i.e., the symbolic representations of open-ended environments. SCOPE comprises two synergistic modules: a Symbolic Execution Simulator (SESim) that conducts symbolic validation and real execution of action plans, leveraging the feedback to refine the plans and evolve the symbolic world; and a Self-Adaptive Symbolic Memory (SASMem) that further distills feedback into evolving symbolic knowledge to enhance long-horizon planning and modeling of the symbolic world. Experiments in open-ended environments show that SCOPE significantly improves the completeness of the symbolic world, the success rate of plans under environment perturbations, and cross-task grounding and adaptability across diverse embodied scenarios.

Problem

• symbolic representation
• open-ended environments
• incomplete perception
• long-horizon planning
• embodied tasks

Innovation

• symbolic planning
• open-ended environments
• self-adaptive framework
• symbolic world evolution
• Vision-Language Models