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

Recent works have explored integrating Vision-Language Models (VLMs) with classical planners that rely on symbolic representations of planning problem 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—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.

Robots and AI agents often need to complete everyday tasks in environments that are not fully known in advance. A common problem is that an agent may start with an incomplete understanding of the scene, so a plan that looks reasonable can fail when an object is missing, has moved, or cannot be used in the expected way. This paper introduces SCOPE, a system that helps an agent check its plan, try actions, learn from failures, and update its understanding of the environment over time. It also keeps reusable lessons from past tasks so that future plans can be corrected more efficiently. In simulated household environments, SCOPE helps agents complete longer tasks more reliably when the environment changes or contains new task-relevant information.