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

• URL: http://arxiv.org/abs/2606.22488v1
• Date: Sun, 21 Jun 2026 13:16:10 GMT
• Title: SCOPE: Evolving Symbolic World for Planning in Open-Ended Environments
• Abstract summary: We introduce SCOPE, a self-adaptive symbolic planning framework that supports refining action plans and evolving the symbolic world.<n>SCOPE comprises two synergistic modules: a Symbolic Execution Simulator (SESim) that conducts symbolic validation and real execution of plans, and a Self-Adaptive Symbolic Memory (SASMem) that distills feedback into evolving symbolic knowledge.
• Score: 65.57374175987802
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• TodoEvolve: Learning to Architect Agent Planning Systems [68.48983335970901]
  TodoEvolve is a meta-planning paradigm that autonomously synthesizes and dynamically revises task-specific planning.<n>PlanFactory provides a common interface for heterogeneous planning patterns.<n>TodoEvolve consistently surpasses carefully engineered planning modules while maintaining economical API costs and runtime overhead.
  arXiv  Detail & Related papers  (2026-02-08T06:37:01Z)
• Wide-Horizon Thinking and Simulation-Based Evaluation for Real-World LLM Planning with Multifaceted Constraints [39.01715254437105]
  This paper introduces the Multiple Aspects of Planning (MAoP) to solve planning problems with multifaceted constraints.<n>Instead of direct planning, MAoP leverages the strategist to conduct pre-planning from various aspects and provide the planning blueprint for planners.
  arXiv  Detail & Related papers  (2025-06-14T09:37:59Z)
• Exploiting Symbolic Heuristics for the Synthesis of Domain-Specific Temporal Planning Guidance using Reinforcement Learning [51.54559117314768]
  Recent work investigated the use of Reinforcement Learning (RL) for the synthesis of guidance to improve the performance of temporal planners.<n>We propose an evolution of this learning and planning framework that focuses on exploiting the information provided by symbolics during both the RL and planning phases.
  arXiv  Detail & Related papers  (2025-05-19T17:19:13Z)
• Deliberate Planning in Language Models with Symbolic Representation [5.869782631289138]
  We introduce SymPlanner, a novel framework that equips large language models with structured planning capabilities.<n>Rather than relying purely on natural language reasoning, SymPlanner grounds the planning process in a symbolic state space.<n>Iterative Correction (IC) refines previously proposed actions by leveraging feedback from the symbolic environment.<n>Contrastive Ranking (CR) enables fine-grained comparison of candidate plans by evaluating them jointly.
  arXiv  Detail & Related papers  (2025-05-02T15:18:03Z)
• Seeing is Believing: Belief-Space Planning with Foundation Models as Uncertainty Estimators [34.28879194786174]
  Generalizable robotic mobile manipulation in open-world environments poses significant challenges due to long horizons, complex goals, and partial observability.<n>A promising approach to address these challenges involves planning with a library of parameterized skills, where a task planner sequences these skills to achieve goals specified in structured languages.<n>This paper introduces a novel framework that leverages vision-language models to estimate uncertainty and facilitate symbolic grounding.
  arXiv  Detail & Related papers  (2025-04-04T07:48:53Z)
• Learning for Long-Horizon Planning via Neuro-Symbolic Abductive Imitation [38.72920702089471]
  We introduce a novel framework textbfABductive textbfImitation textbfLearning (ABIL) that integrates data-driven learning and symbolic-based reasoning.<n>ABIL generates predicate candidates to facilitate the perception from raw observations to symbolic space without laborious predicate annotations.<n> Experiments show that our proposal successfully understands the observations with the task-relevant symbolics to assist the imitation learning.
  arXiv  Detail & Related papers  (2024-11-27T10:26:14Z)
• PDDLEGO: Iterative Planning in Textual Environments [56.12148805913657]
  Planning in textual environments has been shown to be a long-standing challenge even for current models. We propose PDDLEGO that iteratively construct a planning representation that can lead to a partial plan for a given sub-goal. We show that plans produced by few-shot PDDLEGO are 43% more efficient than generating plans end-to-end on the Coin Collector simulation.
  arXiv  Detail & Related papers  (2024-05-30T08:01:20Z)
• Planning as In-Painting: A Diffusion-Based Embodied Task Planning Framework for Environments under Uncertainty [56.30846158280031]
  Task planning for embodied AI has been one of the most challenging problems. We propose a task-agnostic method named 'planning as in-painting' The proposed framework achieves promising performances in various embodied AI tasks.
  arXiv  Detail & Related papers  (2023-12-02T10:07:17Z)
• Learning Concept-Based Causal Transition and Symbolic Reasoning for Visual Planning [36.131648635051334]
  Visual planning simulates how humans make decisions to achieve desired goals. We propose an interpretable and generalizable visual planning framework. We show that our framework can generalize to unseen task trajectories, unseen object categories, and real-world data.
  arXiv  Detail & Related papers  (2023-10-05T05:41:21Z)
• DREAMWALKER: Mental Planning for Continuous Vision-Language Navigation [107.5934592892763]
  We propose DREAMWALKER -- a world model based VLN-CE agent. The world model is built to summarize the visual, topological, and dynamic properties of the complicated continuous environment. It can simulate and evaluate possible plans entirely in such internal abstract world, before executing costly actions.
  arXiv  Detail & Related papers  (2023-08-14T23:45:01Z)
• Learning Type-Generalized Actions for Symbolic Planning [5.281449914031083]
  We propose a novel concept to generalize symbolic actions using a given entity hierarchy.<n>In a simulated grid-based kitchen environment, we show that type-generalized actions can be learned from few observations and generalize to novel situations.
  arXiv  Detail & Related papers  (2023-08-09T11:01:46Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.