While Large Language Models (LLMs) have demonstrated strong zero-shot reasoning capabilities, their deployment as embodied agents still faces fundamental challenges in long-horizon planning. Unlike open-ended text generation, embodied agents must decompose high-level intent into actionable sub-goals while strictly adhering to the logic of a dynamic, observed environment. Standard LLM planners frequently fail to maintain strategy coherence over extended horizons due to context window limitation or hallucinate transitions that violate constraints. We propose GiG, a novel planning framework that structures embodied agents' memory using a Graph-in-Graph architecture. Our approach employs a Graph Neural Network (GNN) to encode environmental states into embeddings, organizing these embeddings into action-connected execution trace graphs within an experience memory bank. By clustering these graph embeddings, the framework enables retrieval of structure-aware priors, allowing agents to ground current decisions in relevant past structural patterns. Furthermore, we introduce a novel bounded lookahead module that leverages symbolic transition logic to enhance the agents' planning capabilities through the grounded action projection. We evaluate our framework on three embodied planning benchmarks-Robotouille Synchronous, Robotouille Asynchronous, and ALFWorld. Our method outperforms state-of-the-art baselines, achieving Pass@1 performance gains of up to 22% on Robotouille Synchronous, 37% on Asynchronous, and 15% on ALFWorld with comparable or lower computational cost.

翻译：尽管大型语言模型（LLM）已展现出强大的零样本推理能力，但其作为具身智能体的部署在长时程规划方面仍面临根本性挑战。与开放式文本生成不同，具身智能体必须将高层意图分解为可执行的子目标，同时严格遵循动态观测环境的逻辑。标准LLM规划器常因上下文窗口限制而难以在长时程中保持策略一致性，或产生违反约束的虚假状态转移。本文提出GiG，一种新颖的规划框架，通过图内图架构构建具身智能体的记忆系统。该方法利用图神经网络（GNN）将环境状态编码为嵌入向量，并将这些嵌入组织为行动关联的执行轨迹图，存储于经验记忆库中。通过对图嵌入进行聚类，该框架能够检索具有结构感知的先验知识，使智能体能够基于相关的历史结构模式进行当前决策。此外，我们引入了一种新颖的有界前瞻模块，该模块利用符号化转移逻辑，通过基于现实约束的行动推演来增强智能体的规划能力。我们在三个具身规划基准测试——Robotouille Synchronous、Robotouille Asynchronous和ALFWorld上评估了本框架。实验表明，我们的方法在计算成本相当或更低的条件下，显著优于现有先进基线模型，在Robotouille Synchronous上Pass@1指标提升达22%，在Asynchronous版本上提升37%，在ALFWorld上提升15%。