用图结构增强大模型规划能力，解决长任务中的幻觉与环境感知问题。
GraphThink: Graph-Enhanced LLM Thinking for Long-Horizon Embodied Task Planning
- 引入任务图与场景图，引导大模型分步思考并记忆环境状态。
- 在ALFRED基准上超越主流API式大模型，零样本和少样本表现优异。
- 适合需要长程规划与环境反馈的机器人任务研究者。
基于大模型的具身智能体在执行长周期任务时，常面临物理幻觉、泛化能力差和环境感知缺失的问题。本文提出GraphThink框架，通过任务图提供结构化知识以支持稳健规划，通过场景图维持环境记忆以实现事件驱动的重规划。具体而言，任务图通过上下文提示与迭代优化引导大模型思考，有效缓解规划幻觉；在GRPO框架下，任务图实现精细奖励设计，提升长周期任务规划能力并改善泛化性能。此外，基于场景图的事件驱动重规划模块实现了闭环环境感知与错误修正。GraphThink在ALFRED基准上达到当前最优性能，其高层规划器在验证集和未见的长周期任务上均超越领先的大模型系统，展现出强大的零样本与少样本能力。额外评估还证明其在新任务与新环境下的强分布外泛化能力。
原文摘要 · Abstract (English)
Embodied agents using LLM-based planners often struggle with physical hallucinations, poor generalization to long-horizon tasks, and lack of environmental awareness. We propose GraphThink, a novel framework that integrates a task graph to provide structured knowledge for robust planning and a scene graph to maintain environmental memory for event-driven replanning. Specifically, the task graph guides LLM thinking through contextual prompting and iterative refinement, effectively mitigating planning hallucinations. Furthermore, within the GRPO framework, the task graph offers delicate reward design to train the LLM planner, enhancing long-horizon planning capabilities and improving generalization. Finally, an event-driven replanning module, powered by the scene graph, enables closed-loop environment awareness and error correction. GraphThink achieves state-of-the-art performance on the ALFRED benchmark. In particular, our high-level planner surpasses leading API-based LLMs on both the validation set and held-out long-horizon tasks, underscoring its robust zero-shot and few-shot capabilities. Additional evaluations further demonstrate strong out-of-distribution generalization to novel tasks and environments.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。