让大模型用粗细结合的记忆增强规划能力，应对环境变化更灵活。
Coarse-to-Fine Grounded Memory for LLM Agent Planning
- 用粗粒度焦点点和细粒度提示构建分层记忆
- 训练时收集经验，推理时检索相关记忆支持决策
- 能动态识别异常并自我反思修正计划
大语言模型（LLM）在复杂规划任务中的应用日益广泛。为避免昂贵的训练成本，现有方法多采用记忆机制，通过离线经验或在线轨迹分析增强模型能力。然而，这些方法依赖单一粒度的记忆，受限于采集经验的质量，导致知识多样性与规划灵活性不足。本文提出一种新的粗到细具身记忆框架（Coarse-to-Fine Grounded Memory），将环境信息以粗粒度焦点点形式具象化，指导训练阶段的经验收集，并从每段经验中提取可操作的混合粒度提示。推理阶段，系统检索相关经验与提示以支持规划。当遇到环境异常时，模型可将当前状态具象为细粒度关键信息，实现灵活的自我问答式反思与计划修正。
原文摘要 · Abstract (English)
Recent advancements in Large Language Models (LLMs) have driven growing interest in LLM-based agents for complex planning tasks. To avoid costly agent training, many studies adopted memory mechanism that enhances LLM with offline experiences or online trajectory analysis. However, existing works focus on single-granularity memory derived from dynamic environmental interactions, which are inherently constrained by the quality of the collected experiences. This limitation, in turn, constrain the diversity of knowledge and the flexibility of planning. We propose Coarse-to-Fine Grounded Memory (\Ours{}), a novel framework that grounds coarse-to-fine memories with LLM, thereby fully leverage them for flexible adaptation to diverse scenarios. \Ours{} grounds environmental information into coarse-grained focus points to guide experience collection in training tasks, followed by grounding of actionable hybrid-grained tips from each experience. At inference, \Ours{} retrieves task-relevant experiences and tips to support planning. When facing environmental anomalies, the LLM grounds the current situation into fine-grained key information, enabling flexible self-QA reflection and plan correction.
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。