让大模型智能体分层复盘经验，更精准地迁移知识。
H$^2$R: Hierarchical Hindsight Reflection for Multi-Task LLM Agents
- 将规划与执行记忆分离，实现分层知识管理
- 在双基准测试中优于基线模型，提升泛化能力
- 适合需要多任务推理的复杂智能体系统
基于大语言模型（LLM）的智能体在多任务场景中展现出强大潜力，因其具备跨任务知识迁移的能力。然而，现有方法常将过往经验视为整体单元，导致知识迁移效率低且粒度粗。本文提出一种新型分层记忆架构，通过解耦高层规划记忆与底层执行记忆，实现细粒度知识迁移。为此，我们引入分层事后反思（H²R）机制，从历史智能体-环境交互中提炼可复用的层级化知识。测试时，H²R分别检索高层与低层记忆，使智能体高效获取并利用相关知识完成新任务。在两个基准测试上的实验结果表明，H²R显著提升泛化与决策性能，优于如Expel等先前基线。
原文摘要 · Abstract (English)
Large language model (LLM)-based agents have shown strong potential in multi-task scenarios, owing to their ability to transfer knowledge across diverse tasks. However, existing approaches often treat prior experiences and knowledge as monolithic units, leading to inefficient and coarse-grained knowledge transfer. In this work, we propose a novel hierarchical memory architecture that enables fine-grained knowledge transfer by decoupling high-level planning memory from low-level execution memory. To construct and refine these hierarchical memories, we introduce Hierarchical Hindsight Reflection (H$^2$R), a mechanism that distills reusable and hierarchical knowledge from past agent-environment interactions. At test time, H$^2$R performs retrievals of high-level and low-level memories separately, allowing LLM-based agents to efficiently access and utilize task-relevant knowledge for new tasks.Experimental results across two benchmarks demonstrate that H$^2$R can improve generalization and decision-making performance, outperforming prior baselines such as Expel.
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。