H$^2$R: Hierarchical Hindsight Reflection for Multi-Task LLM Agents
This addresses a bottleneck in multi-task LLM agents for AI researchers, offering an incremental improvement in knowledge transfer efficiency.
The paper tackles the problem of inefficient knowledge transfer in multi-task LLM agents by proposing a hierarchical memory architecture and a mechanism called Hierarchical Hindsight Reflection (H²R), which improves generalization and decision-making performance, outperforming baselines like Expel in benchmarks.
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.