H-Mem: A Novel Memory Mechanism for Evolving and Retrieving Agent Memory via a Hybrid Structure

TL;DR

H-Mem introduces a hybrid memory structure combining tree and graph models to effectively evolve and retrieve agent memory, significantly improving question-answering performance.

Contribution

It proposes a novel hybrid memory mechanism that models memory evolution over time and enhances retrieval efficiency in LLM-based agents.

Findings

H-Mem achieves state-of-the-art results on three agent memory benchmarks.

The hybrid structure effectively captures memory evolution and relationships.

Memory retrieval is significantly improved using the proposed approach.

Abstract

Memory data are ubiquitous in Large Language Model (LLM)-based agents (e.g., OpenClaw and Manus). A few recent works have attempted to exploit agents'memory for improving their performance on the question-answering (QA) task, but they lack a principled mechanism for effectively modeling how memory data evolves over time and retrieving memory data effectively, leading to poor performance in memory utilization. To fill this gap, we present H-Mem, a novel memory mechanism via a hybrid structure that can not only effectively model the evolution of agent memory over a long period of time, but also provide an efficient memory retrieval approach. Particularly, H-Mem builds a temporal and semantic tree structure that allows the short-term memory data to evolve progressively into long-term memory data, where the latter provides summarized information about the former, while simultaneously constructing a knowledge graph to capture the relationships between entities in memory. Moreover, it offers an effective memory retrieval approach by exploiting the hybrid structure of the tree and graph structures. Extensive experiments on three agent memory benchmarks show that H-Mem achieves state-of-the-art performance on the QA task.