Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.15701 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917499519369216 |
|---|---|
| author | Yu, Jiawei Fang, Yixiang Liu, Xilin Ma, Yuchi |
| author_facet | Yu, Jiawei Fang, Yixiang Liu, Xilin Ma, Yuchi |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_15701 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | H-Mem: A Novel Memory Mechanism for Evolving and Retrieving Agent Memory via a Hybrid Structure Yu, Jiawei Fang, Yixiang Liu, Xilin Ma, Yuchi Computation and Language Artificial Intelligence 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. |
| title | H-Mem: A Novel Memory Mechanism for Evolving and Retrieving Agent Memory via a Hybrid Structure |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2605.15701 |