Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.12285 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918445774274560 |
|---|---|
| author | Wu, Zhaofen Zhang, Hanrong Lin, Fulin Xu, Wujiang Xu, Xinran Chen, Yankai Zou, Henry Peng Chen, Shaowen Zhang, Weizhi Liu, Xue Yu, Philip S. Wang, Hongwei |
| author_facet | Wu, Zhaofen Zhang, Hanrong Lin, Fulin Xu, Wujiang Xu, Xinran Chen, Yankai Zou, Henry Peng Chen, Shaowen Zhang, Weizhi Liu, Xue Yu, Philip S. Wang, Hongwei |
| contents | To sustain coherent long-term interactions, Large Language Model (LLM) agents must navigate the tension between acquiring new information and retaining prior knowledge. Current unified stream-based memory systems facilitate context updates but remain vulnerable to interference from transient noise. Conversely, discrete structured memory architectures provide robust knowledge retention but often struggle to adapt to evolving narratives. To address this, we propose GAM, a hierarchical Graph-based Agentic Memory framework that explicitly decouples memory encoding from consolidation to effectively resolve the conflict between rapid context perception and stable knowledge retention. By isolating ongoing dialogue in an event progression graph and integrating it into a topic associative network only upon semantic shifts, our approach minimizes interference while preserving long-term consistency. Additionally, we introduce a graph-guided, multi-factor retrieval strategy to enhance context precision. Experiments on LoCoMo and LongDialQA indicate that our method consistently outperforms state-of-the-art baselines in both reasoning accuracy and efficiency. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_12285 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | GAM: Hierarchical Graph-based Agentic Memory for LLM Agents Wu, Zhaofen Zhang, Hanrong Lin, Fulin Xu, Wujiang Xu, Xinran Chen, Yankai Zou, Henry Peng Chen, Shaowen Zhang, Weizhi Liu, Xue Yu, Philip S. Wang, Hongwei Artificial Intelligence To sustain coherent long-term interactions, Large Language Model (LLM) agents must navigate the tension between acquiring new information and retaining prior knowledge. Current unified stream-based memory systems facilitate context updates but remain vulnerable to interference from transient noise. Conversely, discrete structured memory architectures provide robust knowledge retention but often struggle to adapt to evolving narratives. To address this, we propose GAM, a hierarchical Graph-based Agentic Memory framework that explicitly decouples memory encoding from consolidation to effectively resolve the conflict between rapid context perception and stable knowledge retention. By isolating ongoing dialogue in an event progression graph and integrating it into a topic associative network only upon semantic shifts, our approach minimizes interference while preserving long-term consistency. Additionally, we introduce a graph-guided, multi-factor retrieval strategy to enhance context precision. Experiments on LoCoMo and LongDialQA indicate that our method consistently outperforms state-of-the-art baselines in both reasoning accuracy and efficiency. |
| title | GAM: Hierarchical Graph-based Agentic Memory for LLM Agents |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2604.12285 |