Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2602.15313 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915929011519488 |
|---|---|
| author | Tang, Zihao Yu, Xin Xiao, Ziyu Wen, Zengxuan Li, Zelin Zhou, Jiaxi Wang, Hualei Wang, Haohua Huang, Haizhen Deng, Weiwei Sun, Feng Zhang, Qi |
| author_facet | Tang, Zihao Yu, Xin Xiao, Ziyu Wen, Zengxuan Li, Zelin Zhou, Jiaxi Wang, Hualei Wang, Haohua Huang, Haizhen Deng, Weiwei Sun, Feng Zhang, Qi |
| contents | AI Memory, specifically how models organizes and retrieves historical messages, becomes increasingly valuable to Large Language Models (LLMs), yet existing methods (RAG and Graph-RAG) primarily retrieve memory through similarity-based mechanisms. While efficient, such System-1-style retrieval struggles with scenarios that require global reasoning or comprehensive coverage of all relevant information. In this work, We propose Mnemis, a novel memory framework that integrates System-1 similarity search with a complementary System-2 mechanism, termed Global Selection. Mnemis organizes memory into a base graph for similarity retrieval and a hierarchical graph that enables top-down, deliberate traversal over semantic hierarchies. By combining the complementary strength from both retrieval routes, Mnemis retrieves memory items that are both semantically and structurally relevant. Mnemis achieves state-of-the-art performance across all compared methods on long-term memory benchmarks, scoring 93.9 on LoCoMo and 91.6 on LongMemEval-S using GPT-4.1-mini. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_15313 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Mnemis: Dual-Route Retrieval on Hierarchical Graphs for Long-Term LLM Memory Tang, Zihao Yu, Xin Xiao, Ziyu Wen, Zengxuan Li, Zelin Zhou, Jiaxi Wang, Hualei Wang, Haohua Huang, Haizhen Deng, Weiwei Sun, Feng Zhang, Qi Computation and Language AI Memory, specifically how models organizes and retrieves historical messages, becomes increasingly valuable to Large Language Models (LLMs), yet existing methods (RAG and Graph-RAG) primarily retrieve memory through similarity-based mechanisms. While efficient, such System-1-style retrieval struggles with scenarios that require global reasoning or comprehensive coverage of all relevant information. In this work, We propose Mnemis, a novel memory framework that integrates System-1 similarity search with a complementary System-2 mechanism, termed Global Selection. Mnemis organizes memory into a base graph for similarity retrieval and a hierarchical graph that enables top-down, deliberate traversal over semantic hierarchies. By combining the complementary strength from both retrieval routes, Mnemis retrieves memory items that are both semantically and structurally relevant. Mnemis achieves state-of-the-art performance across all compared methods on long-term memory benchmarks, scoring 93.9 on LoCoMo and 91.6 on LongMemEval-S using GPT-4.1-mini. |
| title | Mnemis: Dual-Route Retrieval on Hierarchical Graphs for Long-Term LLM Memory |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2602.15313 |