Saved in:
Bibliographic Details
Main Authors: Xu, Derong, Wen, Yi, Jia, Pengyue, Zhang, Yingyi, zhang, wenlin, Wang, Yichao, Guo, Huifeng, Tang, Ruiming, Zhao, Xiangyu, Chen, Enhong, Xu, Tong
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.19549
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915520720142336
author Xu, Derong
Wen, Yi
Jia, Pengyue
Zhang, Yingyi
zhang, wenlin
Wang, Yichao
Guo, Huifeng
Tang, Ruiming
Zhao, Xiangyu
Chen, Enhong
Xu, Tong
author_facet Xu, Derong
Wen, Yi
Jia, Pengyue
Zhang, Yingyi
zhang, wenlin
Wang, Yichao
Guo, Huifeng
Tang, Ruiming
Zhao, Xiangyu
Chen, Enhong
Xu, Tong
contents Large Language Models (LLMs) have recently been widely adopted in conversational agents. However, the increasingly long interactions between users and agents accumulate extensive dialogue records, making it difficult for LLMs with limited context windows to maintain a coherent long-term dialogue memory and deliver personalized responses. While retrieval-augmented memory systems have emerged to address this issue, existing methods often depend on single-granularity memory segmentation and retrieval. This approach falls short in capturing deep memory connections, leading to partial retrieval of useful information or substantial noise, resulting in suboptimal performance. To tackle these limits, we propose MemGAS, a framework that enhances memory consolidation by constructing multi-granularity association, adaptive selection, and retrieval. MemGAS is based on multi-granularity memory units and employs Gaussian Mixture Models to cluster and associate new memories with historical ones. An entropy-based router adaptively selects optimal granularity by evaluating query relevance distributions and balancing information completeness and noise. Retrieved memories are further refined via LLM-based filtering. Experiments on four long-term memory benchmarks demonstrate that MemGAS outperforms state-of-the-art methods on both question answer and retrieval tasks, achieving superior performance across different query types and top-K settings. \footnote{https://github.com/quqxui/MemGAS}
format Preprint
id arxiv_https___arxiv_org_abs_2505_19549
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle From Single to Multi-Granularity: Toward Long-Term Memory Association and Selection of Conversational Agents
Xu, Derong
Wen, Yi
Jia, Pengyue
Zhang, Yingyi
zhang, wenlin
Wang, Yichao
Guo, Huifeng
Tang, Ruiming
Zhao, Xiangyu
Chen, Enhong
Xu, Tong
Computation and Language
Large Language Models (LLMs) have recently been widely adopted in conversational agents. However, the increasingly long interactions between users and agents accumulate extensive dialogue records, making it difficult for LLMs with limited context windows to maintain a coherent long-term dialogue memory and deliver personalized responses. While retrieval-augmented memory systems have emerged to address this issue, existing methods often depend on single-granularity memory segmentation and retrieval. This approach falls short in capturing deep memory connections, leading to partial retrieval of useful information or substantial noise, resulting in suboptimal performance. To tackle these limits, we propose MemGAS, a framework that enhances memory consolidation by constructing multi-granularity association, adaptive selection, and retrieval. MemGAS is based on multi-granularity memory units and employs Gaussian Mixture Models to cluster and associate new memories with historical ones. An entropy-based router adaptively selects optimal granularity by evaluating query relevance distributions and balancing information completeness and noise. Retrieved memories are further refined via LLM-based filtering. Experiments on four long-term memory benchmarks demonstrate that MemGAS outperforms state-of-the-art methods on both question answer and retrieval tasks, achieving superior performance across different query types and top-K settings. \footnote{https://github.com/quqxui/MemGAS}
title From Single to Multi-Granularity: Toward Long-Term Memory Association and Selection of Conversational Agents
topic Computation and Language
url https://arxiv.org/abs/2505.19549