To deliver coherent and personalized experiences in long-term conversations, existing approaches typically perform retrieval augmented response generation by constructing memory banks from conversation history at either the turn-level, session-level, or through summarizationthis http URLthis paper, we present two key findings: (1) The granularity of memory unit matters: turn-level, session-level, and summarization-based methods each exhibit limitations in both memory retrieval accuracy and the semantic quality of the retrieved content. (2) Prompt compression methods, such as LLMLingua-2, can effectively serve as a denoising mechanism, enhancing memory retrieval accuracy across different granularities. Building on these insights, we propose SeCom, a method that constructs the memory bank at segment level by introducing a conversation segmentation model that partitions long-term conversations into topically coherent segments, while applying compression based denoising on memory units to enhance memory retrieval. Experimental results show that SeCom exhibits a significant performance advantage over baselines on long-term conversation benchmarks LOCOMO and Long-MT-Bench+. Additionally, the proposed conversation segmentation method demonstrates superior performance on dialogue segmentation datasets such as DialSeg711, TIAGE, and SuperDialSeg.
View on arXiv@article{pan2025_2502.05589,
title={ On Memory Construction and Retrieval for Personalized Conversational Agents },
author={ Zhuoshi Pan and Qianhui Wu and Huiqiang Jiang and Xufang Luo and Hao Cheng and Dongsheng Li and Yuqing Yang and Chin-Yew Lin and H. Vicky Zhao and Lili Qiu and Jianfeng Gao },
journal={arXiv preprint arXiv:2502.05589},
year={ 2025 }
}