Saved in:
| Main Authors: | , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2503.08026 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911078942769152 |
|---|---|
| author | Tan, Zhen Yan, Jun Hsu, I-Hung Han, Rujun Wang, Zifeng Le, Long T. Song, Yiwen Chen, Yanfei Palangi, Hamid Lee, George Iyer, Anand Chen, Tianlong Liu, Huan Lee, Chen-Yu Pfister, Tomas |
| author_facet | Tan, Zhen Yan, Jun Hsu, I-Hung Han, Rujun Wang, Zifeng Le, Long T. Song, Yiwen Chen, Yanfei Palangi, Hamid Lee, George Iyer, Anand Chen, Tianlong Liu, Huan Lee, Chen-Yu Pfister, Tomas |
| contents | Large Language Models (LLMs) have made significant progress in open-ended dialogue, yet their inability to retain and retrieve relevant information from long-term interactions limits their effectiveness in applications requiring sustained personalization. External memory mechanisms have been proposed to address this limitation, enabling LLMs to maintain conversational continuity. However, existing approaches struggle with two key challenges. First, rigid memory granularity fails to capture the natural semantic structure of conversations, leading to fragmented and incomplete representations. Second, fixed retrieval mechanisms cannot adapt to diverse dialogue contexts and user interaction patterns. In this work, we propose Reflective Memory Management (RMM), a novel mechanism for long-term dialogue agents, integrating forward- and backward-looking reflections: (1) Prospective Reflection, which dynamically summarizes interactions across granularities-utterances, turns, and sessions-into a personalized memory bank for effective future retrieval, and (2) Retrospective Reflection, which iteratively refines the retrieval in an online reinforcement learning (RL) manner based on LLMs' cited evidence. Experiments show that RMM demonstrates consistent improvement across various metrics and benchmarks. For example, RMM shows more than 10% accuracy improvement over the baseline without memory management on the LongMemEval dataset. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_08026 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | In Prospect and Retrospect: Reflective Memory Management for Long-term Personalized Dialogue Agents Tan, Zhen Yan, Jun Hsu, I-Hung Han, Rujun Wang, Zifeng Le, Long T. Song, Yiwen Chen, Yanfei Palangi, Hamid Lee, George Iyer, Anand Chen, Tianlong Liu, Huan Lee, Chen-Yu Pfister, Tomas Computation and Language Artificial Intelligence Large Language Models (LLMs) have made significant progress in open-ended dialogue, yet their inability to retain and retrieve relevant information from long-term interactions limits their effectiveness in applications requiring sustained personalization. External memory mechanisms have been proposed to address this limitation, enabling LLMs to maintain conversational continuity. However, existing approaches struggle with two key challenges. First, rigid memory granularity fails to capture the natural semantic structure of conversations, leading to fragmented and incomplete representations. Second, fixed retrieval mechanisms cannot adapt to diverse dialogue contexts and user interaction patterns. In this work, we propose Reflective Memory Management (RMM), a novel mechanism for long-term dialogue agents, integrating forward- and backward-looking reflections: (1) Prospective Reflection, which dynamically summarizes interactions across granularities-utterances, turns, and sessions-into a personalized memory bank for effective future retrieval, and (2) Retrospective Reflection, which iteratively refines the retrieval in an online reinforcement learning (RL) manner based on LLMs' cited evidence. Experiments show that RMM demonstrates consistent improvement across various metrics and benchmarks. For example, RMM shows more than 10% accuracy improvement over the baseline without memory management on the LongMemEval dataset. |
| title | In Prospect and Retrospect: Reflective Memory Management for Long-term Personalized Dialogue Agents |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2503.08026 |