Elamur Research⌕
☰
home / papers / 2025 / In Prospect and Retrospect: Reflective Memory Management for Long-term Personalized Dialogue Agents

In Prospect and Retrospect: Reflective Memory Management for Long-term Personalized Dialogue Agents

Paper · 2025 · Zhen Tan, Jun Yan, I-Hung Hsu et al.

Summary

LLM dialogue agents keep no state between sessions, so long-term personalization depends on external memory. The authors identify two weaknesses in existing memory systems. First, they split history into fixed units such as turns or sessions, which ignore where topics actually begin and end. Second, they rely on static retrievers that cannot adapt to different users or domains, and labeled data for training personalized retrievers is expensive.

They propose Reflective Memory Management (RMM), which has two parts:

  • Prospective Reflection runs when a session ends. It extracts topic-level summaries, each paired with the raw dialogue segment, and either adds them to the memory bank or merges them into related existing entries.
  • Retrospective Reflection places a lightweight reranker after the retriever and trains it online with reinforcement learning. The training signal is which memories the LLM cites while answering, so no manual labels are needed.

On MSC and LongMemEval, RMM beats the strongest baseline by more than 5% on retrieval and generation metrics. On LongMemEval it gains over 10% accuracy compared with a memory-free baseline. This matters for assistants that must recall user facts, such as allergies, across many sessions.

Key points

  • Memory bank design: each entry is a pair of topic summary and raw dialogue, and the summary serves as the retrieval key. The pipeline is retriever → reranker → LLM, with the reranker updated from the LLM's citation feedback.
  • Retriever settings (LongMemEval, Table 6): with GTE, RMM reaches Recall@5 of 69.8% and accuracy of 70.4% at Top-K=20/Top-M=5. At Top-K=50/Top-M=10 these rise to 74.4% and 73.8%. Contriever and Stella were also tested, and stronger retrievers gain more.
  • MSC results (Gemini-1.5-Flash): RMM scores 30.8 METEOR, 55.4 BERTScore and 69.7% LLM-as-a-judge "Yes", versus 14.8, 31.9 and 25.4% for the long-context baseline. The judge was Gemini-1.5-Pro.
  • Human check of the LLM judge: on 100 MSC samples, Cohen's κ was 0.82 between the two human annotators, and 0.71 and 0.69 between the LLM judge and each human.
  • Granularity and pretraining: topic-based Prospective Reflection comes close to an oracle that picks the best granularity for each instance. Offline supervised contrastive pretraining of GTE on a small labeled set further improves recall and accuracy.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Fields, topics and concepts

📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 works

🧭 Topics 1Research subjects and languages the work is about.Dialogue systems · 624 works

Cite

Cite as Zhen Tan, Jun Yan, I-Hung Hsu, Rujun Han, Zifeng Wang, Long Le, Yiwen Song, Yanfei Chen, Hamid Palangi, George Lee, Anand Rajan Iyer, Tianlong Chen, Huan Liu, Chen-Yu Lee and Tomas Pfister. 2025. In Prospect and Retrospect: Reflective Memory Management for Long-term Personalized Dialogue Agents. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2025.acl-long.413

@inproceedings{tan2025prospect,
  title = {{In Prospect and Retrospect: Reflective Memory Management for Long-term Personalized Dialogue Agents}},
  author = {Zhen Tan, Jun Yan, I-Hung Hsu, Rujun Han, Zifeng Wang, Long Le, Yiwen Song, Yanfei Chen, Hamid Palangi, George Lee, Anand Rajan Iyer, Tianlong Chen, Huan Liu, Chen-Yu Lee and Tomas Pfister},
  booktitle = {Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2025},
  doi = {10.18653/v1/2025.acl-long.413},
  url = {https://doi.org/10.18653/v1/2025.acl-long.413}
}

References

53 references, 15 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Sanghwan Bae, Donghyun Kwak, Soyoung Kang, Min Young Lee, Sungdong Kim, Yuin Jeong, Hyeri Kim, Sang-Woo Lee, Woomyoung Park, and Nako Sung. 2022. Keep me updated! memory management in long-term conversations. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 3769–3787,… find
  2. Satanjeev Banerjee and Alon Lavie. 2005. METEOR: An automatic metric for MT evaluation with improved correlation with human judgments. In Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and/or Summarization, pages 65–72, Ann Arbor, Michigan. Ass…
  3. Jan Buchmann, Xiao Liu, and Iryna Gurevych. 2024. Attribute or abstain: Large language models as long document assistants. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 8113–8140, Miami, Florida, USA. Association for Computational Linguistics. find
  4. Jin Chen, Zheng Liu, Xu Huang, Chenwang Wu, Qi Liu, Gangwei Jiang, Yuanhao Pu, Yuxuan Lei, Xiaolong Chen, Xingmei Wang, Kai Zheng, Defu Lian, and Enhong Chen. 2024. When large language models meet personalization: perspectives of challenges and opportunities. World Wide Web, 27(4). find
  5. Prateek Chhikara, Dev Khant, Saket Aryan, Taranjeet Singh, and Deshraj Yadav. 2025. Mem0: Building production-ready ai agents with scalable long-term memory. Preprint, arXiv:2504.19413.
  6. Yijiang River Dong, Tiancheng Hu, and Nigel Collier. 2024. Can LLM be a personalized judge? In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 10126–10141, Miami, Florida, USA. Association for Computational Linguistics. find
  7. Yanchu Guan, Dong Wang, Zhixuan Chu, Shiyu Wang, Feiyue Ni, Ruihua Song, and Chenyi Zhuang. 2024. Intelligent agents with llm-based process automation. In Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD ’24, page 5018–5027, New York, NY, USA. Association for… find
  8. E.J. Gumbel. 1954. Statistical Theory of Extreme Values and Some Practical Applications: A Series of Lectures. Applied mathematics series. U.S. Government Printing Office. find
  9. Gautier Izacard, Mathilde Caron, Lucas Hosseini, Sebastian Riedel, Piotr Bojanowski, Armand Joulin, and Edouard Grave. 2022. Unsupervised dense information retrieval with contrastive learning. Transactions on Machine Learning Research.
  10. Eric Jang, Shixiang Gu, and Ben Poole. 2017. Categorical reparameterization with gumbel-softmax. In 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24-26, 2017, Conference Track Proceedings. OpenReview.net.
  11. Zhouyu Jiang, Mengshu Sun, Lei Liang, and Zhiqiang Zhang. 2024. Retrieve, summarize, plan: Advancing multi-hop question answering with an iterative approach. ArXiv preprint, abs/2407.13101. — [arXiv:2407.13101](https://arxiv.org/abs/2407.13101) find
  12. Krishnaram Kenthapadi, Mehrnoosh Sameki, and Ankur Taly. 2024. Grounding and evaluation for large language models: Practical challenges and lessons learned (survey). In Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD ’24, page 6523–6533, New York, NY, USA. A… find
  13. Seo Hyun Kim, Kai Tzu-iunn Ong, Taeyoon Kwon, Namyoung Kim, Keummin Ka, SeongHyeon Bae, Yohan Jo, Seung-won Hwang, Dongha Lee, and Jinyoung Yeo. 2024. Theanine: Revisiting memory management in long-term conversations with timeline-augmented response generation. ArXiv preprint, abs/2406.10996. — [arXiv:2406.10996](https://arxiv.org/abs/2406.10996) find
  14. Saydulu Kolasani. 2023. Optimizing natural language processing, large language models (llms) for efficient customer service, and hyper-personalization to enable sustainable growth and revenue. Transactions on Latest Trends in Artificial Intelligence, 4(4). find
  15. Gibbeum Lee, Volker Hartmann, Jongho Park, Dimitris Papailiopoulos, and Kangwook Lee. 2023. Prompted LLMs as chatbot modules for long open-domain conversation. In Findings of the Association for Computational Linguistics: ACL 2023, pages 4536–4554, Toronto, Canada. Association for Computational Ling… find
  16. Hao Li, Chenghao Yang, An Zhang, Yang Deng, Xiang Wang, and Tat-Seng Chua. 2024a. Hello again! llm-powered personalized agent for long-term dialogue. ArXiv preprint, abs/2406.05925.
  17. Huayang Li, Pat Verga, Priyanka Sen, Bowen Yang, Vijay Viswanathan, Patrick Lewis, Taro Watanabe, and Yixuan Su. 2024b. Alr 2 : A retrieve-then-reason framework for long-context question answering. ArXiv preprint, abs/2410.03227. — [arXiv:2410.03227](https://arxiv.org/abs/2410.03227) find
  18. Yuanchun Li, Hao Wen, Weijun Wang, Xiangyu Li, Yizhen Yuan, Guohong Liu, Jiacheng Liu, Wenxing Xu, Xiang Wang, Yi Sun, et al. 2024c. Personal llm agents: Insights and survey about the capability, efficiency and security. ArXiv preprint, abs/2401.05459. find
  19. Yucheng Li, Huiqiang Jiang, Qianhui Wu, Xufang Luo, Surin Ahn, Chengruidong Zhang, Amir H Abdi, Dongsheng Li, Jianfeng Gao, Yuqing Yang, et al. 2024d. Scbench: A kv cache-centric analysis of long-context methods. ArXiv preprint, abs/2412.10319. — [arXiv:2412.10319](https://arxiv.org/abs/2412.10319) find
  20. Zehan Li, Xin Zhang, Yanzhao Zhang, Dingkun Long, Pengjun Xie, and Meishan Zhang. 2023. Towards general text embeddings with multi-stage contrastive learning. ArXiv preprint, abs/2308.03281.
  21. Hao Liu, Matei Zaharia, and Pieter Abbeel. 2024a. Ringattention with blockwise transformers for near-infinite context. In The Twelfth International Conference on Learning Representations. find
  22. Nelson F. Liu, Kevin Lin, John Hewitt, Ashwin Paranjape, Michele Bevilacqua, Fabio Petroni, and Percy Liang. 2024b. Lost in the middle: How language models use long contexts. Transactions of the Association for Computational Linguistics, 12:157–173.
  23. Xiang Liu, Zhenheng Tang, Peijie Dong, Zeyu Li, Bo Li, Xuming Hu, and Xiaowen Chu. 2025. Chunkkv: Semantic-preserving kv cache compression for efficient long-context llm inference. ArXiv preprint, abs/2502.00299. find
  24. Junru Lu, Siyu An, Mingbao Lin, Gabriele Pergola, Yulan He, Di Yin, Xing Sun, and Yunsheng Wu. 2023. Memochat: Tuning llms to use memos for consistent long-range open-domain conversation. ArXiv preprint, abs/2308.08239. — [arXiv:2308.08239](https://arxiv.org/abs/2308.08239) find
  25. Chris J Maddison, Daniel Tarlow, and Tom Minka. 2014. A* sampling. In Advances in Neural Information Processing Systems, volume 27. Curran Associates, Inc. find
  26. Adyasha Maharana, Dong-Ho Lee, Sergey Tulyakov, Mohit Bansal, Francesco Barbieri, and Yuwei Fang. 2024. Evaluating very long-term conversational memory of LLM agents. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 13851–13870… find
  27. Michael McCloskey and Neal J. Cohen. 1989. Catastrophic interference in connectionist networks: The sequential learning problem. volume 24 of Psychology of Learning and Motivation, pages 109–165. Academic Press. find
  28. John Mendonça, Alon Lavie, and Isabel Trancoso. 2024. On the benchmarking of LLMs for open-domain dialogue evaluation. In Proceedings of the 6th Workshop on NLP for Conversational AI (NLP4ConvAI 2024), pages 1–12, Bangkok, Thailand. Association for Computational Linguistics. find
  29. Charles Packer, Sarah Wooders, Kevin Lin, Vivian Fang, Shishir G. Patil, Ion Stoica, and Joseph E. Gonzalez. 2024. Memgpt: Towards llms as operating systems. Preprint, arXiv:2310.08560. find
  30. Zhuoshi Pan, Qianhui Wu, Huiqiang Jiang, Xufang Luo, Hao Cheng, Dongsheng Li, Yuqing Yang, Chin-Yew Lin, H. Vicky Zhao, Lili Qiu, and Jianfeng Gao. 2025. Secom: On memory construction and retrieval for personalized conversational agents. In The Thirteenth International Conference on Learning Represe… find
  31. Jiahuan Pei, Pengjie Ren, and Maarten de Rijke. 2021. A cooperative memory network for personalized task-oriented dialogue systems with incomplete user profiles. In WWW ’21: The Web Conference 2021, Virtual Event / Ljubljana, Slovenia, April 19-23, 2021, pages 1552–1561. ACM / IW3C2. find
  32. Preston Rasmussen, Pavlo Paliychuk, Travis Beauvais, Jack Ryan, and Daniel Chalef. 2025. Zep: A temporal knowledge graph architecture for agent memory. Preprint, arXiv:2501.13956. find
  33. Freda Shi, Xinyun Chen, Kanishka Misra, Nathan Scales, David Dohan, Ed H. Chi, Nathanael Schärli, and Denny Zhou. 2023. Large language models can be easily distracted by irrelevant context. In International Conference on Machine Learning, ICML 2023, 23-29 July 2023, Honolulu, Hawaii, USA, volume 202…
  34. Yu-Min Tseng, Yu-Chao Huang, Teng-Yun Hsiao, Wei-Lin Chen, Chao-Wei Huang, Yu Meng, and Yun-Nung Chen. 2024. Two tales of persona in LLMs: A survey of role-playing and personalization. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 16612–16631, Miami, Florida, USA. A…
  35. Marilyn A. Walker, Diane J. Litman, Candace A. Kamm, and Alicia Abella. 1997. PARADISE: A framework for evaluating spoken dialogue agents. In 35th Annual Meeting of the Association for Computational Linguistics and 8th Conference of the European Chapter of the Association for Computational Linguisti…
  36. Qingyue Wang, Liang Ding, Yanan Cao, Zhiliang Tian, Shi Wang, Dacheng Tao, and Li Guo. 2023. Recursively summarizing enables long-term dialogue memory in large language models. ArXiv preprint, abs/2308.15022. — [arXiv:2308.15022](https://arxiv.org/abs/2308.15022) find
  37. Zora Zhiruo Wang, Jiayuan Mao, Daniel Fried, and Graham Neubig. 2024. Agent workflow memory. Preprint, arXiv:2409.07429.
  38. Joseph Weizenbaum. 1966. Eliza—a computer program for the study of natural language communication between man and machine. Commun. ACM, 9(1):36–45. find
  39. Qingsong Wen, Jing Liang, Carles Sierra, Rose Luckin, Richard Tong, Zitao Liu, Peng Cui, and Jiliang Tang. 2024. Ai for education (ai4edu): Advancing personalized education with llm and adaptive learning. In Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD ’2… find
  40. S. Whittaker, Q. Jones, and L. Terveen. 2002. Managing long term communications: conversation and contact management. In Proceedings of the 35th Annual Hawaii International Conference on System Sciences, pages 1070–1079. find
  41. Michael David Williams and James D. Hollan. 1981. The process of retrieval from very long-term memory. Cognitive Science, 5(2):87–119. find
  42. Ronald J. Williams. 1992. Simple statistical gradient-following algorithms for connectionist reinforcement learning. Mach. Learn., 8(3–4):229–256. find
  43. Di Wu, Hongwei Wang, Wenhao Yu, Yuwei Zhang, Kai-Wei Chang, and Dong Yu. 2024. Longmemeval: Benchmarking chat assistants on long-term interactive memory. ArXiv preprint, abs/2410.10813.
  44. Jing Xu, Arthur Szlam, and Jason Weston. 2022. Beyond goldfish memory: Long-term open-domain conversation. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 5180–5197, Dublin, Ireland. Association for Computational Linguistics. find
  45. Wujiang Xu, Kai Mei, Hang Gao, Juntao Tan, Zujie Liang, and Yongfeng Zhang. 2025. Amem: Agentic memory for llm agents. Preprint, arXiv:2502.12110.
  46. Chiyu Zhang, Yifei Sun, Jun Chen, Jie Lei, Muhammad Abdul-Mageed, Sinong Wang, Rong Jin, Sem Park, Ning Yao, and Bo Long. 2024a. Spar: Personalized content-based recommendation via long engagement attention. ArXiv preprint, abs/2402.10555. — [arXiv:2402.10555](https://arxiv.org/abs/2402.10555) find
  47. Dun Zhang, Jiacheng Li, Ziyang Zeng, and Fulong Wang. 2024b. Jasper and stella: distillation of sota embedding models. ArXiv preprint, abs/2412.19048. — [arXiv:2412.19048](https://arxiv.org/abs/2412.19048) find
  48. Tianyi Zhang, Varsha Kishore, Felix Wu, Kilian Q. Weinberger, and Yoav Artzi. 2020. Bertscore: Evaluating text generation with BERT. In 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26-30, 2020. OpenReview.net. find
  49. Zhehao Zhang, Ryan A Rossi, Branislav Kveton, Yijia Shao, Diyi Yang, Hamed Zamani, Franck Dernoncourt, Joe Barrow, Tong Yu, Sungchul Kim, et al. 2024c. Personalization of large language models: A survey. ArXiv preprint, abs/2411.00027.
  50. Zheyuan Zhang, Daniel Zhang-Li, Jifan Yu, Linlu Gong, Jinchang Zhou, Zhiyuan Liu, Lei Hou, and Juanzi Li. 2024d. Simulating classroom education with llm-empowered agents. ArXiv preprint, abs/2406.19226.
  51. Liang Zhao, Xiachong Feng, Xiaocheng Feng, Weihong Zhong, Dongliang Xu, Qing Yang, Hongtao Liu, Bing Qin, and Ting Liu. 2024. Length extrapolation of transformers: A survey from the perspective of positional encoding. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 99… find
  52. Chuanyang Zheng, Yihang Gao, Han Shi, Minbin Huang, Jingyao Li, Jing Xiong, Xiaozhe Ren, Michael Ng, Xin Jiang, Zhenguo Li, and Yu Li. 2024. Dape: Data-adaptive positional encoding for length extrapolation. In Advances in Neural Information Processing Systems, volume 37, pages 26659–26700. Curran As… find
  53. Wanjun Zhong, Lianghong Guo, Qiqi Gao, He Ye, and Yanlin Wang. 2024. Memorybank: Enhancing large language models with long-term memory. In Thirty-Eighth AAAI Conference on Artificial Intelligence, AAAI 2024, Thirty-Sixth Conference on Innovative Applications of Artificial Intelligence, IAAI 2024, Fo… find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/tan-2025-prospect-retrospect-reflective-memory-management/