---
title: "Structured Episodic Event Memory — paper by Lu et al. (2026)"
description: "The authors propose SEEM (Structured Episodic Event Memory), a two-layer memory for long-running dialogue agents: Graph… 28 references."
authors: ["Zhengxuan Lu", "Dongfang Li", "Yukun Shi", "Beilun Wang", "Longyue Wang", "Baotian Hu"]
year: 2026
venue: "Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)"
source: "https://aclanthology.org/2026.acl-long.277/"
doi: "10.18653/v1/2026.acl-long.277"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/lu-2026-structured-episodic-event-memory/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/lu-2026-structured-episodic-event-memory/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/43/) / Structured Episodic Event Memory

# Structured Episodic Event Memory

**Authors:** Zhengxuan Lu, [Dongfang Li](https://md.research.elamur.ai/free/en/authors/dongfang-li/), Yukun Shi, Beilun Wang, [Longyue Wang](https://md.research.elamur.ai/free/en/authors/longyue-wang/) and [Baotian Hu](https://md.research.elamur.ai/free/en/authors/baotian-hu/) · **Year:** 2026 · **Venue:** [Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)](https://md.research.elamur.ai/free/en/venues/acl/) ([ACL 2026](https://md.research.elamur.ai/free/en/venues/acl/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.acl-long.277/) · [PDF](https://aclanthology.org/2026.acl-long.277.pdf) · [DOI 10.18653/v1/2026.acl-long.277](https://doi.org/10.18653/v1/2026.acl-long.277) · [OpenAlex](https://openalex.org/W7166805315)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary
LLM-based agents lose track of earlier interactions once their context window fills up. Standard RAG memories return isolated, loosely connected snippets, a problem known as "scattered retrieval." Graph-based alternatives such as GraphRAG and Mem0 tie content to rigid schemas.

The authors propose SEEM (Structured Episodic Event Memory), a two-layer memory for long-running dialogue agents:
- **Graph Memory Layer:** stores stable relational facts.
- **Episodic Memory Layer:** turns each passage into Episodic Event Frames (EEFs). These are slot-based event records extracted by an LLM and inspired by frame semantics.

A judging agent spots related frames, and a fusion agent merges them. For example, a question and its reply become one coherent event. Every memory unit keeps a provenance pointer back to its source passage. At query time, hybrid retrieval with Reverse Provenance Expansion (RPE) follows these pointers to rebuild a fuller, connected context.

On LoCoMo and LongMemEval, SEEM beats memory-augmented and dense retrieval baselines, including HippoRAG 2. The work matters for assistants that must reason consistently over long, evolving interaction histories.

## Key points
- Each EEF holds six semantic slots grounded in Case Grammar: Participants, Action, Time, Location, Causality and Manner. It also stores a summary and a provenance pointer to the original passage.
- SEEM outperforms HippoRAG 2 by 4.4 absolute points on LongMemEval. Extra tests with incremental memory construction indicate stable behaviour in sequential deployment.
- Ablations remove four components: relational propagation, RPE, fact provisioning (graph quadruples) and EEFs. Each removal lowers scores, yet even the reduced variants still exceed the baselines.
- A LoCoMo case study shows temporal resolution. Given a reference date of 23 January 2022 and a span of "three years," the system places the event's start in January 2019.
- The authors note three limitations:
  - higher latency and token cost from heavy LLM use;
  - extraction or fusion errors that can permanently corrupt the memory store;
  - fixed slots that may not fit abstract information.

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

## Institutions

- [Harbin Institute of Technology](https://md.research.elamur.ai/free/en/universities/harbin-institute-of-technology/) — University, Harbin, China · 158 works · 28,841 citations
- [Alibaba Group](https://md.research.elamur.ai/free/en/companies/alibaba-group/) — Company, Hangzhou, China · 168 works · 15,386 citations
- [Southeast University](https://md.research.elamur.ai/free/en/universities/southeast-university-cn/) — University, Nanjing, China · 28 works · 354 citations

📚 Shelves (5): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 2,869 works

## Cite

Cite as: Zhengxuan Lu, Dongfang Li, Yukun Shi, Beilun Wang, Longyue Wang and Baotian Hu. 2026. Structured Episodic Event Memory. Proceedings of the 64th 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.

```bibtex
@inproceedings{lu2026structured,
  title = {{Structured Episodic Event Memory}},
  author = {Zhengxuan Lu, Dongfang Li, Yukun Shi, Beilun Wang, Longyue Wang and Baotian Hu},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2026},
  doi = {10.18653/v1/2026.acl-long.277},
  url = {https://doi.org/10.18653/v1/2026.acl-long.277}
}
```

- [← previous StructBreak: Structural Cognitive Overload-Induced Safety Failures in MLLMs](https://md.research.elamur.ai/free/en/papers/luo-2026-structbreak-structural-cognitive-overload-induced/)
- [next → Structured Legal Document Generation in India: A Model-Agnostic Wrapper Approach with VidhikDastaavej](https://md.research.elamur.ai/free/en/papers/nigam-2026-structured-legal-document-generation-india/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/43/)

## References

28 references, 18 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Prateek Chhikara, Dev Khant, Saket Aryan, Taranjeet Singh, and Deshraj Yadav. 2025. [Mem0: Building production-ready ai agents with scalable long-term memory](https://md.research.elamur.ai/free/en/papers/chhikara-2025-mem0-building-production-ready-ai/). arXiv preprint arXiv:2504.19413.
2. Florin Cuconasu, Giovanni Trappolini, Federico Siciliano, Simone Filice, Cesare Campagnano, Yoelle Maarek, Nicola Tonellotto, and Fabrizio Silvestri. 2024. [The power of noise: Redefining retrieval for rag systems](https://md.research.elamur.ai/free/en/papers/cuconasu-2024-power-noise-redefining-retrieval-rag/). In Proceedings of the 47th International ACM SIGIR Conference on Research and Developm…
3. Darren Edge, Ha Trinh, Newman Cheng, Joshua Bradley, Alex Chao, Apurva Mody, Steven Truitt, Dasha Metropolitansky, Robert Osazuwa Ness, and Jonathan Larson. 2024. From local to global: A graph rag approach to query-focused summarization. arXiv preprint arXiv:2404.16130. [find](https://scholar.google.com/scholar?q=Darren+Edge%2C+Ha+Trinh%2C+Newman+Cheng%2C+Joshua+Bradley%2C+Alex+Chao%2C+Apurva+Mody%2C+Steven+Truitt%2C+Dasha+Metropolitansky%2C+Robert+Osazuwa+Ness%2C+and+Jonathan+Larson%2E+2024%2E+From+local+to+global%3A+A+graph+rag+app)
4. Charles J Fillmore. 1976. Frame semantics and the nature of language. Annals of the New York Academy of Sciences, 280(1):20–32. [find](https://scholar.google.com/scholar?q=Charles+J+Fillmore%2E+1976%2E+Frame+semantics+and+the+nature+of+language%2E+Annals+of+the+New+York+Academy+of+Sciences%2C+280%281%29%3A20%E2%80%9332%2E)
5. Yunfan Gao, Yun Xiong, Xinyu Gao, Kangxiang Jia, Jinliu Pan, Yuxi Bi, Yixin Dai, Jiawei Sun, Haofen Wang, and Haofen Wang. 2023. [Retrieval-augmented generation for large language models: A survey](https://md.research.elamur.ai/free/en/papers/gao-2023-retrieval-augmented-generation-large-language/). arXiv preprint arXiv:2312.10997, 2(1).
6. Bernal Jiménez Gutiérrez, Yiheng Shu, Weijian Qi, Sizhe Zhou, and Yu Su. 2025. From RAG to memory: Non-parametric continual learning for large language models. In Forty-second International Conference on Machine Learning. [find](https://scholar.google.com/scholar?q=Bernal+Jim%C3%A9nez+Guti%C3%A9rrez%2C+Yiheng+Shu%2C+Weijian+Qi%2C+Sizhe+Zhou%2C+and+Yu+Su%2E+2025%2E+From+RAG+to+memory%3A+Non%2Dparametric+continual+learning+for+large+language+models%2E+In+Forty%2Dsecond+International+Conference)
7. Taher H Haveliwala. 2002. Topic-sensitive pagerank. In Proceedings of the 11th international conference on World Wide Web, pages 517–526. [find](https://scholar.google.com/scholar?q=Taher+H+Haveliwala%2E+2002%2E+Topic%2Dsensitive+pagerank%2E+In+Proceedings+of+the+11th+international+conference+on+World+Wide+Web%2C+pages+517%E2%80%93526%2E)
8. Vladimir Karpukhin, Barlas Oguz, Sewon Min, Patrick SH Lewis, Ledell Wu, Sergey Edunov, Danqi Chen, and Wen-tau Yih. 2020. [Dense passage retrieval for open-domain question answering](https://md.research.elamur.ai/free/en/papers/karpukhin-2020-dense-passage-retrieval-open-domain/). In EMNLP (1), pages 6769–6781.
9. Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, and 1 others. 2023. [Gpt-4 technical report](https://md.research.elamur.ai/free/en/papers/openai-2023-gpt-4-technical-report/). arXiv preprint arXiv:2303.08774.
10. Chankyu Lee, Rajarshi Roy, Mengyao Xu, Jonathan Raiman, Mohammad Shoeybi, Bryan Catanzaro, and Wei Ping. 2025. [NV-embed: Improved techniques for training LLMs as generalist embedding models](https://md.research.elamur.ai/free/en/papers/lee-2024-nv-embed-improved-techniques-training/). In The Thirteenth International Conference on Learning Representations.
11. Sandhini Agarwal, Lama Ahmad, Jason Ai, Sam Altman, Andy Applebaum, Edwin Arbus, Rahul K Arora, Yu Bai, Bowen Baker, Haiming Bao, and 1 others. 2025. [gpt-oss-120b & gpt-oss-20b model card](https://md.research.elamur.ai/free/en/papers/agarwal-2025-gpt-oss-120b-gpt-oss/). arXiv preprint arXiv:2508.10925.
12. Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen-tau Yih, Tim Rocktäschel, and 1 others. 2020. [Retrieval-augmented generation for knowledge-intensive nlp tasks](https://md.research.elamur.ai/free/en/papers/lewis-2020-retrieval-augmented-generation-knowledge-intensive/). Advances in neural information processing systems, 33:9459–…
13. Hanting Chen, Yasheng Wang, Kai Han, Dong Li, Lin Li, Zhenni Bi, Jinpeng Li, Haoyu Wang, Fei Mi, Mingjian Zhu, Bin Wang, Kaikai Song, Yifei Fu, Xu He, Yu Luo, Chong Zhu, Quan He, Xueyu Wu, Wei He, and 5 others. 2025. [Pangu embedded: An efficient dual-system llm reasoner with metacognition](https://md.research.elamur.ai/free/en/papers/chen-2025-pangu-embedded-efficient-dual/). Preprint,…
14. Aixin Liu, Aoxue Mei, Bangcai Lin, Bing Xue, Bingxuan Wang, Bingzheng Xu, Bochao Wu, Bowei Zhang, Chaofan Lin, Chen Dong, Chengda Lu, Chenggang Zhao, Chengqi Deng, Chenhao Xu, Chong Ruan, Damai Dai, Daya Guo, Dejian Yang, Deli Chen, and 244 others. 2025. [Deepseek-v3.2: Pushing the frontier of open l…](https://md.research.elamur.ai/free/en/papers/deepseek-ai-2025-deepseek-v3-2-pushing/)
15. 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– 1387… [find](https://scholar.google.com/scholar?q=Adyasha+Maharana%2C+Dong%2DHo+Lee%2C+Sergey+Tulyakov%2C+Mohit+Bansal%2C+Francesco+Barbieri%2C+and+Yuwei+Fang%2E+2024%2E+Evaluating+very+long%2Dterm+conversational+memory+of+llm+agents%2E+In+Proceedings+of+the+62nd+Annual)
16. M Minsky. 1975. A framework for representing knowledge. The psychology of computer vision. [find](https://scholar.google.com/scholar?q=M+Minsky%2E+1975%2E+A+framework+for+representing+knowledge%2E+The+psychology+of+computer+vision%2E)
17. Charles Packer, Vivian Fang, Shishir G. Patil, Kevin Lin, Sarah Wooders, and Joseph E. Gonzalez. 2023. Memgpt: Towards llms as operating systems. CoRR, abs/2310.08560. [find](https://scholar.google.com/scholar?q=Charles+Packer%2C+Vivian+Fang%2C+Shishir+G%2E+Patil%2C+Kevin+Lin%2C+Sarah+Wooders%2C+and+Joseph+E%2E+Gonzalez%2E+2023%2E+Memgpt%3A+Towards+llms+as+operating+systems%2E+CoRR%2C+abs%2F2310%2E08560%2E)
18. Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. [Bleu: a method for automatic evaluation of machine translation](https://md.research.elamur.ai/free/en/papers/papineni-2002-bleu-method-automatic-evaluation-machine/). In Proceedings of the 40th Annual Meeting on Association for Computational Linguistics, ACL ’02, page 311–318, USA. Association for Computational Linguistics.
19. Wujiang Xu, Zujie Liang, Kai Mei, Hang Gao, Juntao Tan, and Yongfeng Zhang. 2025. [A-mem: Agentic memory for llm agents](https://md.research.elamur.ai/free/en/papers/xu-2025-mem-agentic-memory-llm-agents/). arXiv preprint arXiv:2502.12110.
20. An Yang, Anfeng Li, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Gao, Chengen Huang, Chenxu Lv, Chujie Zheng, Dayiheng Liu, Fan Zhou, Fei Huang, Feng Hu, Hao Ge, Haoran Wei, Huan Lin, Jialong Tang, and 41 others. 2025. [Qwen3 technical report](https://md.research.elamur.ai/free/en/papers/yang-2025-qwen3-technical-report/). Preprint, arXiv:2505.09388.
21. Xinping Zhao, Xinshuo Hu, Zifei Shan, Shouzheng Huang, Yao Zhou, Xin Zhang, Zetian Sun, Zhenyu Liu, Dongfang Li, Xinyuan Wei, Youcheng Pan, Yang Xiang, Meishan Zhang, Haofen Wang, Jun Yu, Baotian Hu, and Min Zhang. 2025. Kalm-embedding-v2: Superior training techniques and data inspire a versatile em… — [arXiv:2506.20923](https://arxiv.org/abs/2506.20923) [find](https://scholar.google.com/scholar?q=Xinping+Zhao%2C+Xinshuo+Hu%2C+Zifei+Shan%2C+Shouzheng+Huang%2C+Yao+Zhou%2C+Xin+Zhang%2C+Zetian+Sun%2C+Zhenyu+Liu%2C+Dongfang+Li%2C+Xinyuan+Wei%2C+Youcheng+Pan%2C+Yang+Xiang%2C+Meishan+Zhang%2C+Haofen+Wang%2C+Jun+Yu%2C+Baotian+Hu%2C+)
22. 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](https://scholar.google.com/scholar?q=Preston+Rasmussen%2C+Pavlo+Paliychuk%2C+Travis+Beauvais%2C+Jack+Ryan%2C+and+Daniel+Chalef%2E+2025%2E+Zep%3A+A+temporal+knowledge+graph+architecture+for+agent+memory%2E+Preprint%2C+arXiv%3A2501%2E13956%2E)
23. Parth Sarthi, Salman Abdullah, Aditi Tuli, Shubh Khanna, Anna Goldie, and Christopher D Manning. 2024. [RAPTOR: Recursive abstractive processing for tree-organized retrieval](https://md.research.elamur.ai/free/en/papers/sarthi-2024-raptor-recursive-abstractive-processing-tree/). In The Twelfth International Conference on Learning Representations.
24. Yixuan Tang and Yi Yang. 2024. [Multihop-rag: Benchmarking retrieval-augmented generation for multi-hop queries](https://md.research.elamur.ai/free/en/papers/tang-2024-multihop-rag-benchmarking-retrieval-augmented/). arXiv preprint arXiv:2401.15391.
25. Endel Tulving and 1 others. 1972. Episodic and semantic memory. Organization of memory, 1(381-403):1. [find](https://scholar.google.com/scholar?q=Endel+Tulving+and+1+others%2E+1972%2E+Episodic+and+semantic+memory%2E+Organization+of+memory%2C+1%28381%2D403%29%3A1%2E)
26. Di Wu, Hongwei Wang, Wenhao Yu, Yuwei Zhang, Kai-Wei Chang, and Dong Yu. 2025a. [Longmemeval: Benchmarking chat assistants on long-term interactive memory](https://md.research.elamur.ai/free/en/papers/wu-2024-longmemeval-benchmarking-chat-assistants-long/). In The Thirteenth International Conference on Learning Representations.
27. Jinyang Wu, Shuai Zhang, Feihu Che, Mingkuan Feng, Pengpeng Shao, and Jianhua Tao. 2025b. [Pandora’s box or aladdin’s lamp: A comprehensive analysis revealing the role of rag noise in large language models](https://md.research.elamur.ai/free/en/papers/wu-2025-pandora-s-box-or-aladdin/). In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Vo…
28. Zhiheng Xi, Wenxiang Chen, Xin Guo, Wei He, Yiwen Ding, Boyang Hong, Ming Zhang, Junzhe Wang, Senjie Jin, Enyu Zhou, and 1 others. 2025. [The rise and potential of large language model based agents: A survey](https://md.research.elamur.ai/free/en/papers/xi-2023-rise-potential-large-language/). Science China Information Sciences, 68(2):121101.

*Updated 1 November 2026*