Elamur Research⌕
☰
home / papers / 2026 / HyperMem: Hypergraph Memory for Long-Term Conversations

HyperMem: Hypergraph Memory for Long-Term Conversations

Paper · 2026 · Juwei Yue, Chuanrui Hu, Jiawei Sheng et al.

Summary

Conversational agents need memory that persists across long dialogues, but their context windows are fixed. Chunk-based RAG and graph-based memory link items only in pairs. As a result, they miss joint dependencies among three or more pieces of content, and retrieval comes back fragmented. HyperMem addresses this by storing dialogue memory as a hypergraph with three levels: topics, episodes (contiguous segments about one theme) and atomic facts. Hyperedges group all episodes under a topic and all facts within an episode, so related but scattered content can be retrieved together. Construction proceeds in three steps: episode boundaries are detected, episodes are aggregated into topics, and facts are extracted. Indexing combines lexical cues with dense embeddings refined by hypergraph propagation. Retrieval narrows from topics to episodes to facts. On the LoCoMo benchmark, HyperMem reaches a state-of-the-art 92.73% LLM-as-a-judge accuracy while using far fewer tokens than graph-based RAG baselines. This shows that higher-order structure makes long-term memory both more accurate and cheaper to query.

Key points

  • Best configuration ("Episode + Fact") scores 92.73% LLM-as-a-judge on LoCoMo at 7.5x tokens relative to Mem0. "Fact Only" reaches 89.48% at 2.5x. For comparison, GraphRAG gets 67.60% at 35.3x and HyperGraphRAG 86.49% at 26.3x.
  • Ablations show the contribution of individual components:
    • Disabling hypergraph embedding propagation lowers accuracy to 91.69% (−1.04%).
    • Raising topic top-k from 1 to 10 lifts accuracy from 76.88% to 92.66%.
  • Offline memory building for 10 conversations costs 8,291 LLM calls (45.1M tokens). New episodes are added incrementally with 2–3 calls each. Online retrieval uses no LLM calls, and answering takes about 8.5K tokens per question.
  • Stated limitations: the system assumes a single user, and Open Domain questions needing external knowledge remain hard.
  • Code is released in the EverMind-AI/EverOS repository on GitHub.

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

🏛️Chinese Academy of SciencesBeijing · China246 works · 24,952 citations🎓University of Chinese Academy of SciencesBeijing · China188 works · 8,744 citations🔬Institute of Information EngineeringBeijing · China41 works · 1,485 citations

 Fields, topics and concepts

📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Computer Science · 18,614 worksArtificial Intelligence · 17,965 worksArts and Humanities · 17,450 worksLanguage and Linguistics · 17,296 works

Cite

Cite as Juwei Yue, Chuanrui Hu, Jiawei Sheng, Zuyi Zhou, Wenyuan Zhang, Tingwen Liu, Li Guo and Yafeng Deng. 2026. HyperMem: Hypergraph Memory for Long-Term Conversations. 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. DOI 10.18653/v1/2026.acl-long.1627

@inproceedings{yue2026hypermem,
  title = {{HyperMem: Hypergraph Memory for Long-Term Conversations}},
  author = {Juwei Yue, Chuanrui Hu, Jiawei Sheng, Zuyi Zhou, Wenyuan Zhang, Tingwen Liu, Li Guo and Yafeng Deng},
  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.1627},
  url = {https://doi.org/10.18653/v1/2026.acl-long.1627}
}

References

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

  1. Hyper-rag: Combating LLM hallucinations using hypergraph-driven retrieval-augmented generation. CoRR, abs/2504.08758. — [arXiv:2504.08758](https://arxiv.org/abs/2504.08758) find
  2. John R Anderson and Gordon H Bower. 2014. Human associative memory. Psychology press. find
  3. Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil, and Hannaneh Hajishirzi. 2024. Self-rag: Learning to retrieve, generate, and critique through self-reflection. In The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024. OpenReview.net.
  4. Orlando Ayala and Patrice Béchard. 2024. Reducing hallucination in structured outputs via retrieval-augmented generation. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Industry Track, NAACL 2024, Mex… find
  5. Boyu Chen, Zirui Guo, Zidan Yang, Yuluo Chen, Junze Chen, Zhenghao Liu, Chuan Shi, and Cheng Yang. 2025. Pathrag: Pruning graph-based retrieval augmented generation with relational paths. CoRR, abs/2502.14902. — [arXiv:2502.14902](https://arxiv.org/abs/2502.14902) find
  6. Prateek Chhikara, Dev Khant, Saket Aryan, Taranjeet Singh, and Deshraj Yadav. 2025. Mem0: Building production-ready AI agents with scalable long-term memory. CoRR, abs/2504.19413.
  7. Jialin Dong, Bahare Fatemi, Bryan Perozzi, Lin F. Yang, and Anton Tsitsulin. 2024. Don’t forget to connect! improving RAG with graph-based reranking. CoRR, abs/2405.18414. — [arXiv:2405.18414](https://arxiv.org/abs/2405.18414) find
  8. Darren Edge, Ha Trinh, Newman Cheng, Joshua Bradley, Alex Chao, Apurva Mody, Steven Truitt, and Jonathan Larson. 2024. From local to global: A graph RAG approach to query-focused summarization. CoRR, abs/2404.16130. find
  9. Tianyu Fan, Jingyuan Wang, Xubin Ren, and Chao Huang. 2025. Minirag: Towards extremely simple retrieval-augmented generation. CoRR, abs/2501.06713. — [arXiv:2501.06713](https://arxiv.org/abs/2501.06713) find
  10. Wenqi Fan, Yujuan Ding, Liangbo Ning, Shijie Wang, Hengyun Li, Dawei Yin, Tat-Seng Chua, and Qing Li. 2024. A survey on RAG meeting llms: Towards retrieval-augmented large language models. In Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2024, Barcelona, S…
  11. Jizhan Fang, Xinle Deng, Haoming Xu, Ziyan Jiang, Yuqi Tang, Ziwen Xu, Shumin Deng, Yunzhi Yao, Mengru Wang, Shuofei Qiao, Huajun Chen, and Ningyu Zhang. 2025. Lightmem: Lightweight and efficient memory-augmented generation. CoRR, abs/2510.18866. — [arXiv:2510.18866](https://arxiv.org/abs/2510.18866) find
  12. Yifan Feng, Hao Hu, Xingliang Hou, Shiquan Liu, Shihui Ying, Shaoyi Du, Han Hu, and Yue Gao. 2025. find
  13. Yifan Feng, Haoxuan You, Zizhao Zhang, Rongrong Ji, and Yue Gao. 2019. Hypergraph neural networks. In Proceedings of the AAAI conference on artificial intelligence, volume 33, pages 3558–3565. find
  14. Yunfan Gao, Yun Xiong, Xinyu Gao, Kangxiang Jia, Jinliu Pan, Yuxi Bi, Yi Dai, Jiawei Sun, Qianyu Guo, Meng Wang, and Haofen Wang. 2023. Retrieval-augmented generation for large language models: A survey. CoRR, abs/2312.10997.
  15. Zirui Guo, Lianghao Xia, Yanhua Yu, Tu Ao, and Chao Huang. 2025. LightRAG: Simple and fast retrieval-augmented generation. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 10746–10761, Suzhou, China. Association for Computational Linguistics.
  16. Bernal Jimenez Gutierrez, Yiheng Shu, Yu Gu, Michihiro Yasunaga, and Yu Su. 2024. Hipporag: Neurobiologically inspired long-term memory for large language models. In Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, NeurIPS 2024, V…
  17. 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, ICML 2025, Vancouver, BC, Canada, July 13-19, 2025. OpenReview.net.
  18. Xiaoxin He, Yijun Tian, Yifei Sun, Nitesh V. Chawla, Thomas Laurent, Yann LeCun, Xavier Bresson, and Bryan Hooi. 2024. G-retriever: Retrieval-augmented generation for textual graph understanding and question answering. In Advances in Neural Information Processing Systems 38: Annual Conference on Neu…
  19. Chuanrui Hu, Xingze Gao, Zuyi Zhou, Dannong Xu, Yi Bai, Xintong Li, Hui Zhang, Tong Li, Chong Zhang, Lidong Bing, and Yafeng Deng. 2026. Evermemos: A self-organizing memory operating system for structured long-horizon reasoning. CoRR, abs/2601.02163. find
  20. Hao Hu, Yifan Feng, Ruoxue Li, Rundong Xue, Xingliang Hou, Zhiqiang Tian, Yue Gao, and Shaoyi Du. 2025a. Cog-rag: Cognitive-inspired dual-hypergraph with theme alignment retrieval-augmented generation. CoRR, abs/2511.13201. — [arXiv:2511.13201](https://arxiv.org/abs/2511.13201) find
  21. Yuntong Hu, Zhihan Lei, Zheng Zhang, Bo Pan, Chen Ling, and Liang Zhao. 2025b. GRAG: graph retrieval-augmented generation. In Findings of the Association for Computational Linguistics: NAACL 2025, Albuquerque, New Mexico, USA, April 29 - May 4, 2025, pages 4145–4157. Association for Computational Li… find
  22. Haoyu Huang, Yongfeng Huang, Junjie Yang, Zhenyu Pan, Yongqiang Chen, Kaili Ma, Hongzhi Chen, and James Cheng. 2025. Retrieval-augmented generation with hierarchical knowledge. CoRR, abs/2503.10150. find
  23. Bowen Jiang, Zhuoqun Hao, Young-Min Cho, Bryan Li, Yuan Yuan, Sihao Chen, Lyle H. Ungar, Camillo J. Taylor, and Dan Roth. 2025. Know me, respond to me: Benchmarking llms for dynamic user profiling and personalized responses at scale. CoRR, abs/2504.14225. — [arXiv:2504.14225](https://arxiv.org/abs/2504.14225) find
  24. Mandar Kulkarni, Praveen Tangarajan, Kyung Kim, and Anusua Trivedi. 2024. Reinforcement learning for optimizing RAG for domain chatbots. CoRR, abs/2401.06800. — [arXiv:2401.06800](https://arxiv.org/abs/2401.06800) find
  25. Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen-tau Yih, Tim Rocktäschel, Sebastian Riedel, and Douwe Kiela. 2020. Retrieval-augmented generation for knowledge-intensive NLP tasks. In Advances in Neural Information Proc…
  26. Mufei Li, Siqi Miao, and Pan Li. 2025a. Simple is effective: The roles of graphs and large language models in knowledge-graph-based retrieval-augmented generation. In The Thirteenth International Conference on Learning Representations, ICLR 2025, Singapore, April 24-28, 2025. OpenReview.net. find
  27. Zhiyu Li, Shichao Song, Chenyang Xi, Hanyu Wang, Chen Tang, Simin Niu, Ding Chen, Jiawei Yang, Chunyu Li, Qingchen Yu, Jihao Zhao, Yezhaohui Wang, Peng Liu, Zehao Lin, Pengyuan Wang, Jiahao Huo, Tianyi Chen, Kai Chen, Kehang Li, and 20 others. 2025b. Memos: A memory OS for AI system. CoRR, abs/2507.… — [arXiv:2507.03724](https://arxiv.org/abs/2507.03724) find
  28. Xiaoqiang Lin, Aritra Ghosh, Bryan Kian Hsiang Low, Anshumali Shrivastava, and Vijai Mohan. 2025. RE-FRAG: rethinking RAG based decoding. CoRR, abs/2509.01092. — [arXiv:2509.01092](https://arxiv.org/abs/2509.01092) find
  29. Haoran Luo, Haihong E, Guanting Chen, Yandan Zheng, Xiaobao Wu, Yikai Guo, Qika Lin, Yu Feng, Ze-min Kuang, Meina Song, Yifan Zhu, and Luu Anh Tuan. 2025. Hypergraphrag: Retrieval-augmented generation with hypergraph-structured knowledge representation. CoRR, abs/2503.21322. — [arXiv:2503.21322](https://arxiv.org/abs/2503.21322) find
  30. Linhao Luo, Yuan-Fang Li, Gholamreza Haffari, and Shirui Pan. 2024. Reasoning on graphs: Faithful and interpretable large language model reasoning. In The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024. OpenReview.net. find
  31. 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), ACL 2024, Bangkok… find
  32. Jiayan Nan, Wenquan Ma, Wenlong Wu, and Yize Chen. 2025. Nemori: Self-organizing agent memory inspired by cognitive science. CoRR, abs/2508.03341. — [arXiv:2508.03341](https://arxiv.org/abs/2508.03341) find
  33. 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
  34. Preston Rasmussen, Pavlo Paliychuk, Travis Beauvais, Jack Ryan, and Daniel Chalef. 2025. Zep: A temporal knowledge graph architecture for agent memory. CoRR, abs/2501.13956.
  35. Stephen E. Robertson and Hugo Zaragoza. 2009. The probabilistic relevance framework: BM25 and beyond. Found. Trends Inf. Retr., 3(4):333–389. find
  36. Rana Salama, Jason Cai, Michelle Yuan, Anna Currey, Monica Sunkara, Yi Zhang, and Yassine Benajiba. 2025. Meminsight: Autonomous memory augmentation for LLM agents. CoRR, abs/2503.21760.
  37. Parth Sarthi, Salman Abdullah, Aditi Tuli, Shubh Khanna, Anna Goldie, and Christopher D. Manning. 2024. RAPTOR: recursive abstractive processing for tree-organized retrieval. In The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024. OpenReview.n…
  38. Kartik Sharma, Peeyush Kumar, and Yunqing Li. 2024. OG-RAG: ontology-grounded retrieval-augmented generation for large language models. CoRR, abs/2412.15235.
  39. Yu Wang and Xi Chen. 2025. MIRIX: multi-agent memory system for llm-based agents. CoRR, abs/2507.07957. — [arXiv:2507.07957](https://arxiv.org/abs/2507.07957) find
  40. Yu Wang, Ryuichi Takanobu, Zhiqi Liang, Yuzhen Mao, Yuanzhe Hu, Julian J. McAuley, and Xiaojian Wu. 2025. Mem-α: Learning memory construction via reinforcement learning. CoRR, abs/2509.25911. — [arXiv:2509.25911](https://arxiv.org/abs/2509.25911) find
  41. Yuan Xia, Jingbo Zhou, Zhenhui Shi, Jun Chen, and Haifeng Huang. 2025. Improving retrieval augmented language model with self-reasoning. In AAAI-25, Sponsored by the Association for the Advancement of Artificial Intelligence, February 25 -March 4, 2025, Philadelphia, PA, USA, pages 25534– 25542. AAA…
  42. Wujiang Xu, Zujie Liang, Kai Mei, Hang Gao, Juntao Tan, and Yongfeng Zhang. 2025. A-MEM: agentic memory for LLM agents. CoRR, abs/2502.12110.
  43. Sikuan Yan, Xiufeng Yang, Zuchao Huang, Ercong Nie, Zifeng Ding, Zonggen Li, Xiaowen Ma, Hinrich Schütze, Volker Tresp, and Yunpu Ma. 2025. Memory-r1: Enhancing large language model agents to manage and utilize memories via reinforcement learning. CoRR, abs/2508.19828.
  44. Guibin Zhang, Muxin Fu, Guancheng Wan, Miao Yu, Kun Wang, and Shuicheng Yan. 2025a. G-memory: Tracing hierarchical memory for multi-agent systems. CoRR, abs/2506.07398. — [arXiv:2506.07398](https://arxiv.org/abs/2506.07398) find
  45. Guibin Zhang, Muxin Fu, and Shuicheng Yan. 2025b. Memgen: Weaving generative latent memory for self-evolving agents. CoRR, abs/2509.24704. — [arXiv:2509.24704](https://arxiv.org/abs/2509.24704) find
  46. Nan Zhang, Prafulla Kumar Choubey, Alexander R. Fabbri, Gabriel Bernadett-Shapiro, Rui Zhang, Prasenjit Mitra, Caiming Xiong, and Chien-Sheng Wu. 2025c. Sirerag: Indexing similar and related information for multihop reasoning. In The Thirteenth International Conference on Learning Representations, I… find
  47. Wenyuan Zhang, Xinghua Zhang, Haiyang Yu, Shuaiyi Nie, Bingli Wu, Juwei Yue, Tingwen Liu, and Yongbin Li. 2026. Expseek: Self-triggered experience seeking for web agents. Preprint, arXiv:2601.08605.
  48. Huan Lin, Baosong Yang, Pengjun Xie, An Yang, Dayiheng Liu, Junyang Lin, Fei Huang, and Jingren Zhou. 2025d. Qwen3 embedding: Advancing text embedding and reranking through foundation models. CoRR, abs/2506.05176.
  49. Zeyu Zhang, Quanyu Dai, Xiaohe Bo, Chen Ma, Rui Li, Xu Chen, Jieming Zhu, Zhenhua Dong, and Ji-Rong Wen. 2025e. A survey on the memory mechanism of large language model-based agents. ACM Trans. Inf. Syst., 43(6):155:1–155:47. find
  50. 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
  51. Zijian Zhou, Ao Qu, Zhaoxuan Wu, Sunghwan Kim, Alok Prakash, Daniela Rus, Jinhua Zhao, Bryan Kian Hsiang Low, and Paul Pu Liang. 2025. MEM1: learning to synergize memory and reasoning for efficient long-horizon agents. CoRR, abs/2506.15841. — [arXiv:2506.15841](https://arxiv.org/abs/2506.15841) find
  52. Yanzhao Zhang, Mingxin Li, Dingkun Long, Xin Zhang, find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/yue-2026-hypermem-hypergraph-memory-long-term/