Elamur Research⌕
☰
home / papers / 2026 / MemORAI: Memory Organization and Retrieval via Adaptive Graph Intelligence for LLM Conversational Agents

MemORAI: Memory Organization and Retrieval via Adaptive Graph Intelligence for LLM Conversational Agents

Paper · 2026 · Hung Pham Van, Nguyen Manh Hieu, Khang Pham Tran Tuan et al.

Summary

LLM-based conversational agents cannot remember users across long, multi-session interactions. Current graph-based memory stores also have problems: they keep too much generic chatter, they cannot show which dialogue turn a fact came from, and they rank evidence the same way regardless of the question. MemORAI tackles this with a three-stage pipeline:

  1. Conversations are split into topical segments. A gate keeps only persona-relevant utterances, such as personal facts, preferences and commitments, and a short summary stands in for the discarded material.
  2. An LLM extracts entity-relation triplets into a heterogeneous graph of entity, turn and segment nodes. Each fact carries turn-level provenance.
  3. At query time, the system collects a small query-specific subgraph and ranks it with Dynamic Weighted PageRank. In this variant, the edge weights depend on how well each edge matches the query semantically.

On LOCOMO and LongMemEval, MemORAI beats retrieval baselines such as HippoRAG 2, MemGAS and SeCom, at both session and turn level. The work matters because it shows that filtering, provenance and query-aware ranking together make long-term personalized memory more accurate and auditable.

Key points

  • Session-level Recall@10:
    • 98.54 on LongMemEval-s.
    • 92.03 on LOCOMO-10, versus 81.82 for the next-best system, MemGAS.
    • Recall@3 on LOCOMO-10 rises from 57.30 (MemGAS) to 72.05.
  • Turn-level Recall@10:
    • 64.68 on LOCOMO-10, versus 61.81 for HippoRAG 2. HippoRAG 2 remains slightly ahead at Recall@5.
    • 91.63 on LongMemEval-s, versus 88.14 for BGE-M3.
  • Query-conditioned edge weights: compared with uniform weights (w=1), turn R@10 improves from 62.01 to 64.68 on LOCOMO and from 89.75 to 91.63 on LongMemEval-s.
  • Subgraph retrieval vs. full graph:
    • On LOCOMO, turn R@10 rises from 51.77 to 64.68, and PPR latency drops from 14.19 ms to 12.44 ms.
    • Turn coverage stays high: 94.31% on LOCOMO and 99.90% on LongMemEval-s.
  • Adding triplets to retrieved turns during generation:
    • GPT-4o judge scores rise from 51.66 to 60.22 on LOCOMO and from 61.72 to 75.55 on LongMemEval-s.
    • BLEU on LOCOMO rises from 13.58 to 33.00.

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

🎓Monash UniversityMelbourne · Australia60 works · 54,866 citations🎓Hanoi University of Science and TechnologyHanoi · Vietnam10 works · 89 citations🎓Trường Đại học Khoa học và Công nghệ Hà NộiHanoi · Vietnam8 works · 88 citations

 Fields, topics and concepts

📚 Shelves 5The 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 worksInformation Systems · 1,437 works

🧭 Topics 2Research subjects and languages the work is about.Dialogue systems · 624 worksInformation retrieval & search · 473 works

Cite

Cite as Hung Pham Van, Nguyen Manh Hieu, Khang Pham Tran Tuan, Nam Le Hai, Linh Ngo Van, Nguyen Thi Ngoc Diep and Trung Le. 2026. MemORAI: Memory Organization and Retrieval via Adaptive Graph Intelligence for LLM Conversational Agents. Findings of the Association for Computational Linguistics: ACL 2026.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.findings-acl.1408

@inproceedings{van2026memorai,
  title = {{MemORAI: Memory Organization and Retrieval via Adaptive Graph Intelligence for LLM Conversational Agents}},
  author = {Hung Pham Van, Nguyen Manh Hieu, Khang Pham Tran Tuan, Nam {Le Hai}, Linh Ngo Van, Nguyen Thi Ngoc Diep and Trung Le},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.1408},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.1408}
}

References

33 references, 16 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. Preprint, arXiv:2504.19413.
  2. DeepSeek-AI, Aixin Liu, Bei Feng, Bing Xue, Bingxuan Wang, Bochao Wu, Chengda Lu, Chenggang Zhao, Chengqi Deng, Chenyu Zhang, Chong Ruan, Damai Dai, Daya Guo, Dejian Yang, Deli Chen, Dongjie Ji, Erhang Li, Fangyun Lin, Fucong Dai, and 181 others. 2025. Deepseek-v3 technical report. Preprint, arXiv:2… find
  3. Aaron Grattafiori, Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Alex Vaughan, Amy Yang, Angela Fan, Anirudh Goyal, Anthony Hartshorn, Aobo Yang, Archi Mitra, Archie Sravankumar, Artem Korenev, Arthur Hinsvark, and 542 o… — The Llama 3 Herd of Models
  4. Zirui Guo, Lianghao Xia, Yanhua Yu, Tian Ao, and Chao Huang. 2024. Lightrag: Simple and fast retrieval-augmented generation. arXiv preprint arXiv:2410.05779, 2(3).
  5. 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. Preprint, arXiv:2502.14802. find
  6. Nguyen Manh Hieu, Vu Lam Anh, Hung Pham Van, Nam Le Hai, Diep Thi-Ngoc Nguyen, Linh Ngo Van, and Thien Huu Nguyen. 2025. Magix: A multi-granular adaptive graph intelligence framework for enhancing cross-lingual rag. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 5202… find
  7. Gautier Izacard, Mathilde Caron, Lucas Hosseini, Sebastian Riedel, Piotr Bojanowski, Armand Joulin, and Edouard Grave. 2022. Unsupervised dense information retrieval with contrastive learning. Preprint, arXiv:2112.09118.
  8. Tue Le, Hoang Tran Vuong, Quyen Tran, Linh Ngo Van, Mehrtash Harandi, and Trung Le. 2025. Token-level self-play with importance-aware guidance for large language models. In The Thirty-ninth Annual Conference on Neural Information Processing Systems. find
  9. 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. Association for Computational Linguistics. find
  10. 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. 2021. Retrieval-augmented generation for knowledge-intensive nlp tasks. Preprint, arXiv:2005.11401.
  11. Bang Liu, Xinfeng Li, Jiayi Zhang, Jinlin Wang, Tanjin He, Sirui Hong, Hongzhang Liu, Shaokun Zhang, Kaitao Song, Kunlun Zhu, Yuheng Cheng, Suyuchen Wang, Xiaoqiang Wang, Yuyu Luo, Haibo Jin, Peiyan Zhang, Ollie Liu, Jiaqi Chen, Huan Zhang, and 29 others. 2025. Advances and challenges in foundation… — [arXiv:2504.01990](https://arxiv.org/abs/2504.01990) find
  12. Nelson F. Liu, Kevin Lin, John Hewitt, Ashwin Paranjape, Michele Bevilacqua, Fabio Petroni, and Percy Liang. 2023. Lost in the middle: How language models use long contexts. Preprint, arXiv:2307.03172.
  13. Adyasha Maharana, Dong-Ho Lee, Sergey Tulyakov, Mohit Bansal, Francesco Barbieri, and Yuwei Fang. 2024. Evaluating very long-term conversational memory of llm agents. Preprint, arXiv:2402.17753. find
  14. Toan Ngoc Nguyen, Nam Le Hai, Nguyen Doan Hieu, Dai An Nguyen, Linh Ngo Van, Thien Huu Nguyen, and Sang Dinh. 2025. Improving vietnamese-english cross-lingual retrieval for legal and general domains. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for… find
  15. Truong Nguyen, Phi Van Dat, Ngan Nguyen, Linh Ngo Van, Trung Le, and Thanh Hong Nguyen. 2026. CTPD: cross tokenizer preference distillation. In Fortieth AAAI Conference on Artificial Intelligence, Thirty-Eighth Conference on Innovative Applications of Artificial Intelligence, Sixteenth Symposium on…
  16. 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. On memory construction and retrieval for personalized conversational agents. Preprint, arXiv:2502.05589. — [arXiv:2502.05589](https://arxiv.org/abs/2502.05589) find
  17. Alireza Rezazadeh, Zichao Li, Wei Wei, and Yujia Bao. 2024. From isolated conversations to hierarchical schemas: Dynamic tree memory representation for llms. arXiv preprint arXiv:2410.14052. — [arXiv:2410.14052](https://arxiv.org/abs/2410.14052) find
  18. Parth Sarthi, Salman Abdullah, Aditi Tuli, Shubh Khanna, Anna Goldie, and Christopher D. Manning. 2024. Raptor: Recursive abstractive processing for tree-organized retrieval. Preprint, arXiv:2401.18059.
  19. Kaitao Song, Xu Tan, Tao Qin, Jianfeng Lu, and Tie-Yan Liu. 2020. Mpnet: Masked and permuted pre-training for language understanding. Preprint, arXiv:2004.09297.
  20. Zhen Tan, Jun Yan, I-Hung Hsu, Rujun Han, Zifeng Wang, Long T. Le, Yiwen Song, Yanfei Chen, Hamid Palangi, George Lee, Anand 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. Prepr…
  21. Gemini Team, Rohan Anil, Sebastian Borgeaud, Jean-Baptiste Alayrac, Jiahui Yu, Radu Soricut, Johan Schalkwyk, Andrew M. Dai, Anja Hauth, Katie Millican, David Silver, Melvin Johnson, Ioannis Antonoglou, Julian Schrittwieser, Amelia Glaese, Jilin Chen, Emily Pitler, Timothy Lillicrap, Angeliki Lazari… — Gemini: A Family of Highly Capable Multimodal Models
  22. Joan C. Timoneda and Sebastián Vallejo Vera. 2025. Memory is all you need: Testing how model memory affects llm performance in annotation tasks. Preprint, arXiv:2503.04874. — [arXiv:2503.04874](https://arxiv.org/abs/2503.04874) find
  23. Minh-Phuc Truong, Hai An Vu, Tu Vu, and Ngo Van Linh. 2025. Emo: Embedding model distillation via intra-model relation and optimal transport alignments. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 7605–7617.
  24. Duc Trung Vu, Pham Khanh Chi, Dat Phi Van, Linh Ngo Van, Dinh Viet Sang, and Trung Le. 2026a. Dwa-kd: Dual-space weighting and time-warped alignment for cross-tokenizer knowledge distillation. In Findings of the Association for Computational Linguistics: EACL, pages 3513–3527. find
  25. Hai An Vu, Minh-Phuc Truong, Tu Vu, Nguyen Thi Ngoc Diep, Linh Ngo Van, Thien Huu Nguyen, and Trung Le. 2026b. Mol: Mixture of layers in cross-tokenizer embedding model distillation. Knowledge-Based Systems, 343:116001. find
  26. Hoang Tran Vuong, Tue Le, Quyen Tran, Linh Ngo Van, and Trung Le. 2026. MCW-KD: multi-cost wasserstein knowledge distillation for large language models. In Fortieth AAAI Conference on Artificial Intelligence, Thirty-Eighth Conference on Innovative Applications of Artificial Intelligence, Sixteenth S… find
  27. Lei Wang, Chen Ma, Xueyang Feng, Zeyu Zhang, Hao Yang, Jingsen Zhang, Zhiyuan Chen, Jiakai Tang, Xu Chen, Yankai Lin, Wayne Xin Zhao, Zhewei Wei, and Jirong Wen. 2024. A survey on large language model based autonomous agents. Frontiers of Computer Science, 18(6).
  28. Qingyue Wang, Yanhe Fu, Yanan Cao, Shuai Wang, Zhiliang Tian, and Liang Ding. 2025. Recursively summarizing enables long-term dialogue memory in large language models. Preprint, arXiv:2308.15022. — [arXiv:2308.15022](https://arxiv.org/abs/2308.15022) find
  29. Di Wu, Hongwei Wang, Wenhao Yu, Yuwei Zhang, Kai-Wei Chang, and Dong Yu. 2025. Longmemeval: Benchmarking chat assistants on long-term interactive memory. In International Conference on Representation Learning, volume 2025, pages 86809– 86836.
  30. Wujiang Xu, Kai Mei, Hang Gao, Juntao Tan, Zujie Liang, and Yongfeng Zhang. 2025. A-mem: Agentic memory for llm agents. Preprint, arXiv:2502.12110.
  31. 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. Preprint, arXiv:2505.09388.
  32. Ruifeng Yuan, Shichao Sun, Yongqi Li, Zili Wang, Ziqiang Cao, and Wenjie Li. 2024. Personalized large language model assistant with evolving conditional memory. Preprint, arXiv:2312.17257. find
  33. Tianyi Zhang, Varsha Kishore, Felix Wu, Kilian Q. Weinberger, and Yoav Artzi. 2020. Bertscore: Evaluating text generation with bert. Preprint, arXiv:1904.09675. find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/van-2026-memorai-memory-organization-retrieval-adaptive/