Elamur Research⌕
☰
home / papers / 2026 / HeLa-Mem: Hebbian Learning and Associative Memory for LLM Agents

HeLa-Mem: Hebbian Learning and Associative Memory for LLM Agents

Paper · 2026 · Jinchang Zhu, Jindong Li, Cheng Zhang et al.

Summary

LLM agents struggle to stay coherent across long, multi-session dialogues. Most memory systems store past turns as embeddings and fetch them by semantic similarity alone, so they miss links between memories that are related through shared history rather than wording. HeLa-Mem addresses this with a memory design inspired by neuroscience. Each conversation turn becomes a node in an episodic graph, and edge weights grow through Hebbian updates whenever two memories are activated together. A Reflective Agent then finds densely connected hub nodes and condenses them into a semantic store, a step the authors call Hebbian Distillation. Weakly linked, unused nodes are pruned by Adaptive Forgetting. At query time, Dual-Path Retrieval combines similarity search with spreading activation along the learned edges. On LoCoMo, using GPT-4o-mini and GPT-4o backbones, the system outperforms memory baselines across all four question categories while consuming fewer context tokens. This suggests that learned associations can complement embedding retrieval, especially for multi-hop questions.

Key points

  • Evaluated on LoCoMo against ReadAgent, MemoryBank, MemGPT, A-Mem and MemoryOS. HeLa-Mem achieves the best average rank across question categories (1.25) at a lower token cost.
  • The semantic store has three parts: User Model, Factual Memory and Agent Knowledge. Each distilled record links back to its source turns as evidence.
  • Adaptive Forgetting removes peripheral nodes, for example those with degree below 4 and no recent access. This limits graph growth and reduces retrieval noise.
  • In a case study, a turn with only 0.35 semantic similarity was retrieved because a learned edge of weight 0.52 added a Hebbian score. Its combined score of about 0.71 made a correct multi-hop answer possible.
  • The main limitation is a cold start: associations need interaction history before they help. Errors made by the LLM during distillation may also persist in long-term memory.

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 University of Hong KongHong Kong · China126 works · 14,073 citations🎓The Hong Kong University of Science and Technology (Guangzhou)Guangzhou · China53 works · 1,367 citations🎓Jilin UniversityChangchun · China25 works · 5,252 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 worksComputer Vision and Pattern Recognition · 2,869 works

Cite

Cite as Jinchang Zhu, Jindong Li, Cheng Zhang, Jiahong Liu and Menglin Yang. 2026. HeLa-Mem: Hebbian Learning and Associative Memory for LLM Agents. 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.625

@inproceedings{zhu2026hela,
  title = {{HeLa-Mem: Hebbian Learning and Associative Memory for LLM Agents}},
  author = {Jinchang Zhu, Jindong Li, Cheng Zhang, Jiahong Liu and Menglin Yang},
  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.625},
  url = {https://doi.org/10.18653/v1/2026.acl-long.625}
}

References

26 references, 6 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, Red Avila, Igor Babuschkin, Suchir Balaji, Valerie Balcom, Paul Baltescu, Haiming Bao, Mohammad Bavarian, Jeff Belgum, Irwan Bello, and 260 ot… — GPT-4 Technical Report
  2. Prateek Chhikara, Dev Khant, Saket Aryan, Taranjeet Singh, and Deshraj Yadav. 2025. Mem0: Building production-ready ai agents with scalable long-term memory. arXiv preprint arXiv:2504.19413.
  3. 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. arXiv preprint arXiv:2510.18866. — [arXiv:2510.18866](https://arxiv.org/abs/2510.18866) find
  4. Donald Olding Hebb. 2005. The organization of behavior: A neuropsychological theory. Psychology press. find
  5. John J Hopfield. 1982. Neural networks and physical systems with emergent collective computational abilities. Proceedings of the National Academy of Sciences, 79(8):2554–2558. find
  6. Yuyang Hu, Shichun Liu, Yanwei Yue, Guibin Zhang, Boyang Liu, Fangyi Zhu, Jiahang Lin, Honglin Guo, Shihan Dou, Zhiheng Xi, Senjie Jin, Jiejun Tan, Yanbin Yin, Jiongnan Liu, Zeyu Zhang, Zhongxiang Sun, Yutao Zhu, Hao Sun, Boci Peng, and 28 others. 2025. Memory in the age of ai agents. arXiv preprint… — [arXiv:2512.13564](https://arxiv.org/abs/2512.13564) find
  7. Le Huang, Hengzhi Lan, Zijun Sun, Chuan Shi, and Ting Bai. 2024. Emotional rag: Enhancing role-playing agents through emotional retrieval. In 2024 IEEE International Conference on Knowledge Graph (ICKG), pages 120–127. IEEE. find
  8. Jiazheng Kang, Mingming Ji, Zhe Zhao, and Ting Bai. 2025. Memory os of ai agent. arXiv preprint arXiv:2506.06326.
  9. Kuang-Huei Lee, Xinyun Chen, Hiroki Furuta, John Canny, and Ian Fischer. 2024. A human-inspired reading agent with gist memory of very long contexts. arXiv preprint arXiv:2402.09727.
  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. 2020. Retrieval-augmented generation for knowledge-intensive nlp tasks. Advances in neural information process…
  11. Jindong Li, Yali Fu, Jiahong Liu, Linxiao Cao, Wei Ji, Menglin Yang, Irwin King, and Ming-Hsuan Yang. 2026. Discrete tokenization for multimodal llms: A comprehensive survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, pages 1–24. find
  12. Jiafeng Liang, Hao Li, Chang Li, Jiaqi Zhou, Shixin Jiang, Zekun Wang, Changkai Ji, Zhihao Zhu, Runxuan Liu, Tao Ren, Jinlan Fu, See-Kiong Ng, Xia Liang, Ming Liu, and Bing Qin. 2025. Ai meets brain: Memory systems from cognitive neuroscience to autonomous agents. arXiv preprint arXiv:2512.23343. — [arXiv:2512.23343](https://arxiv.org/abs/2512.23343) find
  13. Xinnian Liang, Bing Wang, Huijia Huang, Shuangzhi Wu, Peihao Wu, Lu Lu, Zejun Ma, and Zhoujun Li. 2023. Scm: Enhancing large language model with self-controlled memory framework. arXiv preprint arXiv:2304.13343. — [arXiv:2304.13343](https://arxiv.org/abs/2304.13343) find
  14. Jiahong Liu, Zexuan Qiu, Zhongyang Li, Quanyu Dai, Wenhao Yu, Jieming Zhu, Minda Hu, Menglin Yang, Tat-Seng Chua, and Irwin King. 2025. A survey of personalized large language models: Progress and future directions. arXiv preprint arXiv:2502.11528. — [arXiv:2502.11528](https://arxiv.org/abs/2502.11528) find
  15. Jiahong Liu, Wenhao Yu, Quanyu Dai, Zhongyang Li, Jieming Zhu, Menglin Yang, Tat-Seng Chua, and Irwin King. 2026. Perfit: Exploring personalization shifts in representation space of LLMs. In The Fourteenth International Conference on Learning Representations. find
  16. Lei Liu, Xiaoyan Yang, Yue Shen, Binbin Hu, Zhiqiang Zhang, Jinjie Gu, and Guannan Zhang. 2023. Thinkin-memory: Recalling and post-thinking enable LLMs with long-term memory. arXiv preprint arXiv:2311.08719. — [arXiv:2311.08719](https://arxiv.org/abs/2311.08719) find
  17. Zeyu Zhang, Quanyu Dai, Xiaohe Bo, Chen Ma, Rui Li, Xu Chen, Jieming Zhu, Zhenhua Dong, and Ji-Rong Wen. 2025. A survey on the memory mechanism of large language model-based agents. ACM Trans. Inf. Syst., 43(6). find
  18. Wanjun Zhong, Lianghong Guo, Qiqi Gao, He Ye, and Yanlin Wang. 2024. Memorybank: Enhancing large language models with long-term memory. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 38, pages 19724–19731. find
  19. 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
  20. Charles Packer, Vivian Fang, Shishir_G Patil, Kevin Lin, Sarah Wooders, and Joseph_E Gonzalez. 2023. MemGPT: Towards LLMs as operating systems. find
  21. Joon Sung Park, Joseph O’Brien, Carrie Jun Cai, Meredith Ringel Morris, Percy Liang, and Michael S Bernstein. 2023. Generative agents: Interactive simulacra of human behavior. In Proceedings of the 36th annual acm symposium on user interface software and technology, pages 1–22. find
  22. Hubert Ramsauer, Bernhard Schäfl, Johannes Lehner, Philipp Seidl, Michael Widrich, Thomas Adler, Lukas Gruber, Markus Holzleitner, Milena Pavlović, Geir Kjetil Sandve, Victor Greiff, David Kreil, Michael Kopp, Günter Klambauer, Johannes Brandstetter, and Sepp Hochreiter. 2020. Hopfield networks is… find
  23. Yaxiong Wu, Sheng Liang, Chen Zhang, Yichao Wang, Yongyue Zhang, Huifeng Guo, Ruiming Tang, and Yong Liu. 2025. From human memory to AI memory: A survey on memory mechanisms in the era of LLMs. arXiv preprint arXiv:2504.15965. — [arXiv:2504.15965](https://arxiv.org/abs/2504.15965) find
  24. Wujiang Xu, Zujie Liang, Kai Mei, Hang Gao, Juntao Tan, and Yongfeng Zhang. 2025. A-MEM: Agentic memory for LLM agents. arXiv preprint arXiv:2502.12110.
  25. BY Yan, Chaofan Li, Hongjin Qian, Shuqi Lu, and Zheng Liu. 2025. General agentic memory via deep research. arXiv preprint arXiv:2511.18423. — [arXiv:2511.18423](https://arxiv.org/abs/2511.18423) find
  26. An Yang, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chengyuan Li, Dayiheng Liu, Fei Huang, Haoran Wei, Huan Lin, Jian Yang, Jianhong Tu, Jianwei Zhang, Jianxin Yang, Jiaxi Yang, Jingren Zhou, Junyang Lin, Kai Dang, and 22 others. 2024. Qwen2.5 technical report. arXiv preprint arXi… find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/zhu-2026-hela-mem-hebbian-learning-associative/