---
title: "Hello Again! LLM-powered Personalized Agent for Long-term"
description: "The authors present LD-Agent, a model-agnostic framework that splits long-term dialogue into three… 51 references, cited by 38 papers here."
authors: ["Hao Li", "Chenghao Yang", "An Zhang", "Yang Deng", "Xiang Wang", "Tat-Seng Chua"]
year: 2025
venue: "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)"
source: "https://aclanthology.org/2025.naacl-long.272/"
doi: "10.18653/v1/2025.naacl-long.272"
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/li-2025-hello-again-llm-powered-personalized/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/li-2025-hello-again-llm-powered-personalized/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2025](https://md.research.elamur.ai/free/en/papers/2025/page/3/) / Hello Again! LLM-powered Personalized Agent for Long-term Dialogue

# Hello Again! LLM-powered Personalized Agent for Long-term Dialogue

**Authors:** [Hao Li](https://md.research.elamur.ai/free/en/authors/hao-li/), [Chenghao Yang](https://md.research.elamur.ai/free/en/authors/chenghao-yang/), [An Zhang](https://md.research.elamur.ai/free/en/authors/an-zhang/), [Yang Deng](https://md.research.elamur.ai/free/en/authors/yang-deng/), [Xiang Wang](https://md.research.elamur.ai/free/en/authors/xiang-wang/) and [Tat-Seng Chua](https://md.research.elamur.ai/free/en/authors/tat-seng-chua/) · **Year:** 2025 · **Venue:** [Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)](https://md.research.elamur.ai/free/en/venues/naacl/) ([NAACL 2025](https://md.research.elamur.ai/free/en/venues/naacl/2025/)) · **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/2025.naacl-long.272/) · [PDF](https://aclanthology.org/2025.naacl-long.272.pdf) · [DOI 10.18653/v1/2025.naacl-long.272](https://doi.org/10.18653/v1/2025.naacl-long.272) · [OpenAlex](https://openalex.org/W4411119539)

**Citations:** 17 citations (OpenAlex, 2026-10-14) · [38](https://md.research.elamur.ai/free/en/papers/li-2025-hello-again-llm-powered-personalized/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
Most open-domain chatbots are built for short, single-session exchanges. Real companionship, however, requires remembering past conversations and keeping track of who the user and the bot are. The authors present LD-Agent, a model-agnostic framework that splits long-term dialogue into three separately trainable modules:

- **Event memory:** a long-term bank holds vectorised summaries of earlier sessions, and a short-term bank holds the current session's context. Relevant memories are retrieved using topic information.
- **Persona extraction:** it dynamically builds and updates profiles of both the user and the agent.
- **Response generation:** it combines retrieved memories and personas to produce replies.

Evaluation uses two multi-session datasets, MSC (human-written) and Conversation Chronicles (CC, LLM-generated). LD-Agent reaches state-of-the-art results on both. It works with LLM backbones such as ChatGLM and with non-LLM models. Training on one dataset and testing on the other costs little performance. The framework also transfers to multi-party dialogue. This matters because memory and persona handling no longer depend on a specific architecture.

## Key points
- Three independently tunable modules: event perception (long- and short-term memory banks plus topic-based retrieval), bidirectional user/agent persona extraction, and response generation.
- Benchmarks are MSC and Conversation Chronicles (CC). In cross-domain tests (tuning ChatGLM on MSC and testing on CC, and the reverse), results nearly match in-domain tuning and clearly beat zero-shot ChatGLM.
- On the multi-party Ubuntu IRC dataset with a BART backbone, LD-Agent beats GPT-2, GSN and HeterMPC-BART on most metrics: BLEU-1 is 14.40 vs 12.26 and ROUGE-L is 12.28 vs 11.20.
- Stated limitations: all existing long-term dialogue datasets are synthetic, and the module implementations are deliberately basic.
- Code is public at github.com/leolee99/LD-Agent.

*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

- [National University of Singapore](https://md.research.elamur.ai/free/en/universities/national-university-of-singapore/) — University, Singapore, Singapore · 207 works · 39,576 citations
- [University of Science and Technology of China](https://md.research.elamur.ai/free/en/universities/university-of-science-and-technology-of-china/) — University, Hefei, China · 145 works · 114,409 citations
- [Singapore Management University](https://md.research.elamur.ai/free/en/universities/singapore-management-university/) — University, Singapore, Singapore · 35 works · 2,457 citations

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,450 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,296 works

🧭 Topics (1): [🗨️ Dialogue systems](https://md.research.elamur.ai/free/en/topics/dialogue-systems/) · 654 works

## Cite

Cite as: Hao Li, Chenghao Yang, An Zhang, Yang Deng, Xiang Wang and Tat-Seng Chua. 2025. Hello Again! LLM-powered Personalized Agent for Long-term Dialogue. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers).

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{li2025hello,
  title = {{Hello Again! LLM-powered Personalized Agent for Long-term Dialogue}},
  author = {Hao Li, Chenghao Yang, An Zhang, Yang Deng, Xiang Wang and Tat-Seng Chua},
  booktitle = {Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)},
  year = {2025},
  doi = {10.18653/v1/2025.naacl-long.272},
  url = {https://doi.org/10.18653/v1/2025.naacl-long.272}
}
```

- [← previous A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and Beyond](https://md.research.elamur.ai/free/en/papers/qu-2025-survey-efficient-reasoning-large-reasoning/)
- [next → Memory OS of AI Agent](https://md.research.elamur.ai/free/en/papers/kang-2025-memory-os-ai-agent/)
- [↑ back to papers of 2025](https://md.research.elamur.ai/free/en/papers/2025/page/3/)

## References

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

1. Tianyu Gao, Howard Yen, Jiatong Yu, and Danqi Chen. 2023b. [Enabling large language models to generate text with citations](https://md.research.elamur.ai/free/en/papers/gao-2023-enabling-large-language-models-generate/). In EMNLP, pages 6465–6488.
2. Satanjeev Banerjee and Alon Lavie. 2005. [METEOR: an automatic metric for MT evaluation with improved correlation with human judgments](https://md.research.elamur.ai/free/en/papers/banerjee-2005-meteor-automatic-metric-mt-evaluation/). In ACL Workshop, pages 65–72.
3. Bogdan Gliwa, Iwona Mochol, Maciej Biesek, and Aleksander Wawer. 2019. [Samsum corpus: A human-annotated dialogue dataset for abstractive summarization](https://md.research.elamur.ai/free/en/papers/gliwa-2019-samsum-corpus-human-annotated-dialogue/). CoRR, abs/1911.12237.
4. Yu Cao, Wei Bi, Meng Fang, Shuming Shi, and Dacheng Tao. 2022. A model-agnostic data manipulation method for persona-based dialogue generation. In ACL, pages 7984–8002. [find](https://scholar.google.com/scholar?q=Yu+Cao%2C+Wei+Bi%2C+Meng+Fang%2C+Shuming+Shi%2C+and+Dacheng+Tao%2E+2022%2E+A+model%2Dagnostic+data+manipulation+method+for+persona%2Dbased+dialogue+generation%2E+In+ACL%2C+pages+7984%E2%80%938002%2E)
5. Jia-Chen Gu, Zhen-Hua Ling, Yu Wu, Quan Liu, Zhigang Chen, and Xiaodan Zhu. 2021. Detecting speaker personas from conversational texts. In EMNLP, pages 1126–1136. [find](https://scholar.google.com/scholar?q=Jia%2DChen+Gu%2C+Zhen%2DHua+Ling%2C+Yu+Wu%2C+Quan+Liu%2C+Zhigang+Chen%2C+and+Xiaodan+Zhu%2E+2021%2E+Detecting+speaker+personas+from+conversational+texts%2E+In+EMNLP%2C+pages+1126%E2%80%931136%2E)
6. Liang Chen, Hongru Wang, Yang Deng, Wai-Chung Kwan, Zezhong Wang, and Kam-Fai Wong. 2023a. Towards robust personalized dialogue generation via order-insensitive representation regularization. In ACL Findings, pages 7337–7345. [find](https://scholar.google.com/scholar?q=Liang+Chen%2C+Hongru+Wang%2C+Yang+Deng%2C+Wai%2DChung+Kwan%2C+Zezhong+Wang%2C+and+Kam%2DFai+Wong%2E+2023a%2E+Towards+robust+personalized+dialogue+generation+via+order%2Dinsensitive+representation+regularization%2E+In+ACL+F)
7. Jia-Chen Gu, Zhen-Hua Ling, Xiaodan Zhu, and Quan Liu. 2019. Dually interactive matching network for personalized response selection in retrieval-based chatbots. In EMNLP-IJCNLP, pages 1845–1854. [find](https://scholar.google.com/scholar?q=Jia%2DChen+Gu%2C+Zhen%2DHua+Ling%2C+Xiaodan+Zhu%2C+and+Quan+Liu%2E+2019%2E+Dually+interactive+matching+network+for+personalized+response+selection+in+retrieval%2Dbased+chatbots%2E+In+EMNLP%2DIJCNLP%2C+pages+1845%E2%80%931854%2E)
8. Siyuan Chen, Mengyue Wu, Kenny Q. Zhu, Kunyao Lan, Zhiling Zhang, and Lyuchun Cui. 2023b. Llm-empowered chatbots for psychiatrist and patient simulation: Application and evaluation. CoRR, abs/2305.13614. — [arXiv:2305.13614](https://arxiv.org/abs/2305.13614) [find](https://scholar.google.com/scholar?q=Siyuan+Chen%2C+Mengyue+Wu%2C+Kenny+Q%2E+Zhu%2C+Kunyao+Lan%2C+Zhiling+Zhang%2C+and+Lyuchun+Cui%2E+2023b%2E+Llm%2Dempowered+chatbots+for+psychiatrist+and+patient+simulation%3A+Application+and+evaluation%2E+CoRR%2C+abs%2F2305%2E136)
9. Jia-Chen Gu, Chao-Hong Tan, Chongyang Tao, Zhen-Hua Ling, Huang Hu, Xiubo Geng, and Daxin Jiang. 2022. Hetermpc: A heterogeneous graph neural network for response generation in multi-party conversations. In ACL, pages 5086–5097. [find](https://scholar.google.com/scholar?q=Jia%2DChen+Gu%2C+Chao%2DHong+Tan%2C+Chongyang+Tao%2C+Zhen%2DHua+Ling%2C+Huang+Hu%2C+Xiubo+Geng%2C+and+Daxin+Jiang%2E+2022%2E+Hetermpc%3A+A+heterogeneous+graph+neural+network+for+response+generation+in+multi%2Dparty+conversatio)
10. Xiuyi Chen, Jiaming Xu, and Bo Xu. 2019. A working memory model for task-oriented dialog response generation. In ACL, pages 2687–2693. [find](https://scholar.google.com/scholar?q=Xiuyi+Chen%2C+Jiaming+Xu%2C+and+Bo+Xu%2E+2019%2E+A+working+memory+model+for+task%2Doriented+dialog+response+generation%2E+In+ACL%2C+pages+2687%E2%80%932693%2E)
11. Wenpeng Hu, Zhangming Chan, Bing Liu, Dongyan Zhao, Jinwen Ma, and Rui Yan. 2019. GSN: A graph-structured network for multi-party dialogues. In IJCAI, pages 5010–5016. [find](https://scholar.google.com/scholar?q=Wenpeng+Hu%2C+Zhangming+Chan%2C+Bing+Liu%2C+Dongyan+Zhao%2C+Jinwen+Ma%2C+and+Rui+Yan%2E+2019%2E+GSN%3A+A+graph%2Dstructured+network+for+multi%2Dparty+dialogues%2E+In+IJCAI%2C+pages+5010%E2%80%935016%2E)
12. Yirong Chen, Xiaofen Xing, Jingkai Lin, Huimin Zheng, Zhenyu Wang, Qi Liu, and Xiangmin Xu. 2023c. Soulchat: Improving llms’ empathy, listening, and comfort abilities through fine-tuning with multi-turn empathy conversations. In EMNLP Findings, pages 1170–1183. [find](https://scholar.google.com/scholar?q=Yirong+Chen%2C+Xiaofen+Xing%2C+Jingkai+Lin%2C+Huimin+Zheng%2C+Zhenyu+Wang%2C+Qi+Liu%2C+and+Xiangmin+Xu%2E+2023c%2E+Soulchat%3A+Improving+llms%E2%80%99+empathy%2C+listening%2C+and+comfort+abilities+through+fine%2Dtuning+with+multi%2Dtu)
13. Wenyue Hua, Lizhou Fan, Lingyao Li, Kai Mei, Jianchao Ji, Yingqiang Ge, Libby Hemphill, and Yongfeng Zhang. 2023. War and peace (waragent): Large language model-based multi-agent simulation of world wars. CoRR. [find](https://scholar.google.com/scholar?q=Wenyue+Hua%2C+Lizhou+Fan%2C+Lingyao+Li%2C+Kai+Mei%2C+Jianchao+Ji%2C+Yingqiang+Ge%2C+Libby+Hemphill%2C+and+Yongfeng+Zhang%2E+2023%2E+War+and+peace+%28waragent%29%3A+Large+language+model%2Dbased+multi%2Dagent+simulation+of+world+w)
14. Yulong Chen, Yang Liu, Liang Chen, and Yue Zhang. 2021. [Dialogsum: A real-life scenario dialogue summarization dataset](https://md.research.elamur.ai/free/en/papers/chen-2021-dialogsum-real-life-scenario-dialogue/). In ACL-IJCNLP Findings, volume ACL/IJCNLP 2021, pages 5062–5074.
15. Xu Huang, Jianxun Lian, Yuxuan Lei, Jing Yao, Defu Lian, and Xing Xie. 2023. Recommender AI agent: Integrating large language models for interactive recommendations. CoRR, abs/2308.16505. — [arXiv:2308.16505](https://arxiv.org/abs/2308.16505) [find](https://scholar.google.com/scholar?q=Xu+Huang%2C+Jianxun+Lian%2C+Yuxuan+Lei%2C+Jing+Yao%2C+Defu+Lian%2C+and+Xing+Xie%2E+2023%2E+Recommender+AI+agent%3A+Integrating+large+language+models+for+interactive+recommendations%2E+CoRR%2C+abs%2F2308%2E16505%2E+%E2%80%94+%5BarXiv%3A230)
16. Junyan Cheng and Peter Chin. 2024. Sociodojo: Building lifelong analytical agents with real-world text and time series. In ICLR. [find](https://scholar.google.com/scholar?q=Junyan+Cheng+and+Peter+Chin%2E+2024%2E+Sociodojo%3A+Building+lifelong+analytical+agents+with+real%2Dworld+text+and+time+series%2E+In+ICLR%2E)
17. Jihyoung Jang, Minseong Boo, and Hyounghun Kim. 2023. Conversation chronicles: Towards diverse temporal and relational dynamics in multi-session conversations. In EMNLP, pages 13584–13606. [find](https://scholar.google.com/scholar?q=Jihyoung+Jang%2C+Minseong+Boo%2C+and+Hyounghun+Kim%2E+2023%2E+Conversation+chronicles%3A+Towards+diverse+temporal+and+relational+dynamics+in+multi%2Dsession+conversations%2E+In+EMNLP%2C+pages+13584%E2%80%9313606%2E)
18. Xiang Deng, Yu Gu, Boyuan Zheng, Shijie Chen, Samual Stevens, Boshi Wang, Huan Sun, and Yu Su. 2023. [Mind2web: Towards a generalist agent for the web](https://md.research.elamur.ai/free/en/papers/deng-2023-mind2web-towards-generalist-agent-web/). In NeurIPS.
19. Tomohito Kasahara, Daisuke Kawahara, Nguyen Tung, Shengzhe Li, Kenta Shinzato, and Toshinori Sato. 2022. Building a personalized dialogue system with prompt-tuning. In NAACL, pages 96–105. [find](https://scholar.google.com/scholar?q=Tomohito+Kasahara%2C+Daisuke+Kawahara%2C+Nguyen+Tung%2C+Shengzhe+Li%2C+Kenta+Shinzato%2C+and+Toshinori+Sato%2E+2022%2E+Building+a+personalized+dialogue+system+with+prompt%2Dtuning%2E+In+NAACL%2C+pages+96%E2%80%93105%2E)
20. Yang Deng, Yaliang Li, Wenxuan Zhang, Bolin Ding, and Wai Lam. 2022. Toward personalized answer generation in e-commerce via multi-perspective preference modeling. ACM Trans. Inf. Syst., 40(4):87:1– 87:28. [find](https://scholar.google.com/scholar?q=Yang+Deng%2C+Yaliang+Li%2C+Wenxuan+Zhang%2C+Bolin+Ding%2C+and+Wai+Lam%2E+2022%2E+Toward+personalized+answer+generation+in+e%2Dcommerce+via+multi%2Dperspective+preference+modeling%2E+ACM+Trans%2E+Inf%2E+Syst%2E%2C+40%284%29%3A87%3A1%E2%80%93+8)
21. Diederik P. Kingma and Jimmy Ba. 2015. [Adam: A method for stochastic optimization](https://md.research.elamur.ai/free/en/papers/kingma-2014-adam-method-stochastic-optimization/). In ICLR.
22. Danica Dillion, Niket Tandon, Yuling Gu, and Kurt Gray. 2023. Can ai language models replace human participants? Trends in Cognitive Sciences. [find](https://scholar.google.com/scholar?q=Danica+Dillion%2C+Niket+Tandon%2C+Yuling+Gu%2C+and+Kurt+Gray%2E+2023%2E+Can+ai+language+models+replace+human+participants%3F+Trends+in+Cognitive+Sciences%2E)
23. Mike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad, Abdelrahman Mohamed, Omer Levy, Veselin Stoyanov, and Luke Zettlemoyer. 2020. [BART: denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension](https://md.research.elamur.ai/free/en/papers/lewis-2020-bart-denoising-sequence-sequence-pre/). In ACL, pages 7871–7880.
24. Yanran Li, Hui Su, Xiaoyu Shen, Wenjie Li, Ziqiang Cao, and Shuzi Niu. 2017. [Dailydialog: A manually labelled multi-turn dialogue dataset](https://md.research.elamur.ai/free/en/papers/li-2017-dailydialog-manually-labelled-multi-turn/). In IJCNLP, pages 986–995.
25. Chin-Yew Lin. 2004. [Rouge: A package for automatic evaluation of summaries](https://md.research.elamur.ai/free/en/papers/lin-2004-rouge-package-automatic-evaluation-summaries/). In ACL.
26. Qian Liu, Yihong Chen, Bei Chen, Jian-Guang Lou, Zixuan Chen, Bin Zhou, and Dongmei Zhang. 2020. [You impress me: Dialogue generation via mutual persona perception](https://md.research.elamur.ai/free/en/papers/liu-2020-you-impress-me-dialogue-generation/). In ACL, pages 1417–1427.
27. Hongru Wang, Wenyu Huang, Yang Deng, Rui Wang, Zezhong Wang, Yufei Wang, Fei Mi, Jeff Z. Pan, and Kam-Fai Wong. 2024. Unims-rag: A unified multi-source retrieval-augmented generation for personalized dialogue systems. CoRR, abs/2401.13256. — [arXiv:2401.13256](https://arxiv.org/abs/2401.13256) [find](https://scholar.google.com/scholar?q=Hongru+Wang%2C+Wenyu+Huang%2C+Yang+Deng%2C+Rui+Wang%2C+Zezhong+Wang%2C+Yufei+Wang%2C+Fei+Mi%2C+Jeff+Z%2E+Pan%2C+and+Kam%2DFai+Wong%2E+2024%2E+Unims%2Drag%3A+A+unified+multi%2Dsource+retrieval%2Daugmented+generation+for+personalized+)
28. Lanrui Wang, Jiangnan Li, Chenxu Yang, Zheng Lin, and Weiping Wang. 2023b. Enhancing empathetic and emotion support dialogue generation with prophetic commonsense inference. CoRR, abs/2311.15316. — [arXiv:2311.15316](https://arxiv.org/abs/2311.15316) [find](https://scholar.google.com/scholar?q=Lanrui+Wang%2C+Jiangnan+Li%2C+Chenxu+Yang%2C+Zheng+Lin%2C+and+Weiping+Wang%2E+2023b%2E+Enhancing+empathetic+and+emotion+support+dialogue+generation+with+prophetic+commonsense+inference%2E+CoRR%2C+abs%2F2311%2E15316%2E+%E2%80%94+%5Ba)
29. Adyasha Maharana, Dong-Ho Lee, Sergey Tulyakov, Mohit Bansal, Francesco Barbieri, and Yuwei Fang. 2024. Evaluating very long-term conversational memory of LLM agents. CoRR, abs/2402.17753. [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+CoRR%2C+abs%2F2402%2E17753%2E)
30. Qingyue Wang, Liang Ding, Yanan Cao, Zhiliang Tian, Shi Wang, Dacheng Tao, and Li Guo. 2023c. Recursively summarizing enables long-term dialogue memory in large language models. CoRR, abs/2308.15022. — [arXiv:2308.15022](https://arxiv.org/abs/2308.15022) [find](https://scholar.google.com/scholar?q=Qingyue+Wang%2C+Liang+Ding%2C+Yanan+Cao%2C+Zhiliang+Tian%2C+Shi+Wang%2C+Dacheng+Tao%2C+and+Li+Guo%2E+2023c%2E+Recursively+summarizing+enables+long%2Dterm+dialogue+memory+in+large+language+models%2E+CoRR%2C+abs%2F2308%2E15022%2E+)
31. Minsik Oh, Joosung Lee, Jiwei Li, and Guoyin Wang. 2023. PK-ICR: persona-knowledge interactive multi-context retrieval for grounded dialogue. In EMNLP, pages 16383–16395. [find](https://scholar.google.com/scholar?q=Minsik+Oh%2C+Joosung+Lee%2C+Jiwei+Li%2C+and+Guoyin+Wang%2E+2023%2E+PK%2DICR%3A+persona%2Dknowledge+interactive+multi%2Dcontext+retrieval+for+grounded+dialogue%2E+In+EMNLP%2C+pages+16383%E2%80%9316395%2E)
32. Wenhui Wang, Furu Wei, Li Dong, Hangbo Bao, Nan Yang, and Ming Zhou. 2020. Minilm: Deep self-attention distillation for task-agnostic compression of pre-trained transformers. In NeurIPS. [find](https://scholar.google.com/scholar?q=Wenhui+Wang%2C+Furu+Wei%2C+Li+Dong%2C+Hangbo+Bao%2C+Nan+Yang%2C+and+Ming+Zhou%2E+2020%2E+Minilm%3A+Deep+self%2Dattention+distillation+for+task%2Dagnostic+compression+of+pre%2Dtrained+transformers%2E+In+NeurIPS%2E)
33. 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 ACL, pages 311–318.
34. Joon Sung Park, Joseph C. O’Brien, Carrie Jun Cai, Meredith Ringel Morris, Percy Liang, and Michael S. Bernstein. 2023. Generative agents: Interactive simulacra of human behavior. In UIST, pages 2:1–2:22. [find](https://scholar.google.com/scholar?q=Joon+Sung+Park%2C+Joseph+C%2E+O%E2%80%99Brien%2C+Carrie+Jun+Cai%2C+Meredith+Ringel+Morris%2C+Percy+Liang%2C+and+Michael+S%2E+Bernstein%2E+2023%2E+Generative+agents%3A+Interactive+simulacra+of+human+behavior%2E+In+UIST%2C+pages+2%3A1%E2%80%932)
35. Zekun Moore Wang, Zhongyuan Peng, Haoran Que, Jiaheng Liu, Wangchunshu Zhou, Yuhan Wu, Hongcheng Guo, Ruitong Gan, Zehao Ni, Man Zhang, Zhaoxiang Zhang, Wanli Ouyang, Ke Xu, Wenhu Chen, Jie Fu, and Junran Peng. 2023d. [Rolellm: Benchmarking, eliciting, and enhancing role-playing abilities of large la…](https://md.research.elamur.ai/free/en/papers/wang-2023-rolellm-benchmarking-eliciting-enhancing-role/)
36. Chen Qian, Xin Cong, Cheng Yang, Weize Chen, Yusheng Su, Juyuan Xu, Zhiyuan Liu, and Maosong Sun. 2023. [Communicative agents for software development](https://md.research.elamur.ai/free/en/papers/qian-2023-chatdev-communicative-agents-software/). CoRR, abs/2307.07924.
37. Jason Wei, Maarten Bosma, Vincent Y. Zhao, Kelvin Guu, Adams Wei Yu, Brian Lester, Nan Du, Andrew M. Dai, and Quoc V. Le. 2022a. [Finetuned language models are zero-shot learners](https://md.research.elamur.ai/free/en/papers/wei-2021-finetuned-language-models-zero-shot/). In ICLR.
38. Alec Radford, Karthik Narasimhan, Tim Salimans, and Ilya Sutskever. Improving language understanding by generative pre-training. [find](https://scholar.google.com/scholar?q=Alec+Radford%2C+Karthik+Narasimhan%2C+Tim+Salimans%2C+and+Ilya+Sutskever%2E+Improving+language+understanding+by+generative+pre%2Dtraining%2E)
39. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Brian Ichter, Fei Xia, Ed H. Chi, Quoc V. Le, and Denny Zhou. 2022b. [Chain-of-thought prompting elicits reasoning in large language models](https://md.research.elamur.ai/free/en/papers/wei-2022-chain-thought-prompting-elicits-reasoning/). In NeurIPS.
40. Hannah Rashkin, Eric Michael Smith, Margaret Li, and Y-Lan Boureau. 2019. Towards empathetic open-domain conversation models: A new benchmark and dataset. In ACL, pages 5370–5381. [find](https://scholar.google.com/scholar?q=Hannah+Rashkin%2C+Eric+Michael+Smith%2C+Margaret+Li%2C+and+Y%2DLan+Boureau%2E+2019%2E+Towards+empathetic+open%2Ddomain+conversation+models%3A+A+new+benchmark+and+dataset%2E+In+ACL%2C+pages+5370%E2%80%935381%2E)
41. Stephen Roller, Emily Dinan, Naman Goyal, Da Ju, Mary Williamson, Yinhan Liu, Jing Xu, Myle Ott, Eric Michael Smith, Y-Lan Boureau, and Jason Weston. 2021. [Recipes for building an open-domain chatbot](https://md.research.elamur.ai/free/en/papers/roller-2021-recipes-building-open-domain-chatbot/). In EACL, pages 300–325.
42. Omar Shaikh, Valentino Chai, Michele J. Gelfand, Diyi Yang, and Michael S. Bernstein. 2023. Rehearsal: Simulating conflict to teach conflict resolution. CoRR, abs/2309.12309. [find](https://scholar.google.com/scholar?q=Omar+Shaikh%2C+Valentino+Chai%2C+Michele+J%2E+Gelfand%2C+Diyi+Yang%2C+and+Michael+S%2E+Bernstein%2E+2023%2E+Rehearsal%3A+Simulating+conflict+to+teach+conflict+resolution%2E+CoRR%2C+abs%2F2309%2E12309%2E)
43. Bowen Wu, Mengyuan Li, Zongsheng Wang, Yifu Chen, Derek F. Wong, Qihang Feng, Junhong Huang, and Baoxun Wang. 2020a. Guiding variational response generator to exploit persona. In ACL, pages 53–65. [find](https://scholar.google.com/scholar?q=Bowen+Wu%2C+Mengyuan+Li%2C+Zongsheng+Wang%2C+Yifu+Chen%2C+Derek+F%2E+Wong%2C+Qihang+Feng%2C+Junhong+Huang%2C+and+Baoxun+Wang%2E+2020a%2E+Guiding+variational+response+generator+to+exploit+persona%2E+In+ACL%2C+pages+53%E2%80%9365%2E)
44. Chien-Sheng Wu, Andrea Madotto, Zhaojiang Lin, Peng Xu, and Pascale Fung. 2020b. Getting to know you: User attribute extraction from dialogues. In LREC, pages 581–589. [find](https://scholar.google.com/scholar?q=Chien%2DSheng+Wu%2C+Andrea+Madotto%2C+Zhaojiang+Lin%2C+Peng+Xu%2C+and+Pascale+Fung%2E+2020b%2E+Getting+to+know+you%3A+User+attribute+extraction+from+dialogues%2E+In+LREC%2C+pages+581%E2%80%93589%2E)
45. Jing Xu, Arthur Szlam, and Jason Weston. 2022a. Beyond goldfish memory: Long-term open-domain conversation. In ACL, pages 5180–5197. [find](https://scholar.google.com/scholar?q=Jing+Xu%2C+Arthur+Szlam%2C+and+Jason+Weston%2E+2022a%2E+Beyond+goldfish+memory%3A+Long%2Dterm+open%2Ddomain+conversation%2E+In+ACL%2C+pages+5180%E2%80%935197%2E)
46. Yunfan Shao, Linyang Li, Junqi Dai, and Xipeng Qiu. 2023. [Character-llm: A trainable agent for role-playing](https://md.research.elamur.ai/free/en/papers/shao-2023-character-llm-trainable-agent-role/). In EMNLP, pages 13153–13187.
47. Ruoxi Xu, Yingfei Sun, Mengjie Ren, Shiguang Guo, Ruotong Pan, Hongyu Lin, Le Sun, and Xianpei Han. 2024. AI for social science and social science of AI: A survey. CoRR, abs/2401.11839. [find](https://scholar.google.com/scholar?q=Ruoxi+Xu%2C+Yingfei+Sun%2C+Mengjie+Ren%2C+Shiguang+Guo%2C+Ruotong+Pan%2C+Hongyu+Lin%2C+Le+Sun%2C+and+Xianpei+Han%2E+2024%2E+AI+for+social+science+and+social+science+of+AI%3A+A+survey%2E+CoRR%2C+abs%2F2401%2E11839%2E)
48. Guanzhi Wang, Yuqi Xie, Yunfan Jiang, Ajay Mandlekar, Chaowei Xiao, Yuke Zhu, Linxi Fan, and Anima Anandkumar. 2023a. Voyager: An open-ended embodied agent with large language models. CoRR, abs/2305.16291. [find](https://scholar.google.com/scholar?q=Guanzhi+Wang%2C+Yuqi+Xie%2C+Yunfan+Jiang%2C+Ajay+Mandlekar%2C+Chaowei+Xiao%2C+Yuke+Zhu%2C+Linxi+Fan%2C+and+Anima+Anandkumar%2E+2023a%2E+Voyager%3A+An+open%2Dended+embodied+agent+with+large+language+models%2E+CoRR%2C+abs%2F2305%2E1)
49. Xinchao Xu, Zhibin Gou, Wenquan Wu, Zheng-Yu Niu, Hua Wu, Haifeng Wang, and Shihang Wang. 2022b. Long time no see! open-domain conversation with long-term persona memory. In ACL Findings, pages 2639–2650. [find](https://scholar.google.com/scholar?q=Xinchao+Xu%2C+Zhibin+Gou%2C+Wenquan+Wu%2C+Zheng%2DYu+Niu%2C+Hua+Wu%2C+Haifeng+Wang%2C+and+Shihang+Wang%2E+2022b%2E+Long+time+no+see%21+open%2Ddomain+conversation+with+long%2Dterm+persona+memory%2E+In+ACL+Findings%2C+pages+2639%E2%80%932)
50. Aohan Zeng, Xiao Liu, Zhengxiao Du, Zihan Wang, Hanyu Lai, Ming Ding, Zhuoyi Yang, Yifan Xu, Wendi Zheng, Xiao Xia, Weng Lam Tam, Zixuan Ma, Yufei Xue, Jidong Zhai, Wenguang Chen, Zhiyuan Liu, Peng Zhang, Yuxiao Dong, and Jie Tang. 2023. [GLM-130B: an open bilingual pre-trained model](https://md.research.elamur.ai/free/en/papers/zeng-2022-glm-130b-open-bilingual-pre/). In ICLR.
51. A An Zhang, Leheng Sheng, Yuxin Chen, Hao Li, Yang Deng, Xiang Wang, and Tat-Seng Chua. 2023a. On generative agents in recommendation. CoRR, abs/2310.10108. — [arXiv:2310.10108](https://arxiv.org/abs/2310.10108) [find](https://scholar.google.com/scholar?q=A+An+Zhang%2C+Leheng+Sheng%2C+Yuxin+Chen%2C+Hao+Li%2C+Yang+Deng%2C+Xiang+Wang%2C+and+Tat%2DSeng+Chua%2E+2023a%2E+On+generative+agents+in+recommendation%2E+CoRR%2C+abs%2F2310%2E10108%2E+%E2%80%94+%5BarXiv%3A2310%2E10108%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F)

*Updated 30 October 2026*