---
title: "A Dual-Phase Self-Evolution Framework for Large Language"
description: "The authors propose DPSE (Dual-Phase Self-Evolution), which lets a model improve both aspects from its own interaction logs. 33 references."
authors: ["Haoran Sun", "Zekun Zhang", "Shaoning Zeng"]
year: 2026
venue: "Findings of the Association for Computational Linguistics: ACL 2026"
source: "https://aclanthology.org/2026.findings-acl.37/"
doi: "10.18653/v1/2026.findings-acl.37"
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/sun-2026-dual-phase-self-evolution-framework/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/sun-2026-dual-phase-self-evolution-framework/)

[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/20/) / A Dual-Phase Self-Evolution Framework for Large Language Models

# A Dual-Phase Self-Evolution Framework for Large Language Models

**Authors:** [Haoran Sun](https://md.research.elamur.ai/free/en/authors/haoran-sun/), [Zekun Zhang](https://md.research.elamur.ai/free/en/authors/zekun-zhang/) and [Shaoning Zeng](https://md.research.elamur.ai/free/en/authors/shaoning-zeng/) · **Year:** 2026 · **Venue:** [Findings of the Association for Computational Linguistics: ACL 2026](https://md.research.elamur.ai/free/en/venues/findings/) ([Findings of the Association for Computational Linguistics 2026](https://md.research.elamur.ai/free/en/venues/findings/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.findings-acl.37/) · [PDF](https://aclanthology.org/2026.findings-acl.37.pdf) · [DOI 10.18653/v1/2026.findings-acl.37](https://doi.org/10.18653/v1/2026.findings-acl.37) · [OpenAlex](https://openalex.org/W7166884525)

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

## Summary
Post-training methods such as preference optimization or memory-augmented prompting help LLMs match user expectations, but they leave the model's underlying domain knowledge mostly unchanged. SFT can add that knowledge, but it needs costly annotated data. The authors propose DPSE (Dual-Phase Self-Evolution), which lets a model improve both aspects from its own interaction logs. A Censor module turns implicit and explicit user behaviour into a satisfaction score and assigns topics, building a structured preference memory. That memory drives two kinds of data growth: topic-aware expansion, based on topic distribution, and preference-driven expansion, guided by satisfaction scores. Training runs in two stages: supervised fine-tuning for domain grounding, then frequency-aware preference optimization (a DPO variant) on satisfaction-labelled samples. DPSE beats SFT, PO and memory-augmented baselines both on broad NLP evaluations and on tasks involving extended, multi-session conversations. In a simulated long-term deployment, its MT-Bench score rises steadily. The work suggests a largely autonomous route to continual LLM improvement without manual annotation.

## Key points
- Censor combines five signals: explicit feedback, dwell time (U-shaped mapping), query–response coherence, similarity to earlier answers, and sentiment. These pass through a gate MLP and a credibility MLP, with hand-set constraints such as limiting the similarity weight to 10%.
- Long-term simulation: 100,000 WildChat conversations were streamed into DPSE, with self-evolution triggered every 1,000 samples. The MT-Bench absolute score grew from 3.65 to 8.97.
- The 1,000 threshold was chosen over 500 (frequent but noisy updates) and larger values (sparse updates).
- In ablations, removing Censor or Dataset Construction hurt most, which points to data quality as the main source of gains.
- Experiments use 1.5B–7B models. The authors list limitations: noisy heuristic signals, a fixed topic taxonomy, possible bias amplification, and retraining cost.

*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

- [University of Electronic Science and Technology of China](https://md.research.elamur.ai/free/en/universities/university-of-electronic-science-and-technology-of-china/) — University, Chengdu, China · 31 works · 2,012 citations

📚 Shelves (4): [🖥️ 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

🧭 Topics (1): [🧠 Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/) · 3,320 works

## Cite

Cite as: Haoran Sun, Zekun Zhang and Shaoning Zeng. 2026. A Dual-Phase Self-Evolution Framework for Large Language Models. Findings of the Association for Computational Linguistics: ACL 2026.

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

```bibtex
@inproceedings{sun2026dual,
  title = {{A Dual-Phase Self-Evolution Framework for Large Language Models}},
  author = {Haoran Sun, Zekun Zhang and Shaoning Zeng},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.37},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.37}
}
```

- [← previous A Dialogue System for Second Language Learning with Dynamic Adaptation to In-Dialogue Difficulty Changes](https://md.research.elamur.ai/free/en/papers/morioka-2026-dialogue-system-second-language-learning/)
- [next → A Dual-View Analysis of Multiple Languages in Colonial Newspapers](https://md.research.elamur.ai/free/en/papers/su-2026-dual-view-analysis-multiple-languages/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/20/)

## References

33 references, 15 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Yuntao Bai, Andy Jones, Kamal Ndousse, Amanda Askell, Anna Chen, Nova DasSarma, Dawn Drain, Stanislav Fort, Deep Ganguli, Tom Henighan, and 1 others. 2022. Training a helpful and harmless assistant with reinforcement learning from human feedback. arXiv preprint arXiv:2204.05862. [find](https://scholar.google.com/scholar?q=Yuntao+Bai%2C+Andy+Jones%2C+Kamal+Ndousse%2C+Amanda+Askell%2C+Anna+Chen%2C+Nova+DasSarma%2C+Dawn+Drain%2C+Stanislav+Fort%2C+Deep+Ganguli%2C+Tom+Henighan%2C+and+1+others%2E+2022%2E+Training+a+helpful+and+harmless+assistant+wi)
2. Tianlong Chen, Sijia Liu, Shiyu Chang, Yu Cheng, Lisa Amini, and Zhangyang Wang. 2020. Adversarial robustness: From self-supervised pre-training to fine-tuning. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 699–708. [find](https://scholar.google.com/scholar?q=Tianlong+Chen%2C+Sijia+Liu%2C+Shiyu+Chang%2C+Yu+Cheng%2C+Lisa+Amini%2C+and+Zhangyang+Wang%2E+2020%2E+Adversarial+robustness%3A+From+self%2Dsupervised+pre%2Dtraining+to+fine%2Dtuning%2E+In+Proceedings+of+the+IEEE%2FCVF+conferen)
3. Ganqu Cui, Lifan Yuan, Ning Ding, Guanming Yao, Bingxiang He, Wei Zhu, Yuan Ni, Guotong Xie, Ruobing Xie, Yankai Lin, Zhiyuan Liu, and Maosong Sun. 2024. Ultrafeedback: Boosting language models with scaled ai feedback. Preprint, arXiv:2310.01377. [find](https://scholar.google.com/scholar?q=Ganqu+Cui%2C+Lifan+Yuan%2C+Ning+Ding%2C+Guanming+Yao%2C+Bingxiang+He%2C+Wei+Zhu%2C+Yuan+Ni%2C+Guotong+Xie%2C+Ruobing+Xie%2C+Yankai+Lin%2C+Zhiyuan+Liu%2C+and+Maosong+Sun%2E+2024%2E+Ultrafeedback%3A+Boosting+language+models+with+s)
4. Ning Ding, Yulin Chen, Bokai Xu, Yujia Qin, Zhi Zheng, Shengding Hu, Zhiyuan Liu, Maosong Sun, and Bowen Zhou. 2023. [Enhancing chat language models by scaling high-quality instructional conversations](https://md.research.elamur.ai/free/en/papers/ding-2023-enhancing-chat-language-models-scaling/). Preprint, arXiv:2305.14233.
5. Guanting Dong, Hongyi Yuan, Keming Lu, Chengpeng Li, Mingfeng Xue, Dayiheng Liu, Wei Wang, Zheng Yuan, Chang Zhou, and Jingren Zhou. 2023. [How abilities in large language models are affected by supervised fine-tuning data composition](https://md.research.elamur.ai/free/en/papers/dong-2024-how-abilities-large-language-models/). arXiv preprint arXiv:2310.05492.
6. Yann Dubois, Balázs Galambosi, Percy Liang, and Tatsunori B. Hashimoto. 2025. Length-controlled alpacaeval: A simple way to debias automatic evaluators. Preprint, arXiv:2404.04475. [find](https://scholar.google.com/scholar?q=Yann+Dubois%2C+Bal%C3%A1zs+Galambosi%2C+Percy+Liang%2C+and+Tatsunori+B%2E+Hashimoto%2E+2025%2E+Length%2Dcontrolled+alpacaeval%3A+A+simple+way+to+debias+automatic+evaluators%2E+Preprint%2C+arXiv%3A2404%2E04475%2E)
7. Jiawei Gu, Xuhui Jiang, Zhichao Shi, Hexiang Tan, Xuehao Zhai, Chengjin Xu, Wei Li, Yinghan Shen, Shengjie Ma, Honghao Liu, and 1 others. 2024. A survey on llm-as-a-judge. arXiv preprint arXiv:2411.15594. [find](https://scholar.google.com/scholar?q=Jiawei+Gu%2C+Xuhui+Jiang%2C+Zhichao+Shi%2C+Hexiang+Tan%2C+Xuehao+Zhai%2C+Chengjin+Xu%2C+Wei+Li%2C+Yinghan+Shen%2C+Shengjie+Ma%2C+Honghao+Liu%2C+and+1+others%2E+2024%2E+A+survey+on+llm%2Das%2Da%2Djudge%2E+arXiv+preprint+arXiv%3A2411%2E15)
8. Xu Huang, Weiwen Liu, Xiaolong Chen, Xingmei Wang, Hao Wang, Defu Lian, Yasheng Wang, Ruiming Tang, and Enhong Chen. 2024. Understanding the planning of llm agents: A survey. arXiv preprint arXiv:2402.02716. [find](https://scholar.google.com/scholar?q=Xu+Huang%2C+Weiwen+Liu%2C+Xiaolong+Chen%2C+Xingmei+Wang%2C+Hao+Wang%2C+Defu+Lian%2C+Yasheng+Wang%2C+Ruiming+Tang%2C+and+Enhong+Chen%2E+2024%2E+Understanding+the+planning+of+llm+agents%3A+A+survey%2E+arXiv+preprint+arXiv%3A2402)
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](https://md.research.elamur.ai/free/en/papers/lee-2024-human-inspired-reading-agent-gist/). arXiv preprint arXiv:2402.09727.
10. Shunyu Liu, Wenkai Fang, Zetian Hu, Junjie Zhang, Yang Zhou, Kongcheng Zhang, Rongcheng Tu, Ting-En Lin, Fei Huang, Mingli Song, and 1 others. 2025. A survey of direct preference optimization. arXiv preprint arXiv:2503.11701. — [arXiv:2503.11701](https://arxiv.org/abs/2503.11701) [find](https://scholar.google.com/scholar?q=Shunyu+Liu%2C+Wenkai+Fang%2C+Zetian+Hu%2C+Junjie+Zhang%2C+Yang+Zhou%2C+Kongcheng+Zhang%2C+Rongcheng+Tu%2C+Ting%2DEn+Lin%2C+Fei+Huang%2C+Mingli+Song%2C+and+1+others%2E+2025%2E+A+survey+of+direct+preference+optimization%2E+arXiv+p)
11. Adyasha Maharana, Dong-Ho Lee, Sergey Tulyakov, Mohit Bansal, Francesco Barbieri, and Yuwei Fang. 2024. Evaluating very long-term conversational memory of llm agents. arXiv preprint arXiv: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+arXiv+preprint+arXiv%3A2402%2E17753%2E)
12. Long Ouyang, Jeff Wu, Xu Jiang, Diogo Almeida, Carroll L. Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, John Schulman, Jacob Hilton, Fraser Kelton, Luke Miller, Maddie Simens, Amanda Askell, Peter Welinder, Paul Christiano, Jan Leike, and Ryan Lowe. 2022. [Train…](https://md.research.elamur.ai/free/en/papers/ouyang-2022-training-language-models-follow-instructions/)
13. Rafael Rafailov, Archit Sharma, Eric Mitchell, Christopher D Manning, Stefano Ermon, and Chelsea Finn. 2023. [Direct preference optimization: Your language model is secretly a reward model](https://md.research.elamur.ai/free/en/papers/rafailov-2023-direct-preference-optimization-language-model/). Advances in neural information processing systems, 36:53728–53741.
14. Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J Liu. 2020. [Exploring the limits of transfer learning with a unified text-to-text transformer](https://md.research.elamur.ai/free/en/papers/raffel-2019-exploring-limits-transfer-learning-unified/). In Journal of Machine Learning Research. T5 Paper.
15. Zhuocheng Shen. 2024. Llm with tools: A survey. arXiv preprint arXiv:2409.18807. — [arXiv:2409.18807](https://arxiv.org/abs/2409.18807) [find](https://scholar.google.com/scholar?q=Zhuocheng+Shen%2E+2024%2E+Llm+with+tools%3A+A+survey%2E+arXiv+preprint+arXiv%3A2409%2E18807%2E+%E2%80%94+%5BarXiv%3A2409%2E18807%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2409%2E18807%29)
16. Feifan Song, Bowen Yu, Minghao Li, Haiyang Yu, Fei Huang, Yongbin Li, and Houfeng Wang. 2024. [Preference ranking optimization for human alignment](https://md.research.elamur.ai/free/en/papers/song-2023-preference-ranking-optimization-human-alignment/). In Proceedings of the AAAI Conference on Artificial Intelligence, volume 38, pages 18990–18998.
17. Haoran Sun, Haoyu Bian, Shaoning Zeng, Yunbo Rao, Xu Xu, Lin Mei, and Jianping Gou. 2025. Datasetagent: A novel multi-agent system for auto-constructing datasets from real-world images. Preprint, arXiv:2507.08648. — [arXiv:2507.08648](https://arxiv.org/abs/2507.08648) [find](https://scholar.google.com/scholar?q=Haoran+Sun%2C+Haoyu+Bian%2C+Shaoning+Zeng%2C+Yunbo+Rao%2C+Xu+Xu%2C+Lin+Mei%2C+and+Jianping+Gou%2E+2025%2E+Datasetagent%3A+A+novel+multi%2Dagent+system+for+auto%2Dconstructing+datasets+from+real%2Dworld+images%2E+Preprint%2C+arXi)
18. Haoran Sun and Shaoning Zeng. 2025. Introspection of thought helps ai agents. Preprint, arXiv:2507.08664. — [arXiv:2507.08664](https://arxiv.org/abs/2507.08664) [find](https://scholar.google.com/scholar?q=Haoran+Sun+and+Shaoning+Zeng%2E+2025%2E+Introspection+of+thought+helps+ai+agents%2E+Preprint%2C+arXiv%3A2507%2E08664%2E+%E2%80%94+%5BarXiv%3A2507%2E08664%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2507%2E08664%29)
19. Haoran Sun, Shaoning Zeng, and Bob Zhang. 2026. [H-MEM: Hierarchical memory for high-efficiency long-term reasoning in LLM agents](https://md.research.elamur.ai/free/en/papers/sun-2026-h-mem-hierarchical-memory-high/). In Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pages 341–350, Rabat, Morocco. Ass…
20. Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timothée Lacroix, Baptiste Rozière, Naman Goyal, Eric Hambro, Faisal Azhar, Aurelien Rodriguez, Armand Joulin, Edouard Grave, and Guillaume Lample. 2023. [Llama: Open and efficient foundation language models](https://md.research.elamur.ai/free/en/papers/touvron-2023-llama-open-efficient-foundation-language/). Preprint…
21. Lewis Tunstall, Edward Beeching, Nathan Lambert, Nazneen Rajani, Shengyi Huang, Kashif Rasul, Alvaro Bartolome, Alexander M. Rush, and Thomas Wolf. The Alignment Handbook. [find](https://scholar.google.com/scholar?q=Lewis+Tunstall%2C+Edward+Beeching%2C+Nathan+Lambert%2C+Nazneen+Rajani%2C+Shengyi+Huang%2C+Kashif+Rasul%2C+Alvaro+Bartolome%2C+Alexander+M%2E+Rush%2C+and+Thomas+Wolf%2E+The+Alignment+Handbook%2E)
22. Jianing Wang, Yang Zhou, Xiaocheng Zhang, Mengjiao Bao, and Peng Yan. 2025. Self-evolutionary large language models through uncertainty-enhanced preference optimization. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 39, pages 25362–25370. [find](https://scholar.google.com/scholar?q=Jianing+Wang%2C+Yang+Zhou%2C+Xiaocheng+Zhang%2C+Mengjiao+Bao%2C+and+Peng+Yan%2E+2025%2E+Self%2Devolutionary+large+language+models+through+uncertainty%2Denhanced+preference+optimization%2E+In+Proceedings+of+the+AAAI+Con)
23. Junchao Wu, Shu Yang, Runzhe Zhan, Yulin Yuan, Lidia Sam Chao, and Derek Fai Wong. 2025. [A survey on llm-generated text detection: Necessity, methods, and future directions](https://md.research.elamur.ai/free/en/papers/wu-2025-survey-llm-generated-text-detection/). Computational Linguistics, pages 1–66.
24. 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.
25. An Yang, Baosong Yang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Zhou, Chengpeng Li, Chengyuan Li, Dayiheng Liu, Fei Huang, Guanting Dong, Haoran Wei, Huan Lin, Jialong Tang, Jialin Wang, Jian Yang, Jianhong Tu, Jianwei Zhang, Jianxin Ma, and 40 others. 2024. Qwen2 technical report. arXiv preprint arXi… [find](https://scholar.google.com/scholar?q=An+Yang%2C+Baosong+Yang%2C+Binyuan+Hui%2C+Bo+Zheng%2C+Bowen+Yu%2C+Chang+Zhou%2C+Chengpeng+Li%2C+Chengyuan+Li%2C+Dayiheng+Liu%2C+Fei+Huang%2C+Guanting+Dong%2C+Haoran+Wei%2C+Huan+Lin%2C+Jialong+Tang%2C+Jialin+Wang%2C+Jian+Yang%2C+Jian)
26. Yifan Yao, Jinhao Duan, Kaidi Xu, Yuanfang Cai, Zhibo Sun, and Yue Zhang. 2024. [A survey on large language model (llm) security and privacy: The good, the bad, and the ugly](https://md.research.elamur.ai/free/en/papers/yao-2023-survey-large-language-model-llm/). High-Confidence Computing, page 100211.
27. Zihao Yi, Jiarui Ouyang, Yuwen Liu, Tianhao Liao, Zhe Xu, and Ying Shen. 2024. [A survey on recent advances in llm-based multi-turn dialogue systems](https://md.research.elamur.ai/free/en/papers/yi-2024-survey-recent-advances-llm-based/). arXiv preprint arXiv:2402.18013.
28. Hongyi Yuan, Zheng Yuan, Chuanqi Tan, Wei Wang, Songfang Huang, and Fei Huang. 2023. Rrhf: Rank responses to align language models with human feedback. Advances in Neural Information Processing Systems, 36:10935–10950. [find](https://scholar.google.com/scholar?q=Hongyi+Yuan%2C+Zheng+Yuan%2C+Chuanqi+Tan%2C+Wei+Wang%2C+Songfang+Huang%2C+and+Fei+Huang%2E+2023%2E+Rrhf%3A+Rank+responses+to+align+language+models+with+human+feedback%2E+Advances+in+Neural+Information+Processing+System)
29. Yongcheng Zeng, Xinyu Cui, Xuanfa Jin, Guoqing Liu, Zexu Sun, Dong Li, Ning Yang, Jianye Hao, Haifeng Zhang, and Jun Wang. 2025. Evolving llms’ self-refinement capability via iterative preference optimization. arXiv preprint arXiv:2502.05605. — [arXiv:2502.05605](https://arxiv.org/abs/2502.05605) [find](https://scholar.google.com/scholar?q=Yongcheng+Zeng%2C+Xinyu+Cui%2C+Xuanfa+Jin%2C+Guoqing+Liu%2C+Zexu+Sun%2C+Dong+Li%2C+Ning+Yang%2C+Jianye+Hao%2C+Haifeng+Zhang%2C+and+Jun+Wang%2E+2025%2E+Evolving+llms%E2%80%99+self%2Drefinement+capability+via+iterative+preference+opti)
30. Zeyu Zhang, Xiaohe Bo, Chen Ma, Rui Li, Xu Chen, Quanyu Dai, Jieming Zhu, Zhenhua Dong, and Ji-Rong Wen. 2024. A survey on the memory mechanism of large language model based agents. arXiv preprint arXiv:2404.13501. [find](https://scholar.google.com/scholar?q=Zeyu+Zhang%2C+Xiaohe+Bo%2C+Chen+Ma%2C+Rui+Li%2C+Xu+Chen%2C+Quanyu+Dai%2C+Jieming+Zhu%2C+Zhenhua+Dong%2C+and+Ji%2DRong+Wen%2E+2024%2E+A+survey+on+the+memory+mechanism+of+large+language+model+based+agents%2E+arXiv+preprint+arX)
31. Wenting Zhao, Xiang Ren, Jack Hessel, Claire Cardie, Yejin Choi, and Yuntian Deng. 2024. [Wildchat: 1m chatgpt interaction logs in the wild](https://md.research.elamur.ai/free/en/papers/zhao-2024-wildchat-1m-chatgpt-interaction-logs/). Preprint, arXiv:2405.01470.
32. Lianmin Zheng, Wei-Lin Chiang, Ying Sheng, Siyuan Zhuang, Zhanghao Wu, Yonghao Zhuang, Zi Lin, Zhuohan Li, Dacheng Li, Eric. P Xing, Hao Zhang, Joseph E. Gonzalez, and Ion Stoica. 2023. [Judging llm-as-a-judge with mt-bench and chatbot arena](https://md.research.elamur.ai/free/en/papers/zheng-2023-judging-llm-judge-mt-bench/). Preprint, arXiv:2306.05685.
33. 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](https://scholar.google.com/scholar?q=Wanjun+Zhong%2C+Lianghong+Guo%2C+Qiqi+Gao%2C+He+Ye%2C+and+Yanlin+Wang%2E+2024%2E+Memorybank%3A+Enhancing+large+language+models+with+long%2Dterm+memory%2E+In+Proceedings+of+the+AAAI+Conference+on+Artificial+Intelligence)

*Updated 1 November 2026*