---
title: "From Experience to Skill — paper by Wu et al. (2026)"
description: "The authors treat GEO as a strategy learning problem and introduce MAGEO. 31 references."
authors: ["Beining Wu", "Fuyou Mao", "Jiong Lin", "Cheng Yang", "Jiaxuan Lu", "Yifu Guo", "Siyu Zhang", "Yifan Wu", "Ying Huang", "Fu Li"]
year: 2026
venue: "Findings of the Association for Computational Linguistics: ACL 2026"
source: "https://aclanthology.org/2026.findings-acl.2149/"
doi: "10.18653/v1/2026.findings-acl.2149"
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/wu-2026-experience-skill-multi-agent-generative/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/wu-2026-experience-skill-multi-agent-generative/)

[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/34/) / From Experience to Skill: Multi-Agent Generative Engine Optimization via Reusable Strategy Learning

# From Experience to Skill: Multi-Agent Generative Engine Optimization via Reusable Strategy Learning

**Authors:** Beining Wu, Fuyou Mao, Jiong Lin, [Cheng Yang](https://md.research.elamur.ai/free/en/authors/cheng-hong-yang/), Jiaxuan Lu, [Yifu Guo](https://md.research.elamur.ai/free/en/authors/yifu-guo/), Siyu Zhang, [Yifan Wu](https://md.research.elamur.ai/free/en/authors/yifan-wu/), Ying Huang and Fu Li · **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.2149/) · [PDF](https://aclanthology.org/2026.findings-acl.2149.pdf) · [DOI 10.18653/v1/2026.findings-acl.2149](https://doi.org/10.18653/v1/2026.findings-acl.2149) · [OpenAlex](https://openalex.org/W7166812840)

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

## Summary
Generative engines now answer queries with synthesized, cited responses rather than ranked links. Web creators therefore need Generative Engine Optimization (GEO), but existing GEO methods tune each document separately and keep no record of what worked. The authors treat GEO as a strategy learning problem and introduce MAGEO. In this multi-agent system, Preference, Planner, Editor and Evaluator agents iteratively rewrite a target document. A Skill Bank stores successful editing patterns, organized by engine and scenario, so they can be reused in later tasks. To measure the effect of an edit causally, a Twin Branch Evaluation Protocol fixes the retrieval list and compares engine answers with the original document and with the edited one. A new metric, DSV-CF, scores semantic visibility together with citation correctness. The authors also release MSME-GEO-Bench, built from real-world queries across several scenarios and engines. On three mainstream engines, MAGEO clearly beats heuristic GEO in both visibility and citation fidelity. This positions GEO as cumulative skill learning rather than ad hoc rule tweaking.

## Key points
- **Results with GPT-5.2 on MSME-GEO-Bench:**
  - WLV rises from 1.33 for the GEO Quote heuristic to 3.95 for MAGEO Lite and 4.52 for MAGEO Full.
  - The false-citation ratio drops from 0.058 to 0.047 (Lite) and 0.043 (Full).
- **Cost:**
  - Average tokens per query: 5.7k for GEO Quote, 8.9k for Lite, 12.4k for Full.
  - Latency grows to 38.7s for Full, so the authors recommend Lite for cost-sensitive use.
- **Ablations:** WLV falls to 2.08 without engine preference modeling and to 1.41 without the Skill Bank.
- **Combinatorial baseline:** stacking four heuristics (More Quotes, Citing Source, Authoritative, Technical Terms) reaches only 1.90 WLV. This suggests the gains are not just additive rule composition.
- **Limitations:**
  - Higher inference cost than heuristic methods.
  - Possible bias from using Gemini-3 Pro for benchmark annotation.
  - No formal analysis of how skills generalize.
  - Text-only scope; multimodal GEO is not covered.

*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

- [Hong Kong University of Science and Technology](https://md.research.elamur.ai/free/en/universities/hong-kong-university-of-science-and-technology/) — University, Hong Kong, China · 170 works · 26,341 citations
- [Shanghai Artificial Intelligence Laboratory](https://md.research.elamur.ai/free/en/labs/shanghai-artificial-intelligence-laboratory/) — Research institute, Shanghai, China · 152 works · 13,166 citations
- [Sun Yat-sen University](https://md.research.elamur.ai/free/en/universities/sun-yat-sen-university/) — University, Guangzhou, China · 72 works · 9,502 citations
- [Central South University](https://md.research.elamur.ai/free/en/universities/central-south-university/) — University, Changsha, China · 23 works · 657 citations
- [Hangzhou Dianzi University](https://md.research.elamur.ai/free/en/universities/hangzhou-dianzi-university/) — University, Hangzhou, China · 15 works · 1,061 citations

📚 Shelves (2): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🗄️ Information Systems](https://md.research.elamur.ai/free/en/shelves/computer-science/information-systems/) · 1,730 works

## Cite

Cite as: Beining Wu, Fuyou Mao, Jiong Lin, Cheng Yang, Jiaxuan Lu, Yifu Guo, Siyu Zhang, Yifan Wu, Ying Huang and Fu Li. 2026. From Experience to Skill: Multi-Agent Generative Engine Optimization via Reusable Strategy Learning. 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{wu2026experience,
  title = {{From Experience to Skill: Multi-Agent Generative Engine Optimization via Reusable Strategy Learning}},
  author = {Beining Wu, Fuyou Mao, Jiong Lin, Cheng Yang, Jiaxuan Lu, Yifu Guo, Siyu Zhang, Yifan Wu, Ying Huang and Fu Li},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.2149},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.2149}
}
```

- [← previous From Emotion to Expression: Theoretical Foundations and Resources for Fear Speech](https://md.research.elamur.ai/free/en/papers/shankaran-2026-emotion-expression-theoretical-foundations-resources/)
- [next → From Explicit to Implicit: A Theoretical Framework and Transfer Method for Preference Internalization in Language Models](https://md.research.elamur.ai/free/en/papers/wang-2026-explicit-implicit-theoretical-framework-transfer/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/34/)

## References

31 references, 8 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Pranjal Aggarwal, Vishvak Murahari, Tanmay Rajpurohit, Ashwin Kalyan, Karthik Narasimhan, and Ameet Deshpande. 2024. Geo: Generative engine optimization. In Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pages 5–16. [find](https://scholar.google.com/scholar?q=Pranjal+Aggarwal%2C+Vishvak+Murahari%2C+Tanmay+Rajpurohit%2C+Ashwin+Kalyan%2C+Karthik+Narasimhan%2C+and+Ameet+Deshpande%2E+2024%2E+Geo%3A+Generative+engine+optimization%2E+In+Proceedings+of+the+30th+ACM+SIGKDD+Conferen)
2. Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil, and Hannaneh Hajishirzi. 2024. [Self-rag: Learning to retrieve, generate, and critique through self-reflection](https://md.research.elamur.ai/free/en/papers/asai-2023-self-rag-learning-retrieve-generate/). In The Twelfth International Conference on Learning Representations.
3. Jinze Bai, Shuai Bai, Yunfei Chu, Zeyu Cui, Kai Dang, Xiaodong Deng, Yang Fan, Wenbin Ge, Yu Han, Fei Huang, and 1 others. 2023. [Qwen technical report](https://md.research.elamur.ai/free/en/papers/bai-2023-qwen-technical-report/). arXiv preprint arXiv:2309.16609.
4. Xiaohe Bo, Zeyu Zhang, Quanyu Dai, Xueyang Feng, Lei Wang, Rui Li, Xu Chen, and Ji-Rong Wen. 2024. Reflective multi-agent collaboration based on large language models. In Advances in Neural Information Processing Systems, volume 37. [find](https://scholar.google.com/scholar?q=Xiaohe+Bo%2C+Zeyu+Zhang%2C+Quanyu+Dai%2C+Xueyang+Feng%2C+Lei+Wang%2C+Rui+Li%2C+Xu+Chen%2C+and+Ji%2DRong+Wen%2E+2024%2E+Reflective+multi%2Dagent+collaboration+based+on+large+language+models%2E+In+Advances+in+Neural+Informatio)
5. Qiyuan Chen, Jiahe Chen, Hongsen Huang, Qian Shao, Jintai Chen, Renjie Hua, Hongxia Xu, Ruijia Wu, Ren Chuan, and Jian Wu. 2025a. Cc-gseo-bench: A content-centric benchmark for measuring source influence in generative search engines. Preprint, arXiv:2509.05607. — [arXiv:2509.05607](https://arxiv.org/abs/2509.05607) [find](https://scholar.google.com/scholar?q=Qiyuan+Chen%2C+Jiahe+Chen%2C+Hongsen+Huang%2C+Qian+Shao%2C+Jintai+Chen%2C+Renjie+Hua%2C+Hongxia+Xu%2C+Ruijia+Wu%2C+Ren+Chuan%2C+and+Jian+Wu%2E+2025a%2E+Cc%2Dgseo%2Dbench%3A+A+content%2Dcentric+benchmark+for+measuring+source+influe)
6. Xiaolu Chen, Haojie Wu, Jie Bao, Zhen Chen, Yong Liao, and Hu Huang. 2025b. Role-augmented intent-driven generative search engine optimization. arXiv preprint arXiv:2508.11158. — [arXiv:2508.11158](https://arxiv.org/abs/2508.11158) [find](https://scholar.google.com/scholar?q=Xiaolu+Chen%2C+Haojie+Wu%2C+Jie+Bao%2C+Zhen+Chen%2C+Yong+Liao%2C+and+Hu+Huang%2E+2025b%2E+Role%2Daugmented+intent%2Ddriven+generative+search+engine+optimization%2E+arXiv+preprint+arXiv%3A2508%2E11158%2E+%E2%80%94+%5BarXiv%3A2508%2E11158%5D%28ht)
7. Ruining Chong, Cunliang Kong, Liu Wu, Zhenghao Liu, Ziye Jin, Liner Yang, Yange Fan, Hanghang Fan, and Erhong Yang. 2023. Leveraging prefix transfer for multi-intent text revision. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pa… [find](https://scholar.google.com/scholar?q=Ruining+Chong%2C+Cunliang+Kong%2C+Liu+Wu%2C+Zhenghao+Liu%2C+Ziye+Jin%2C+Liner+Yang%2C+Yange+Fan%2C+Hanghang+Fan%2C+and+Erhong+Yang%2E+2023%2E+Leveraging+prefix+transfer+for+multi%2Dintent+text+revision%2E+In+Proceedings+of+t)
8. Michael D. Godlevsky, Sergey V. Orekhov, and Elena Orekhova. 2017. Theoretical fundamentals of search engine optimization based on machine learning. In International Conference on Information and Communication Technologies in Education, Research, and Industrial Applications. [find](https://scholar.google.com/scholar?q=Michael+D%2E+Godlevsky%2C+Sergey+V%2E+Orekhov%2C+and+Elena+Orekhova%2E+2017%2E+Theoretical+fundamentals+of+search+engine+optimization+based+on+machine+learning%2E+In+International+Conference+on+Information+and+Comm)
9. Priyanshu Gupta, Shashank Kirtania, Ananya Singha, Sumit Gulwani, Arjun Radhakrishna, Gustavo Soares, and Sherry Shi. 2024. Metareflection: Learning instructions for language agents using past reflections. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pag… [find](https://scholar.google.com/scholar?q=Priyanshu+Gupta%2C+Shashank+Kirtania%2C+Ananya+Singha%2C+Sumit+Gulwani%2C+Arjun+Radhakrishna%2C+Gustavo+Soares%2C+and+Sherry+Shi%2E+2024%2E+Metareflection%3A+Learning+instructions+for+language+agents+using+past+reflect)
10. Zihan Huang, Tao Wu, Wang Lin, Shengyu Zhang, Jingyuan Chen, and Fei Wu. 2025. Autogeo: Automating geometric image dataset creation for enhanced geometry understanding. IEEE Transactions on Multimedia. [find](https://scholar.google.com/scholar?q=Zihan+Huang%2C+Tao+Wu%2C+Wang+Lin%2C+Shengyu+Zhang%2C+Jingyuan+Chen%2C+and+Fei+Wu%2E+2025%2E+Autogeo%3A+Automating+geometric+image+dataset+creation+for+enhanced+geometry+understanding%2E+IEEE+Transactions+on+Multimedia)
11. Jiajie Jin, Xiaoxi Li, Guanting Dong, Yuyao Zhang, Yutao Zhu, Yongkang Wu, Zhonghua Li, Ye Qi, and Zhicheng Dou. 2025. [Hierarchical document refinement for long-context retrieval-augmented generation](https://md.research.elamur.ai/free/en/papers/jin-2025-hierarchical-document-refinement-long-context/). In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume…
12. 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](https://md.research.elamur.ai/free/en/papers/lewis-2020-retrieval-augmented-generation-knowledge-intensive/). Preprint, arXiv:2005.11401.
13. Xiaoxi Li, Guanting Dong, Jiajie Jin, Yuyao Zhang, Yujia Zhou, Yutao Zhu, Peitian Zhang, and Zhicheng Dou. 2025a. [Search-o1: Agentic search-enhanced large reasoning models](https://md.research.elamur.ai/free/en/papers/li-2025-search-o1-agentic-search-enhanced/). In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 5420–5438, Suzhou, China.
14. Yang Li, Mingxuan Luo, Yeyun Gong, Chen Lin, Jian Jiao, Yi Liu, and Kaili Huang. 2025b. Deepthink: Aligning language models with domain-specific user intents. Preprint, arXiv:2502.05497. — [arXiv:2502.05497](https://arxiv.org/abs/2502.05497) [find](https://scholar.google.com/scholar?q=Yang+Li%2C+Mingxuan+Luo%2C+Yeyun+Gong%2C+Chen+Lin%2C+Jian+Jiao%2C+Yi+Liu%2C+and+Kaili+Huang%2E+2025b%2E+Deepthink%3A+Aligning+language+models+with+domain%2Dspecific+user+intents%2E+Preprint%2C+arXiv%3A2502%2E05497%2E+%E2%80%94+%5BarXiv%3A2502)
15. Tian Liang, Zhiwei He, Wenxiang Jiao, Xing Wang, Yan Wang, Rui Wang, Yujiu Yang, Shuming Shi, and Zhaopeng Tu. 2024. [Encouraging divergent thinking in large language models through multi-agent debate](https://md.research.elamur.ai/free/en/papers/liang-2023-encouraging-divergent-thinking-large-language/). In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 17…
16. Nora Freya Lindemann. 2025. Chatbots, search engines, and the sealing of knowledges. AI & SOCI-ETY, 40(6):5063–5076. [find](https://scholar.google.com/scholar?q=Nora+Freya+Lindemann%2E+2025%2E+Chatbots%2C+search+engines%2C+and+the+sealing+of+knowledges%2E+AI+%26+SOCI%2DETY%2C+40%286%29%3A5063%E2%80%935076%2E)
17. Konstantinos I Roumeliotis and Nikolaos D Tselikas. 2023. Chatgpt and open-ai models: A preliminary review. Future Internet, 15(6):192. [find](https://scholar.google.com/scholar?q=Konstantinos+I+Roumeliotis+and+Nikolaos+D+Tselikas%2E+2023%2E+Chatgpt+and+open%2Dai+models%3A+A+preliminary+review%2E+Future+Internet%2C+15%286%29%3A192%2E)
18. Dongyu Ru, Lin Qiu, Xiangkun Hu, Tianhang Zhang, Peng Shi, Shuaichen Chang, Cheng Jiayang, Cunxiang Wang, Shichao Sun, Huanyu Li, Zizhao Zhang, Binjie Wang, Jiarong Jiang, Tong He, Zhiguo Wang, Pengfei Liu, Yue Zhang, and Zheng Zhang. 2024. Ragchecker: A fine-grained framework for diagnosing retriev… [find](https://scholar.google.com/scholar?q=Dongyu+Ru%2C+Lin+Qiu%2C+Xiangkun+Hu%2C+Tianhang+Zhang%2C+Peng+Shi%2C+Shuaichen+Chang%2C+Cheng+Jiayang%2C+Cunxiang+Wang%2C+Shichao+Sun%2C+Huanyu+Li%2C+Zizhao+Zhang%2C+Binjie+Wang%2C+Jiarong+Jiang%2C+Tong+He%2C+Zhiguo+Wang%2C+Pengfe)
19. Reijo Savolainen. 2010. Everyday life information seeking. [find](https://scholar.google.com/scholar?q=Reijo+Savolainen%2E+2010%2E+Everyday+life+information+seeking%2E)
20. Weijia Shi, Sewon Min, Michihiro Yasunaga, Minjoon Seo, Richard James, Mike Lewis, Luke Zettlemoyer, and Wen tau Yih. 2024. [Replug: Retrieval-augmented black-box language models](https://md.research.elamur.ai/free/en/papers/shi-2023-replug-retrieval-augmented-black-box/). In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Hum…
21. Me Sun and Le Yu. 2025. Ai-driven sem keyword optimization and consumer search intent prediction: An intelligent approach to search engine marketing. Journal of Sustainability, Policy, and Practice, 1(3):26–39. trace with difficulty-aware prompting. arXiv preprint arXiv:2505.19716. — [arXiv:2505.19716](https://arxiv.org/abs/2505.19716) [find](https://scholar.google.com/scholar?q=Me+Sun+and+Le+Yu%2E+2025%2E+Ai%2Ddriven+sem+keyword+optimization+and+consumer+search+intent+prediction%3A+An+intelligent+approach+to+search+engine+marketing%2E+Journal+of+Sustainability%2C+Policy%2C+and+Practice%2C+1)
22. Cheng Yang, Hui Jin, Xinlei Yu, Zhipeng Wang, Yao-qun Liu, Fenglei Fan, Dajiang Lei, Gangyong Jia, Changmiao Wang, and Ruiquan Ge. 2026. Lungn-oduleagent: A collaborative multi-agent system for precision diagnosis of lung nodules. In Proceedings of the AAAI Conference on Artificial Intelligence, vol… [find](https://scholar.google.com/scholar?q=Cheng+Yang%2C+Hui+Jin%2C+Xinlei+Yu%2C+Zhipeng+Wang%2C+Yao%2Dqun+Liu%2C+Fenglei+Fan%2C+Dajiang+Lei%2C+Gangyong+Jia%2C+Changmiao+Wang%2C+and+Ruiquan+Ge%2E+2026%2E+Lungn%2Doduleagent%3A+A+collaborative+multi%2Dagent+system+for+precis)
23. Cheng Yang, Jiaxuan Lu, Haiyuan Wan, Junchi Yu, and Feiwei Qin. 2025. From what to why: A multi-agent system for evidence-based chemical reaction condition reasoning. arXiv preprint arXiv:2509.23768. — [arXiv:2509.23768](https://arxiv.org/abs/2509.23768) [find](https://scholar.google.com/scholar?q=Cheng+Yang%2C+Jiaxuan+Lu%2C+Haiyuan+Wan%2C+Junchi+Yu%2C+and+Feiwei+Qin%2E+2025%2E+From+what+to+why%3A+A+multi%2Dagent+system+for+evidence%2Dbased+chemical+reaction+condition+reasoning%2E+arXiv+preprint+arXiv%3A2509%2E23768%2E+)
24. Xinlei Yu, Chengming Xu, Zhangquan Chen, Bo Yin, Cheng Yang, Yongbo He, Yihao Hu, Jiangning Zhang, Cheng Tan, Xiaobin Hu, and 1 others. 2026. Dual latent memory for visual multi-agent system. arXiv preprint arXiv:2602.00471. — [arXiv:2602.00471](https://arxiv.org/abs/2602.00471) [find](https://scholar.google.com/scholar?q=Xinlei+Yu%2C+Chengming+Xu%2C+Zhangquan+Chen%2C+Bo+Yin%2C+Cheng+Yang%2C+Yongbo+He%2C+Yihao+Hu%2C+Jiangning+Zhang%2C+Cheng+Tan%2C+Xiaobin+Hu%2C+and+1+others%2E+2026%2E+Dual+latent+memory+for+visual+multi%2Dagent+system%2E+arXiv+pr)
25. Xinlei Yu, Chengming Xu, Zhangquan Chen, Yudong Zhang, Shilin Lu, Cheng Yang, Jiangning Zhang, Shuicheng Yan, and Xiaobin Hu. 2025. Visual document understanding and reasoning: A multi-agent collaboration framework with agent-wise adaptive test-time scaling. arXiv preprint arXiv:2508.03404. — [arXiv:2508.03404](https://arxiv.org/abs/2508.03404) [find](https://scholar.google.com/scholar?q=Xinlei+Yu%2C+Chengming+Xu%2C+Zhangquan+Chen%2C+Yudong+Zhang%2C+Shilin+Lu%2C+Cheng+Yang%2C+Jiangning+Zhang%2C+Shuicheng+Yan%2C+and+Xiaobin+Hu%2E+2025%2E+Visual+document+understanding+and+reasoning%3A+A+multi%2Dagent+collabora)
26. Yue Yu, Wei Ping, Zihan Liu, Boxin Wang, Jiaxuan You, Chao Zhang, Mohammad Shoeybi, and Bryan Catanzaro. 2024. Rankrag: Unifying context ranking with retrieval-augmented generation in llms. In Advances in Neural Information Processing Systems, volume 37. [find](https://scholar.google.com/scholar?q=Yue+Yu%2C+Wei+Ping%2C+Zihan+Liu%2C+Boxin+Wang%2C+Jiaxuan+You%2C+Chao+Zhang%2C+Mohammad+Shoeybi%2C+and+Bryan+Catanzaro%2E+2024%2E+Rankrag%3A+Unifying+context+ranking+with+retrieval%2Daugmented+generation+in+llms%2E+In+Advance)
27. 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)
28. Annalisa Szymanski, Noah Ziems, Heather A Eicher-Miller, Toby Jia-Jun Li, Meng Jiang, and Ronald A Metoyer. 2025. Limitations of the llm-as-a-judge approach for evaluating llm outputs in expert knowledge tasks. In Proceedings of the 30th International Conference on Intelligent User Interfaces, pages… [find](https://scholar.google.com/scholar?q=Annalisa+Szymanski%2C+Noah+Ziems%2C+Heather+A+Eicher%2DMiller%2C+Toby+Jia%2DJun+Li%2C+Meng+Jiang%2C+and+Ronald+A+Metoyer%2E+2025%2E+Limitations+of+the+llm%2Das%2Da%2Djudge+approach+for+evaluating+llm+outputs+in+expert+knowle)
29. Gemini Team, Rohan Anil, Sebastian Borgeaud, Jean-Baptiste Alayrac, Jiahui Yu, Radu Soricut, Johan Schalkwyk, Andrew M Dai, Anja Hauth, Katie Millican, and 1 others. 2023. [Gemini: a family of highly capable multimodal models](https://md.research.elamur.ai/free/en/papers/gemini-team-2023-gemini-family-highly-capable-multimodal/). arXiv preprint arXiv:2312.11805.
30. Xiaoqiang Wang, Suyuchen Wang, Yun Zhu, and Bang Liu. 2025. R 3 mem: Bridging memory retention and retrieval via reversible compression. In Findings of the Association for Computational Linguistics: ACL 2025, pages 4541–4557, Vienna, Austria. [find](https://scholar.google.com/scholar?q=Xiaoqiang+Wang%2C+Suyuchen+Wang%2C+Yun+Zhu%2C+and+Bang+Liu%2E+2025%2E+R+3+mem%3A+Bridging+memory+retention+and+retrieval+via+reversible+compression%2E+In+Findings+of+the+Association+for+Computational+Linguistics%3A+A)
31. Yifan Wu, Jingze Shi, Bingheng Wu, Jiayi Zhang, Xiaotian Lin, Nan Tang, and Yuyu Luo. 2025. Concise reasoning, big gains: Pruning long reasoning [find](https://scholar.google.com/scholar?q=Yifan+Wu%2C+Jingze+Shi%2C+Bingheng+Wu%2C+Jiayi+Zhang%2C+Xiaotian+Lin%2C+Nan+Tang%2C+and+Yuyu+Luo%2E+2025%2E+Concise+reasoning%2C+big+gains%3A+Pruning+long+reasoning)

*Updated 2 November 2026*