---
title: "Large Language Model Agent — paper by Luo et al. (2025)"
description: "Its core is a \"Build–Collaborate–Evolve\" framework: Build: how a single agent is assembled. 27 references, cited by 54 papers here."
authors: ["Junyu Luo", "Weizhi Zhang", "Ye Yuan", "Yusheng Zhao", "Junwei Yang", "Yiyang Gu", "Bohan Wu", "Binqi Chen", "Ziyue Qiao", "Qingqing Long", "Rongcheng Tu", "Xiao Luo", "Wei Ju", "Zhiping Xiao", "Yifan Wang", "Meng Xiao", "Chenwu Liu", "Jingyang Yuan", "Shichang Zhang", "Yiqiao Jin", "Fan Zhang", "Xian Wu", "Hanqing Zhao", "Dacheng Tao", "Philip S. Yu", "Ming Zhang"]
year: 2025
venue: "arXiv:2503.21460"
source: "https://arxiv.org/abs/2503.21460"
doi: "10.48550/arxiv.2503.21460"
arxiv: "2503.21460"
licence: "CC BY 4.0 (arXiv)"
licence_url: "http://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/luo-2025-large-language-model-agent-survey/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/luo-2025-large-language-model-agent-survey/)

[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/2/) / Large Language Model Agent: A Survey on Methodology, Applications and Challenges

# Large Language Model Agent: A Survey on Methodology, Applications and Challenges

**Authors:** [Junyu Luo](https://md.research.elamur.ai/free/en/authors/junyu-luo/), Weizhi Zhang, Ye Yuan, [Yusheng Zhao](https://md.research.elamur.ai/free/en/authors/yusheng-zhao/), Junwei Yang, Yiyang Gu, Bohan Wu, Binqi Chen, Ziyue Qiao, Qingqing Long, Rongcheng Tu, Xiao Luo, Wei Ju, Zhiping Xiao, Yifan Wang, Meng Xiao, Chenwu Liu, Jingyang Yuan, Shichang Zhang, Yiqiao Jin, Fan Zhang, Xian Wu, Hanqing Zhao, [Dacheng Tao](https://md.research.elamur.ai/free/en/authors/dacheng-tao/), [Philip S. Yu](https://md.research.elamur.ai/free/en/authors/philip-s-yu/) and [Ming Zhang](https://md.research.elamur.ai/free/en/authors/ming-zhang/) · **Year:** 2025 · **Venue:** arXiv:2503.21460 · **Licence:** [CC BY 4.0 (arXiv)](http://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://arxiv.org/abs/2503.21460) · [PDF](https://arxiv.org/pdf/2503.21460) · [DOI 10.48550/arxiv.2503.21460](https://doi.org/10.48550/arxiv.2503.21460) · [arXiv 2503.21460](https://arxiv.org/abs/2503.21460) · [OpenAlex](https://openalex.org/W4415062702)

**Citations:** 5 citations (OpenAlex, 2026-10-14) · 54 in our library, of the 141,840 papers whose bibliographies we read

## Summary
Work on LLM-based agents has grown quickly but remains scattered. Existing reviews tend to cover one slice, such as games, deployment settings, multimodality or security, or they give broad overviews without a method-level breakdown. Luo et al. address this with a survey built around how agents are engineered. Its core is a "Build–Collaborate–Evolve" framework:

- **Build:** how a single agent is assembled.
- **Collaborate:** how several agents coordinate.
- **Evolve:** how agents improve through self-learning, interaction or outside knowledge.

Around this core the authors also cover benchmarks and tooling, real-world risks (security, privacy, social impact) and application areas from the natural sciences to medicine and gaming. The result is a resource rather than an experiment: a structured map that places hundreds of papers in one taxonomy, plus a curated, maintained paper list on GitHub (Awesome-Agent-Papers). It is useful as an orientation guide for anyone designing or comparing agent systems. It also makes explicit how single-agent design choices connect to multi-agent behavior, which earlier surveys usually treated separately.

## Key points
- **Agent construction** rests on four interlocking components: profile definition, memory, planning and action execution. Profiles can be human-curated (e.g., CAMEL, AutoGen, MetaGPT, ChatDev) or generated dynamically (e.g., Generative Agents, RecAgent, DSPy).
- **Memory** is split into three types:
  - short-term memory (ReAct, Graph of Thoughts);
  - long-term memory (Voyager, Reflexion, MemGPT);
  - retrieval used as memory (RAG, GraphRAG, DeepRAG).
- **Collaboration** is classified as centralized (Coscientist, MetaGPT), decentralized (MedAgents, multi-agent debate) or hybrid (KnowAgent, TextGrad).
- **Evolution** covers three routes: self-improvement (SELF-REFINE, STaR, Self-Rewarding), multi-agent co-evolution, and learning from external resources (CRITIC).
- **Real-world risks** are grouped into:
  - agent-centric and data-centric security;
  - privacy issues such as memorization and IP exploitation;
  - ethics.
- The survey (arXiv:2503.21460v1, March 2025) cites over 300 references.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

📚 Shelves (2): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 9,085 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 8,888 works

## Cite

Cite as: Junyu Luo, Weizhi Zhang, Ye Yuan, Yusheng Zhao, Junwei Yang, Yiyang Gu, Bohan Wu, Binqi Chen, Ziyue Qiao, Qingqing Long, Rongcheng Tu, Xiao Luo, Wei Ju, Zhiping Xiao, Yifan Wang, Meng Xiao, Chenwu Liu, Jingyang Yuan, Shichang Zhang, Yiqiao Jin, Fan Zhang, Xian Wu, Hanqing Zhao, Dacheng Tao, Philip S. Yu and Ming Zhang. 2025. Large Language Model Agent: A Survey on Methodology, Applications and Challenges. arXiv:2503.21460.

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

```bibtex
@misc{luo2025large,
  title = {{Large Language Model Agent: A Survey on Methodology, Applications and Challenges}},
  author = {Junyu Luo, Weizhi Zhang, Ye Yuan, Yusheng Zhao, Junwei Yang, Yiyang Gu, Bohan Wu, Binqi Chen, Ziyue Qiao, Qingqing Long, Rongcheng Tu, Xiao Luo, Wei Ju, Zhiping Xiao, Yifan Wang, Meng Xiao, Chenwu Liu, Jingyang Yuan, Shichang Zhang, Yiqiao Jin, Fan Zhang, Xian Wu, Hanqing Zhao, Dacheng Tao, Philip S. Yu and Ming Zhang},
  year = {2025},
  doi = {10.48550/arxiv.2503.21460},
  eprint = {2503.21460},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2503.21460}
}
```

- [← previous LegalAgentBench: Evaluating LLM Agents in Legal Domain](https://md.research.elamur.ai/free/en/papers/li-2025-legalagentbench-evaluating-llm-agents-legal/)
- [next → mmBERT: A Modern Multilingual Encoder with Annealed Language Learning](https://md.research.elamur.ai/free/en/papers/marone-2025-mmbert-modern-multilingual-encoder-annealed/)
- [↑ back to papers of 2025](https://md.research.elamur.ai/free/en/papers/2025/page/2/)

## References

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

1. S. Wu, S. Zhao, Q. Huang, K. Huang, M. Yasunaga, K. Cao, V. Ioannidis, K. Subbian, J. Leskovec, and J. Y. Zou, “Avatar: Optimizing llm agents for tool usage via contrastive reasoning,” NeurIPS, vol. 37, pp. 25 981–26 010, 2025. Y. Huang, J. Sansom, Z. Ma, F. Gervits, and J. Chai, “Drivlme: Enhancing… [find](https://scholar.google.com/scholar?q=S%2E+Wu%2C+S%2E+Zhao%2C+Q%2E+Huang%2C+K%2E+Huang%2C+M%2E+Yasunaga%2C+K%2E+Cao%2C+V%2E+Ioannidis%2C+K%2E+Subbian%2C+J%2E+Leskovec%2C+and+J%2E+Y%2E+Zou%2C+%E2%80%9CAvatar%3A+Optimizing+llm+agents+for+tool+usage+via+contrastive+reasoning%2C%E2%80%9D+NeurIPS%2C+vol%2E+3)
2. IEEE, 2024, pp. 3153–3160. Y. Zhang, S. Yang, C. Bai, F. Wu, X. Li, Z. Wang, and X. Li, “Towards efficient llm grounding for embodied multi-agent collaboration,” arXiv preprint arXiv:2405.14314, 2024. B. Colle, “Improving embodied llm agents capabilities through collaboration,” 2024. D. A. Boiko, R.… [find](https://scholar.google.com/scholar?q=IEEE%2C+2024%2C+pp%2E+3153%E2%80%933160%2E+Y%2E+Zhang%2C+S%2E+Yang%2C+C%2E+Bai%2C+F%2E+Wu%2C+X%2E+Li%2C+Z%2E+Wang%2C+and+X%2E+Li%2C+%E2%80%9CTowards+efficient+llm+grounding+for+embodied+multi%2Dagent+collaboration%2C%E2%80%9D+arXiv+preprint+arXiv%3A2405%2E14314%2C+2024%2E)
3. IEEE, 2024, pp. 102–103. Q. Zhong, L. Ding, J. Liu, B. Du, and D. Tao, “Self-evolution learning for discriminative language model pretraining,” in ACL Findings, 2023, pp. 4130–4145. T. Akiba, M. Shing, Y. Tang, Q. Sun, and D. Ha, “Evolutionary optimization of model merging recipes,” Nature Machine I… [find](https://scholar.google.com/scholar?q=IEEE%2C+2024%2C+pp%2E+102%E2%80%93103%2E+Q%2E+Zhong%2C+L%2E+Ding%2C+J%2E+Liu%2C+B%2E+Du%2C+and+D%2E+Tao%2C+%E2%80%9CSelf%2Devolution+learning+for+discriminative+language+model+pretraining%2C%E2%80%9D+in+ACL+Findings%2C+2023%2C+pp%2E+4130%E2%80%934145%2E+T%2E+Akiba%2C+M%2E+Shing)
4. W. Yuan, R. Y. Pang, K. Cho, X. Li, S. Sukhbaatar, J. Xu, and J. Weston, “Self-rewarding language models,” 2024. [94] K. Yang, D. Klein, A. Celikyilmaz, N. Peng, and Y. Tian, “Rlcd: Reinforcement learning from contrastive distillation for lm alignment,” in ICLR, 2024. [95] J.-C. Pang, P. Wang, K. Li… [find](https://scholar.google.com/scholar?q=W%2E+Yuan%2C+R%2E+Y%2E+Pang%2C+K%2E+Cho%2C+X%2E+Li%2C+S%2E+Sukhbaatar%2C+J%2E+Xu%2C+and+J%2E+Weston%2C+%E2%80%9CSelf%2Drewarding+language+models%2C%E2%80%9D+2024%2E+%5B94%5D+K%2E+Yang%2C+D%2E+Klein%2C+A%2E+Celikyilmaz%2C+N%2E+Peng%2C+and+Y%2E+Tian%2C+%E2%80%9CRlcd%3A+Reinforcement+lear)
5. SPIE, 2024, pp. 226–232. [108] J. Jiang, Z. Chen, Y. Min, J. Chen, X. Cheng, J. Wang, Y. Tang, H. Sun, J. Deng, W. X. Zhao et al., “Technical report: Enhancing llm reasoning with reward-guided tree search,” arXiv preprint arXiv:2411.11694, 2024. [109] C. B. Browne, E. Powley, D. Whitehouse, S. M. Lu… — [METAL: A Multi-Agent Framework for Chart Generation with Test-Time Scaling](https://md.research.elamur.ai/free/en/papers/li-2025-metal-multi-agent-framework-chart/)
6. [117] Z. Yin, Q. Sun, C. Chang, Q. Guo, J. Dai, X. Huang, and X. Qiu, “Exchange-of-thought: Enhancing large language model capabilities through cross-model communication,” arXiv preprint arXiv:2312.01823, 2023. [118] Y. Li, S. Ren, P. Wu, S. Chen, C. Feng, and W. Zhang, “Learning distilled collabora… [find](https://scholar.google.com/scholar?q=%5B117%5D+Z%2E+Yin%2C+Q%2E+Sun%2C+C%2E+Chang%2C+Q%2E+Guo%2C+J%2E+Dai%2C+X%2E+Huang%2C+and+X%2E+Qiu%2C+%E2%80%9CExchange%2Dof%2Dthought%3A+Enhancing+large+language+model+capabilities+through+cross%2Dmodel+communication%2C%E2%80%9D+arXiv+preprint+arXiv%3A2312%2E01)
7. Springer, 2024, pp. 372–384. [135] Z. Guo, Y. Huang, and D. Xiong, “Ctooleval: a chinese benchmark for llm-powered agent evaluation in real-world api interactions,” in ACL Findings, 2024, pp. 15 711–15 724. [136] Y. Jiang, K. C. Black, G. Geng, D. Park, A. Y. Ng, and J. H. Chen, “Medagentbench: Data… [find](https://scholar.google.com/scholar?q=Springer%2C+2024%2C+pp%2E+372%E2%80%93384%2E+%5B135%5D+Z%2E+Guo%2C+Y%2E+Huang%2C+and+D%2E+Xiong%2C+%E2%80%9CCtooleval%3A+a+chinese+benchmark+for+llm%2Dpowered+agent+evaluation+in+real%2Dworld+api+interactions%2C%E2%80%9D+in+ACL+Findings%2C+2024%2C+pp%2E+15+711%E2%80%931)
8. [139] Y. Zhang, Q. Jiang, X. Han, N. Chen, Y. Yang, and K. Ren, “Benchmarking data science agents,” arXiv preprint arXiv:2402.17168, 2024. [140] Y. Huang, J. Luo, Y. Yu, Y. Zhang, F. Lei, Y. Wei, S. He, L. Huang, X. Liu, J. Zhao et al., “Da-code: Agent data science code generation benchmark for larg… [find](https://scholar.google.com/scholar?q=%5B139%5D+Y%2E+Zhang%2C+Q%2E+Jiang%2C+X%2E+Han%2C+N%2E+Chen%2C+Y%2E+Yang%2C+and+K%2E+Ren%2C+%E2%80%9CBenchmarking+data+science+agents%2C%E2%80%9D+arXiv+preprint+arXiv%3A2402%2E17168%2C+2024%2E+%5B140%5D+Y%2E+Huang%2C+J%2E+Luo%2C+Y%2E+Yu%2C+Y%2E+Zhang%2C+F%2E+Lei%2C+Y%2E+Wei%2C+S%2E+H)
9. Springer, 2024, pp. 161–178. [149] J. Yang, S. Liu, H. Guo, Y. Dong, X. Zhang, S. Zhang, P. Wang, Z. Zhou, B. Xie, Z. Wang et al., “Egolife: Towards egocentric life assistant,” arXiv preprint arXiv:2503.03803, 2025. [150] J. Wang, M. Zerun, Y. Li, S. Zhang, C. Chen, K. Chen, and X. Le, “Gta: a bench… [find](https://scholar.google.com/scholar?q=Springer%2C+2024%2C+pp%2E+161%E2%80%93178%2E+%5B149%5D+J%2E+Yang%2C+S%2E+Liu%2C+H%2E+Guo%2C+Y%2E+Dong%2C+X%2E+Zhang%2C+S%2E+Zhang%2C+P%2E+Wang%2C+Z%2E+Zhou%2C+B%2E+Xie%2C+Z%2E+Wang+et+al%2E%2C+%E2%80%9CEgolife%3A+Towards+egocentric+life+assistant%2C%E2%80%9D+arXiv+preprint+arXiv%3A25)
10. Springer, 2024, pp. 39–48. [153] Z. Li, X. Wu, H. Du, H. Nghiem, and G. Shi, “Benchmark evaluations, applications, and challenges of large vision language models: A survey,” arXiv preprint arXiv:2501.02189, 2025. [154] M. Kenney, “Ml research benchmark,” arXiv preprint arXiv:2410.22553, 2024. [155]… [find](https://scholar.google.com/scholar?q=Springer%2C+2024%2C+pp%2E+39%E2%80%9348%2E+%5B153%5D+Z%2E+Li%2C+X%2E+Wu%2C+H%2E+Du%2C+H%2E+Nghiem%2C+and+G%2E+Shi%2C+%E2%80%9CBenchmark+evaluations%2C+applications%2C+and+challenges+of+large+vision+language+models%3A+A+survey%2C%E2%80%9D+arXiv+preprint+arXiv%3A2501%2E)
11. [161] X. Wang, Y. Chen, L. Yuan, Y. Zhang, Y. Li, H. Peng, and H. Ji, “[Executable code actions elicit better llm agents](https://md.research.elamur.ai/free/en/papers/wang-2024-executable-code-actions-elicit-better/),” ArXiv, vol. abs/2402.01030, 2024. [162] T. Schick, J. Dwivedi-Yu, R. Dessı̀, R. Raileanu, M. Lomeli, E. Hambro, L. Zettlemoyer, N. Cancedda, and T. Scialom, “Toolformer: Language…
12. Chen, Eds., Miami, Florida, USA, Nov. 2024, pp. 19 452–19 458. [166] L. Yuan, Y. Chen, X. Wang, Y. R. Fung, H. Peng, and H. Ji, “Craft: Customizing llms by creating and retrieving from specialized toolsets,” arXiv preprint arXiv:2309.17428, 2023. [167] C. Qian, C. Xiong, Z. Liu, and Z. Liu, “Toolink… [find](https://scholar.google.com/scholar?q=Chen%2C+Eds%2E%2C+Miami%2C+Florida%2C+USA%2C+Nov%2E+2024%2C+pp%2E+19+452%E2%80%9319+458%2E+%5B166%5D+L%2E+Yuan%2C+Y%2E+Chen%2C+X%2E+Wang%2C+Y%2E+R%2E+Fung%2C+H%2E+Peng%2C+and+H%2E+Ji%2C+%E2%80%9CCraft%3A+Customizing+llms+by+creating+and+retrieving+from+specialized+too)
13. [186] X. Chen, Y. Nie, W. Guo, and X. Zhang, “When llm meets drl: Advancing jailbreaking efficiency via drl-guided search,” in NeurIPS, 2024. [187] Z. Lin, W. Ma, M. Zhou, Y. Zhao, H. Wang, Y. Liu, J. Wang, and L. Li, “Pathseeker: Exploring llm security vulnerabilities with a reinforcement learning-… [find](https://scholar.google.com/scholar?q=%5B186%5D+X%2E+Chen%2C+Y%2E+Nie%2C+W%2E+Guo%2C+and+X%2E+Zhang%2C+%E2%80%9CWhen+llm+meets+drl%3A+Advancing+jailbreaking+efficiency+via+drl%2Dguided+search%2C%E2%80%9D+in+NeurIPS%2C+2024%2E+%5B187%5D+Z%2E+Lin%2C+W%2E+Ma%2C+M%2E+Zhou%2C+Y%2E+Zhao%2C+H%2E+Wang%2C+Y%2E+Liu%2C+J%2E)
14. [210] Y. Tian, X. Yang, J. Zhang, Y. Dong, and H. Su, “Evil geniuses: Delving into the safety of llm-based agents,” arXiv preprint arXiv:2311.11855, 2023. [211] C. Wang, Q. Long, X. Meng, X. Cai, C. Wu, Z. Meng, X. Wang, and Y. Zhou, “Biorag: A rag-llm framework for biological question reasoning,” a… [find](https://scholar.google.com/scholar?q=%5B210%5D+Y%2E+Tian%2C+X%2E+Yang%2C+J%2E+Zhang%2C+Y%2E+Dong%2C+and+H%2E+Su%2C+%E2%80%9CEvil+geniuses%3A+Delving+into+the+safety+of+llm%2Dbased+agents%2C%E2%80%9D+arXiv+preprint+arXiv%3A2311%2E11855%2C+2023%2E+%5B211%5D+C%2E+Wang%2C+Q%2E+Long%2C+X%2E+Meng%2C+X%2E+Cai%2C+C%2E+W)
15. IEEE, 2020, pp. 1314–1331. [232] L. Wang, J. Wang, J. Wan, L. Long, Z. Yang, and Z. Qin, “Property existence inference against generative models,” in USENIX, 2024, pp. 2423–2440. [find](https://scholar.google.com/scholar?q=IEEE%2C+2020%2C+pp%2E+1314%E2%80%931331%2E+%5B232%5D+L%2E+Wang%2C+J%2E+Wang%2C+J%2E+Wan%2C+L%2E+Long%2C+Z%2E+Yang%2C+and+Z%2E+Qin%2C+%E2%80%9CProperty+existence+inference+against+generative+models%2C%E2%80%9D+in+USENIX%2C+2024%2C+pp%2E+2423%E2%80%932440%2E)
16. [233] N. Kandpal, E. Wallace, and C. Raffel, “[Deduplicating training data mitigates privacy risks in language models](https://md.research.elamur.ai/free/en/papers/kandpal-2022-deduplicating-training-data-mitigates-privacy/),” in ICML. PMLR, 2022, pp. 10 697–10 707. [234] S. Kim, S. Yun, H. Lee, M. Gubri, S. Yoon, and S. J. Oh, “Propile: Probing privacy leakage in large language models,” NeurIPS, vol. 36,…
17. PMLR, 2023, pp. 17 061–17 084. [239] Y. Lin, Z. Gao, H. Du, D. Niyato, J. Kang, Z. Xiong, and Z. Zheng, “Blockchain-based efficient and trustworthy aigc services in metaverse,” IEEE Transactions on Services Computing, 2024. [240] X. Shen, Y. Qu, M. Backes, and Y. Zhang, “Prompt stealing attacks agai… — [On the Opportunities and Risks of Foundation Models](https://md.research.elamur.ai/free/en/papers/bommasani-2021-opportunities-risks-foundation-models/)
18. IEEE, 2024, pp. 1–5. [247] S. Moore, R. Tong, A. Singh, Z. Liu, X. Hu, Y. Lu, J. Liang, C. Cao, H. Khosravi, P. Denny et al., “Empowering Education with LLMs -The Next-Gen Interface and Content Generation,” in International Conference on Artificial Intelligence in Education. [find](https://scholar.google.com/scholar?q=IEEE%2C+2024%2C+pp%2E+1%E2%80%935%2E+%5B247%5D+S%2E+Moore%2C+R%2E+Tong%2C+A%2E+Singh%2C+Z%2E+Liu%2C+X%2E+Hu%2C+Y%2E+Lu%2C+J%2E+Liang%2C+C%2E+Cao%2C+H%2E+Khosravi%2C+P%2E+Denny+et+al%2E%2C+%E2%80%9CEmpowering+Education+with+LLMs+%2DThe+Next%2DGen+Interface+and+Content+Genera)
19. Springer, 2023, pp. 32–37. [248] S. Liu, Y. Jin, C. Li, D. F. Wong, Q. Wen, L. Sun, H. Chen, X. Xie, and J. Wang, “Culturevlm: Characterizing and improving cultural understanding of vision-language models for over 100 countries,” arXiv:2501.01282, 2025. [249] P. Henderson, X. Li, D. Jurafsky, T. Has… [find](https://scholar.google.com/scholar?q=Springer%2C+2023%2C+pp%2E+32%E2%80%9337%2E+%5B248%5D+S%2E+Liu%2C+Y%2E+Jin%2C+C%2E+Li%2C+D%2E+F%2E+Wong%2C+Q%2E+Wen%2C+L%2E+Sun%2C+H%2E+Chen%2C+X%2E+Xie%2C+and+J%2E+Wang%2C+%E2%80%9CCulturevlm%3A+Characterizing+and+improving+cultural+understanding+of+vision%2Dlanguage+mo)
20. [256] I. Shumailov, Z. Shumaylov, Y. Zhao, N. Papernot, R. Anderson, and Y. Gal, “AI models collapse when trained on recursively generated data,” Nature, vol. 631, no. 8022, pp. 755–759, 2024. [257] L. Weidinger, J. Mellor, M. Rauh, C. Griffin, J. Uesato, P.-S. Huang, M. Cheng, M. Glaese, B. Balle,… — [Ethical and social risks of harm from Language Models](https://md.research.elamur.ai/free/en/papers/weidinger-2021-ethical-social-risks-harm-language/)
21. [277] X. Cai, C. Wang, Q. Long, Y. Zhou, and M. Xiao, “Knowledge hierarchy guided biological-medical dataset distillation for domain llm training,” arXiv preprint arXiv:2501.15108, 2025. [278] Z. Chen, C. Hu, M. Wu, Q. Long, X. Wang, Y. Zhou, and M. Xiao, “Genesum: Large language model-based gene su… — [arXiv:2501.15108](https://arxiv.org/abs/2501.15108) [find](https://scholar.google.com/scholar?q=%5B277%5D+X%2E+Cai%2C+C%2E+Wang%2C+Q%2E+Long%2C+Y%2E+Zhou%2C+and+M%2E+Xiao%2C+%E2%80%9CKnowledge+hierarchy+guided+biological%2Dmedical+dataset+distillation+for+domain+llm+training%2C%E2%80%9D+arXiv+preprint+arXiv%3A2501%2E15108%2C+2025%2E+%5B278%5D+Z%2E+Chen)
22. IEEE, 2024, pp. 1438–1443. [279] K. Keshavjee, J. Bosomworth, J. Copen, J. Lai, B. Kucukyazici, R. Lilani, and A. M. Holbrook, “Best practices in emr implementation: a systematic review,” in AMIA Annual Symposium Proceedings, vol. 2006, 2006, p. 982. [280] X. Ye, M. Xiao, Z. Ning, W. Dai, W. Cui, Y.… [find](https://scholar.google.com/scholar?q=IEEE%2C+2024%2C+pp%2E+1438%E2%80%931443%2E+%5B279%5D+K%2E+Keshavjee%2C+J%2E+Bosomworth%2C+J%2E+Copen%2C+J%2E+Lai%2C+B%2E+Kucukyazici%2C+R%2E+Lilani%2C+and+A%2E+M%2E+Holbrook%2C+%E2%80%9CBest+practices+in+emr+implementation%3A+a+systematic+review%2C%E2%80%9D+in+AMIA+Annu)
23. SIAM, 2023, pp. 667–675. [281] J. Li, Y. Lai, W. Li, J. Ren, M. Zhang, X. Kang, S. Wang, P. Li, Y.-Q. Zhang, W. Ma et al., “Agent hospital: A simulacrum of hospital with evolvable medical agents,” arXiv preprint arXiv:2405.02957, 2024. [282] W. Yan, H. Liu, T. Wu, Q. Chen, W. Wang, H. Chai, J. Wang,… [find](https://scholar.google.com/scholar?q=SIAM%2C+2023%2C+pp%2E+667%E2%80%93675%2E+%5B281%5D+J%2E+Li%2C+Y%2E+Lai%2C+W%2E+Li%2C+J%2E+Ren%2C+M%2E+Zhang%2C+X%2E+Kang%2C+S%2E+Wang%2C+P%2E+Li%2C+Y%2E%2DQ%2E+Zhang%2C+W%2E+Ma+et+al%2E%2C+%E2%80%9CAgent+hospital%3A+A+simulacrum+of+hospital+with+evolvable+medical+agents%2C%E2%80%9D+arX)
24. [299] C. Gao, X. Lan, Z. Lu, J. Mao, J. Piao, H. Wang, D. Jin, and Y. Li, “S3: Social-network simulation system with large language model-empowered agents,” arXiv preprint arXiv:2307.14984, 2023. [300] Y. Dong, X. Jiang, Z. Jin, and G. Li, “Self-collaboration code generation via chatgpt,” ACM Transa… [find](https://scholar.google.com/scholar?q=%5B299%5D+C%2E+Gao%2C+X%2E+Lan%2C+Z%2E+Lu%2C+J%2E+Mao%2C+J%2E+Piao%2C+H%2E+Wang%2C+D%2E+Jin%2C+and+Y%2E+Li%2C+%E2%80%9CS3%3A+Social%2Dnetwork+simulation+system+with+large+language+model%2Dempowered+agents%2C%E2%80%9D+arXiv+preprint+arXiv%3A2307%2E14984%2C+2023%2E+%5B300)
25. IEEE, 2024, pp. 865–876. [313] X. Cheng, X. Wang, X. Zhang, T. Ge, S.-Q. Chen, F. Wei, H. Zhang, and D. Zhao, “xrag: Extreme context compression for retrieval-augmented generation with one token,” in NeurIPS, 2024. [314] Y. Jin, M. Chandra, G. Verma, Y. Hu, M. De Choudhury, and S. Kumar, “Better to… — [The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery](https://md.research.elamur.ai/free/en/papers/lu-2024-ai-scientist-fully-automated/)
26. [323] K. Zhu, J. Chen, J. Wang, N. Z. Gong, D. Yang, and X. Xie, “Dyval: Dynamic evaluation of large language models for reasoning tasks,” in ICLR, 2024. [324] K. Zhu, J. Wang, Q. Zhao, R. Xu, and X. Xie, “Dynamic evaluation of large language models by meta probing agents,” in ICML. [find](https://scholar.google.com/scholar?q=%5B323%5D+K%2E+Zhu%2C+J%2E+Chen%2C+J%2E+Wang%2C+N%2E+Z%2E+Gong%2C+D%2E+Yang%2C+and+X%2E+Xie%2C+%E2%80%9CDyval%3A+Dynamic+evaluation+of+large+language+models+for+reasoning+tasks%2C%E2%80%9D+in+ICLR%2C+2024%2E+%5B324%5D+K%2E+Zhu%2C+J%2E+Wang%2C+Q%2E+Zhao%2C+R%2E+Xu%2C+and+X%2E+)
27. PMLR, 2024, pp. 62 599–62 617. [325] X. Yi, J. Yao, X. Wang, and X. Xie, “Unpacking the ethical value alignment in big models,” arXiv preprint arXiv:2310.17551, 2023. [326] X. Wang, L. Jiang, J. Hernandez-Orallo, D. Stillwell, L. Sun, F. Luo, and X. Xie, “Evaluating general-purpose ai with psychomet… [find](https://scholar.google.com/scholar?q=PMLR%2C+2024%2C+pp%2E+62+599%E2%80%9362+617%2E+%5B325%5D+X%2E+Yi%2C+J%2E+Yao%2C+X%2E+Wang%2C+and+X%2E+Xie%2C+%E2%80%9CUnpacking+the+ethical+value+alignment+in+big+models%2C%E2%80%9D+arXiv+preprint+arXiv%3A2310%2E17551%2C+2023%2E+%5B326%5D+X%2E+Wang%2C+L%2E+Jiang%2C+J%2E+Herna)

*Updated 24 October 2026*