---
title: "Mixture-of-Agents Enhances Large Language Model Capabilities"
description: "The authors first describe a property they call collaborativeness: a model usually writes a better… 44 references, cited by 90 papers here."
authors: ["Junlin Wang", "Jue Wang", "Ben Athiwaratkun", "Ce Zhang", "James Zou"]
year: 2024
venue: "arXiv:2406.04692"
source: "https://arxiv.org/abs/2406.04692"
doi: "10.48550/arxiv.2406.04692"
arxiv: "2406.04692"
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/wang-2024-mixture-agents-enhances-large/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/wang-2024-mixture-agents-enhances-large/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2024](https://md.research.elamur.ai/free/en/papers/2024/page/3/) / Mixture-of-Agents Enhances Large Language Model Capabilities

# Mixture-of-Agents Enhances Large Language Model Capabilities

**Authors:** [Junlin Wang](https://md.research.elamur.ai/free/en/authors/junlin-wang/), [Jue Wang](https://md.research.elamur.ai/free/en/authors/jue-wang/), [Ben Athiwaratkun](https://md.research.elamur.ai/free/en/authors/ben-athiwaratkun/), [Ce Zhang](https://md.research.elamur.ai/free/en/authors/ce-zhang/) and [James Zou](https://md.research.elamur.ai/free/en/authors/james-zou/) · **Year:** 2024 · **Venue:** arXiv:2406.04692 · **Licence:** [CC BY 4.0 (arXiv)](http://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://arxiv.org/abs/2406.04692) · [PDF](https://arxiv.org/pdf/2406.04692) · [DOI 10.48550/arxiv.2406.04692](https://doi.org/10.48550/arxiv.2406.04692) · [arXiv 2406.04692](https://arxiv.org/abs/2406.04692) · [OpenAlex](https://openalex.org/W4399511904)

**Citations:** 26 citations (OpenAlex, 2026-10-14) · [90](https://md.research.elamur.ai/free/en/papers/wang-2024-mixture-agents-enhances-large/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
Different LLMs have complementary strengths, but scaling any single model further is very expensive. This paper asks whether several existing models can be combined to beat each of them individually. The authors first describe a property they call collaborativeness: a model usually writes a better answer when it can see other models' answers, even answers from weaker models. Building on this, they propose Mixture-of-Agents (MoA). MoA is a layered pipeline in which each layer contains several LLM agents, and every agent receives all responses from the previous layer. A final aggregator then merges these into one reply using an Aggregate-and-Synthesize prompt. The approach relies only on prompting, needs no fine-tuning, and is presented as a model-level analogue of Mixture-of-Experts. The authors evaluate it on AlpacaEval 2.0, MT-Bench and FLASK. A MoA built solely from open-source models ranks first on AlpacaEval 2.0 with a 65.1% LC win rate, compared with 57.5% for GPT-4 Omni. The result suggests that orchestrating freely available models can rival proprietary systems, and the paper offers practical advice on choosing models by quality and diversity.

## Key points
- **Agent roles.** Agents act as *proposers*, which supply diverse reference answers, or *aggregators*, which merge them. GPT-4o, Qwen1.5 and LLaMA-3 perform well in both roles. WizardLM is a strong proposer but a weak aggregator.
- **Model selection.** Choosing models for each layer depends on two factors: their individual win rate and the diversity of their outputs. Heterogeneous proposers help more than repeated samples from a single model.
- **Benchmark results.** The open-source-only MoA reaches 65.1% LC win rate on AlpacaEval 2.0, versus 57.5% for GPT-4o. The best reported MoA configuration reaches 65.8%. MoA also achieves top results on MT-Bench and FLASK.
- **Cost efficiency.** In the budget analysis, the MoA-Lite variant scores about 4% above GPT-4 Turbo at less than half the price. The authors analyse both cost and TFLOPs along a Pareto front.
- **Limitations and code.** The main drawback is a high Time to First Token, because output only begins after the last layer. The authors suggest using fewer layers or chunk-wise aggregation as fixes. Code is available at github.com/togethercomputer/moa.

*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 Chicago](https://md.research.elamur.ai/free/en/universities/university-of-chicago/) — University, Chicago, United States · 52 works · 50,893 citations
- [Duke University](https://md.research.elamur.ai/free/en/universities/duke-university/) — University, Durham, United States · 37 works · 15,861 citations

Also on the byline: [Together](https://ror.org/01azqfh67).

📚 Shelves (5): [🖥️ 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 · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 3,486 works

## Cite

Cite as: Junlin Wang, Jue Wang, Ben Athiwaratkun, Ce Zhang and James Zou. 2024. Mixture-of-Agents Enhances Large Language Model Capabilities. arXiv:2406.04692.

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

```bibtex
@misc{wang2024mixture,
  title = {{Mixture-of-Agents Enhances Large Language Model Capabilities}},
  author = {Junlin Wang, Jue Wang, Ben Athiwaratkun, Ce Zhang and James Zou},
  year = {2024},
  doi = {10.48550/arxiv.2406.04692},
  eprint = {2406.04692},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2406.04692}
}
```

- [← previous DeepSeek-Prover-V1.5: Harnessing Proof Assistant Feedback for Reinforcement Learning and Monte-Carlo Tree Search](https://md.research.elamur.ai/free/en/papers/xin-2024-deepseek-prover-v1-5-harnessing/)
- [next → Quantifying the Persona Effect in LLM Simulations](https://md.research.elamur.ai/free/en/papers/hu-2024-quantifying-persona-effect-llm-simulations/)
- [↑ back to papers of 2024](https://md.research.elamur.ai/free/en/papers/2024/page/3/)

## References

44 references, 32 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Bai, J., Bai, S., Chu, Y., Cui, Z., Dang, K., Deng, X., Fan, Y., Ge, W., Han, Y., Huang, F., et al. [Qwen technical report](https://md.research.elamur.ai/free/en/papers/bai-2023-qwen-technical-report/). arXiv preprint arXiv:2309.16609, 2023.
2. Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J. D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. [Language models are few-shot learners](https://md.research.elamur.ai/free/en/papers/brown-2020-language-models-few-shot-learners/). Advances in neural information processing systems, 33:1877–1901, 2020.
3. Chan, C.-M., Chen, W., Su, Y., Yu, J., Xue, W., Zhang, S., Fu, J., and Liu, Z. [Chateval: Towards better llm-based evaluators through multi-agent debate](https://md.research.elamur.ai/free/en/papers/chan-2023-chateval-better-llm-based/). arXiv preprint arXiv:2308.07201, 2023.
4. Chen, J. C.-Y., Saha, S., and Bansal, M. [Reconcile: Round-table conference improves reasoning via consensus among diverse llms](https://md.research.elamur.ai/free/en/papers/chen-2024-reconcile-round-table-conference-improves/). arXiv preprint arXiv:2309.13007, 2023a.
5. Chen, L., Zaharia, M., and Zou, J. [Frugalgpt: How to use large language models while reducing cost and improving performance](https://md.research.elamur.ai/free/en/papers/chen-2023-frugalgpt-use-large-language-models/). arXiv preprint arXiv:2305.05176, 2023b.
6. Chowdhery, A., Narang, S., Devlin, J., Bosma, M., Mishra, G., Roberts, A., Barham, P., Chung, H. W., Sutton, C., Gehrmann, S., et al. [Palm: Scaling language modeling with pathways](https://md.research.elamur.ai/free/en/papers/chowdhery-2022-palm-scaling-language-modeling-pathways/). arXiv preprint arXiv:2204.02311, 2022.
7. Diao, S., Wang, P., Lin, Y., and Zhang, T. Active prompting with chain-of-thought for large language models. arXiv preprint arXiv:2302.12246, 2023. [find](https://scholar.google.com/scholar?q=Diao%2C+S%2E%2C+Wang%2C+P%2E%2C+Lin%2C+Y%2E%2C+and+Zhang%2C+T%2E+Active+prompting+with+chain%2Dof%2Dthought+for+large+language+models%2E+arXiv+preprint+arXiv%3A2302%2E12246%2C+2023%2E)
8. Du, Y., Li, S., Torralba, A., Tenenbaum, J. B., and Mordatch, I. [Improving factuality and reasoning in language models through multiagent debate](https://md.research.elamur.ai/free/en/papers/du-2023-improving-factuality-reasoning-language-models/). arXiv preprint arXiv:2305.14325, 2023.
9. Dubois, Y., Galambosi, B., Liang, P., and Hashimoto, T. B. Length-controlled alpacaeval: A simple way to debias automatic evaluators. arXiv preprint arXiv:2404.04475, 2024. [find](https://scholar.google.com/scholar?q=Dubois%2C+Y%2E%2C+Galambosi%2C+B%2E%2C+Liang%2C+P%2E%2C+and+Hashimoto%2C+T%2E+B%2E+Length%2Dcontrolled+alpacaeval%3A+A+simple+way+to+debias+automatic+evaluators%2E+arXiv+preprint+arXiv%3A2404%2E04475%2C+2024%2E)
10. Fu, Y., Peng, H., Sabharwal, A., Clark, P., and Khot, T. [Complexity-based prompting for multi-step reasoning](https://md.research.elamur.ai/free/en/papers/fu-2022-complexity-based-prompting-multi-step/). arXiv preprint arXiv:2210.00720, 2022.
11. Guo, D., Zhu, Q., Yang, D., Xie, Z., Dong, K., Zhang, W., Chen, G., Bi, X., Wu, Y., Li, Y., et al. Deepseek-coder: When the large language model meets programming–the rise of code intelligence. arXiv preprint arXiv:2401.14196, 2024. [find](https://scholar.google.com/scholar?q=Guo%2C+D%2E%2C+Zhu%2C+Q%2E%2C+Yang%2C+D%2E%2C+Xie%2C+Z%2E%2C+Dong%2C+K%2E%2C+Zhang%2C+W%2E%2C+Chen%2C+G%2E%2C+Bi%2C+X%2E%2C+Wu%2C+Y%2E%2C+Li%2C+Y%2E%2C+et+al%2E+Deepseek%2Dcoder%3A+When+the+large+language+model+meets+programming%E2%80%93the+rise+of+code+intelligence%2E+arXiv+)
12. Hendrycks, D., Burns, C., Kadavath, S., Arora, A., Basart, S., Tang, E., Song, D., and Steinhardt, J. [Measuring mathematical problem solving with the math dataset](https://md.research.elamur.ai/free/en/papers/hendrycks-2021-measuring-mathematical-problem-solving-math/). arXiv preprint arXiv:2103.03874, 2021.
13. Huang, Y., Feng, X., Li, B., Xiang, Y., Wang, H., Qin, B., and Liu, T. Enabling ensemble learning for heterogeneous large language models with deep parallel collaboration. arXiv preprint arXiv:2404.12715, 2024. — [arXiv:2404.12715](https://arxiv.org/abs/2404.12715) [find](https://scholar.google.com/scholar?q=Huang%2C+Y%2E%2C+Feng%2C+X%2E%2C+Li%2C+B%2E%2C+Xiang%2C+Y%2E%2C+Wang%2C+H%2E%2C+Qin%2C+B%2E%2C+and+Liu%2C+T%2E+Enabling+ensemble+learning+for+heterogeneous+large+language+models+with+deep+parallel+collaboration%2E+arXiv+preprint+arXiv%3A2404%2E12)
14. Jiang, A. Q., Sablayrolles, A., Roux, A., Mensch, A., Savary, B., Bamford, C., Chaplot, D. S., de Las Casas, D., Hanna, E. B., Bressand, F., Lengyel, G., Bour, G., Lample, G., Lavaud, L. R., Saulnier, L., Lachaux, M., Stock, P., Subramanian, S., Yang, S., Antoniak, S., Scao, T. L., Gervet, T., Lavri… [find](https://scholar.google.com/scholar?q=Jiang%2C+A%2E+Q%2E%2C+Sablayrolles%2C+A%2E%2C+Roux%2C+A%2E%2C+Mensch%2C+A%2E%2C+Savary%2C+B%2E%2C+Bamford%2C+C%2E%2C+Chaplot%2C+D%2E+S%2E%2C+de+Las+Casas%2C+D%2E%2C+Hanna%2C+E%2E+B%2E%2C+Bressand%2C+F%2E%2C+Lengyel%2C+G%2E%2C+Bour%2C+G%2E%2C+Lample%2C+G%2E%2C+Lavaud%2C+L%2E+R%2E%2C+Saulnier%2C)
15. Jiang, D., Ren, X., and Lin, B. Y. [LLM-blender: Ensembling large language models with pairwise ranking and generative fusion](https://md.research.elamur.ai/free/en/papers/jiang-2023-llm-blender-ensembling-large-language/). In Rogers, A., Boyd-Graber, J., and Okazaki, N. (eds.), Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 1…
16. Kojima, T., Gu, S. S., Reid, M., Matsuo, Y., and Iwasawa, Y. [Large language models are zero-shot reasoners](https://md.research.elamur.ai/free/en/papers/kojima-2022-large-language-models-zero-shot/). Advances in neural information processing systems, 35:22199–22213, 2022.
17. Liang, T., He, Z., Jiao, W., Wang, X., Wang, Y., Wang, R., Yang, Y., Tu, Z., and Shi, S. [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/). arXiv preprint arXiv:2305.19118, 2023.
18. Ling, Z., Fang, Y., Li, X., Huang, Z., Lee, M., Memisevic, R., and Su, H. [Deductive verification of chain-of-thought reasoning](https://md.research.elamur.ai/free/en/papers/ling-2023-deductive-verification-chain-thought-reasoning/). arXiv preprint arXiv:2306.03872, 2023.
19. Lu, K., Yuan, H., Lin, R., Lin, J., Yuan, Z., Zhou, C., and Zhou, J. [Routing to the expert: Efficient reward-guided ensemble of large language models](https://md.research.elamur.ai/free/en/papers/lu-2023-routing-expert-efficient-reward-guided/), 2023.
20. OpenAI. [Gpt-4 technical report](https://md.research.elamur.ai/free/en/papers/openai-2023-gpt-4-technical-report/), 2023.
21. Ouyang, L., Wu, J., Jiang, X., Almeida, D., Wainwright, C., Mishkin, P., Zhang, C., Agarwal, S., Slama, K., Ray, A., et al. [Training language models to follow instructions with human feedback](https://md.research.elamur.ai/free/en/papers/ouyang-2022-training-language-models-follow-instructions/). Advances in neural information processing systems, 35:27730–27744, 2022.
22. Papineni, K., Roukos, S., Ward, T., and Zhu, W. [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 Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, July 6-12, 2002, Philadelphia, PA, USA, pp. 311–318.
23. ACL, 2002. [doi: 10.3115/ 1073083.1073135](https://md.research.elamur.ai/free/en/papers/papineni-2002-bleu-method-automatic-evaluation-machine/). URL https://aclanthology.org/P02-1040/. [↗](https://aclanthology.org/P02-1040/)
24. RapidFuzz. python-levenshtein by rapidfuzz. python-Levenshtein, 2023. [https://github.com/rapidfuzz/](https://github.com/rapidfuzz/) [↗](https://github.com/rapidfuzz/)
25. Roziere, B., Gehring, J., Gloeckle, F., Sootla, S., Gat, I., Tan, X. E., Adi, Y., Liu, J., Remez, T., Rapin, J., et al. [Code llama: Open foundation models for code](https://md.research.elamur.ai/free/en/papers/roziere-2024-code-llama-open-foundation-models/). arXiv preprint arXiv:2308.12950, 2023.
26. Shazeer, N., Mirhoseini, A., Maziarz, K., Davis, A., Le, Q., Hinton, G., and Dean, J. Outrageously large neural networks: The sparsely-gated mixture-of-experts layer. arXiv preprint arXiv:1701.06538, 2017. [find](https://scholar.google.com/scholar?q=Shazeer%2C+N%2E%2C+Mirhoseini%2C+A%2E%2C+Maziarz%2C+K%2E%2C+Davis%2C+A%2E%2C+Le%2C+Q%2E%2C+Hinton%2C+G%2E%2C+and+Dean%2C+J%2E+Outrageously+large+neural+networks%3A+The+sparsely%2Dgated+mixture%2Dof%2Dexperts+layer%2E+arXiv+preprint+arXiv%3A1701%2E06538%2C+)
27. Shnitzer, T., Ou, A., Silva, M., Soule, K., Sun, Y., Solomon, J., Thompson, N., and Yurochkin, M. [Large language model routing with benchmark datasets](https://md.research.elamur.ai/free/en/papers/shnitzer-2023-large-language-model-routing-benchmark/), 2024. URL [https://openreview.net/](https://openreview.net/) forum?id=LyNsMNNLjY. [↗](https://openreview.net/)
28. Team, G., Anil, R., Borgeaud, S., Wu, Y., Alayrac, J.-B., Yu, J., Soricut, R., Schalkwyk, J., Dai, A. M., Hauth, A., et al. [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, 2023.
29. The Mosaic Research Team. Introducing dbrx: A new state-of-the-art open llm. 2024. URL [https://www.databricks.com/blog/introducing-dbrx-new-state-art-open-llm](https://www.databricks.com/blog/introducing-dbrx-new-state-art-open-llm). [↗](https://www.databricks.com/blog/introducing-dbrx-new-state-art-open-llm)
30. Touvron, H., Lavril, T., Izacard, G., Martinet, X., Lachaux, M.-A., Lacroix, T., Rozière, B., Goyal, N., Hambro, E., Azhar, F., et al. [Llama: Open and efficient foundation language models](https://md.research.elamur.ai/free/en/papers/touvron-2023-llama-open-efficient-foundation-language/). arXiv preprint arXiv:2302.13971, 2023a.
31. Touvron, H., Martin, L., Stone, K., Albert, P., Almahairi, A., Babaei, Y., Bashlykov, N., Batra, S., Bhargava, P., Bhosale, S., et al. [Llama 2: Open foundation and fine-tuned chat models](https://md.research.elamur.ai/free/en/papers/touvron-2023-llama-2-open-foundation-fine/). arXiv preprint arXiv:2307.09288, 2023b.
32. Wang, H., Polo, F. M., Sun, Y., Kundu, S., Xing, E., and Yurochkin, M. Fusing models with complementary expertise. In The Twelfth International Conference on Learning Representations, 2024a. URL [https://openreview.net/forum?id=PhMrGCMIRL](https://openreview.net/forum?id=PhMrGCMIRL). [↗](https://openreview.net/forum?id=PhMrGCMIRL)
33. Wang, L., Xu, W., Lan, Y., Hu, Z., Lan, Y., Lee, R. K.-W., and Lim, E.-P. Plan-and-solve prompting: Improving zero-shot chain-of-thought reasoning by large language models. arXiv preprint arXiv:2305.04091, 2023. [find](https://scholar.google.com/scholar?q=Wang%2C+L%2E%2C+Xu%2C+W%2E%2C+Lan%2C+Y%2E%2C+Hu%2C+Z%2E%2C+Lan%2C+Y%2E%2C+Lee%2C+R%2E+K%2E%2DW%2E%2C+and+Lim%2C+E%2E%2DP%2E+Plan%2Dand%2Dsolve+prompting%3A+Improving+zero%2Dshot+chain%2Dof%2Dthought+reasoning+by+large+language+models%2E+arXiv+preprint+arXiv%3A2305%2E0)
34. Wang, Q., Wang, Z., Su, Y., Tong, H., and Song, Y. [Rethinking the bounds of llm reasoning: Are multi-agent discussions the key?](https://md.research.elamur.ai/free/en/papers/wang-2024-rethinking-bounds-llm-reasoning/) arXiv preprint arXiv:2402.18272, 2024b.
35. Wang, X., Wei, J., Schuurmans, D., Le, Q., Chi, E., Narang, S., Chowdhery, A., and Zhou, D. [Self-consistency improves chain of thought reasoning in language models](https://md.research.elamur.ai/free/en/papers/wang-2022-self-consistency-improves-chain-thought/). arXiv preprint arXiv:2203.11171, 2022.
36. Wei, J., Wang, X., Schuurmans, D., Bosma, M., Xia, F., Chi, E., Le, Q. V., Zhou, D., et al. Chain-of-thought prompting elicits reasoning in large language models. Advances in Neural Information Processing Systems, 35:24824–24837, 2022. [*Figure 6: (a) Spearman Correlation using TF-IDF similarity; (b)…](https://md.research.elamur.ai/free/en/papers/xu-2023-wizardlm-empowering-large-pre-trained/)
37. Xu, X., Tao, C., Shen, T., Xu, C., Xu, H., Long, G., and Lou, J.-g. Re-reading improves reasoning in language models. arXiv preprint arXiv:2309.06275, 2023b. — [arXiv:2309.06275](https://arxiv.org/abs/2309.06275) [find](https://scholar.google.com/scholar?q=Xu%2C+X%2E%2C+Tao%2C+C%2E%2C+Shen%2C+T%2E%2C+Xu%2C+C%2E%2C+Xu%2C+H%2E%2C+Long%2C+G%2E%2C+and+Lou%2C+J%2E%2Dg%2E+Re%2Dreading+improves+reasoning+in+language+models%2E+arXiv+preprint+arXiv%3A2309%2E06275%2C+2023b%2E+%E2%80%94+%5BarXiv%3A2309%2E06275%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs)
38. Yao, S., Yu, D., Zhao, J., Shafran, I., Griffiths, T. L., Cao, Y., and Narasimhan, K. Tree of thoughts: Deliberate problem solving with large language models. arXiv preprint arXiv:2305.10601, 2023a. [find](https://scholar.google.com/scholar?q=Yao%2C+S%2E%2C+Yu%2C+D%2E%2C+Zhao%2C+J%2E%2C+Shafran%2C+I%2E%2C+Griffiths%2C+T%2E+L%2E%2C+Cao%2C+Y%2E%2C+and+Narasimhan%2C+K%2E+Tree+of+thoughts%3A+Deliberate+problem+solving+with+large+language+models%2E+arXiv+preprint+arXiv%3A2305%2E10601%2C+2023a%2E)
39. Yao, Y., Li, Z., and Zhao, H. Beyond chain-of-thought, effective graph-of-thought reasoning in large language models. arXiv preprint arXiv:2305.[16582, 2023b](https://md.research.elamur.ai/free/en/papers/yao-2023-chain-thought-effective-graph-thought/).
40. Ye, S., Kim, D., Kim, S., Hwang, H., Kim, S., Jo, Y., Thorne, J., Kim, J., and Seo, M. [Flask: Fine-grained language model evaluation based on alignment skill sets](https://md.research.elamur.ai/free/en/papers/ye-2023-flask-fine-grained-language-model/). arXiv preprint arXiv:2307.10928, 2023.
41. Zhang, J., Xu, X., and Deng, S. [Exploring collaboration mechanisms for llm agents: A social psychology view](https://md.research.elamur.ai/free/en/papers/zhang-2024-exploring-collaboration-mechanisms-llm-agents/). arXiv preprint arXiv:2310.02124, 2023.
42. Zhang, S., Roller, S., Goyal, N., Artetxe, M., Chen, M., Chen, S., Dewan, C., Diab, M., Li, X., Lin, X. V., et al. [Opt: Open pre-trained transformer language models](https://md.research.elamur.ai/free/en/papers/zhang-2022-opt-open-pre-trained-transformer/). arXiv e-prints, pp. arXiv–2205, 2022a.
43. Zhang, Z., Zhang, A., Li, M., and Smola, A. [Automatic chain of thought prompting in large language models](https://md.research.elamur.ai/free/en/papers/zhang-2022-automatic-chain-thought-prompting-large/). arXiv preprint arXiv:2210.03493, 2022b.
44. Zheng, L., Chiang, W.-L., Sheng, Y., Zhuang, S., Wu, Z., Zhuang, Y., Lin, Z., Li, Z., Li, D., Xing, E. P., Zhang, H., Gonzalez, J. E., and Stoica, I. [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/). arXiv preprint arXiv:2306.05685, 2023.

*Updated 2 November 2026*