Elamur Research⌕
☰
home / papers / 2025 / MasRouter: Learning to Route LLMs for Multi-Agent Systems

MasRouter: Learning to Route LLMs for Multi-Agent Systems

Paper · 2025 · Yanwei Yue, Guibin Zhang, Boyang Liu et al.

Summary

LLM-based multi-agent systems (MAS) often outperform single agents, but they consume many tokens. Existing LLM routers choose one model per query, so they only fit single-agent setups. They ignore how agents should cooperate and which roles they should play. The authors formalize this broader task as Multi-Agent System Routing (MASR). For each query, MASR selects a collaboration mode (e.g., Chain, Tree, LLM-Debate), the number and roles of agents, and an LLM backbone for every agent, weighing quality against cost.

Their solution, MasRouter, is a cascade of three controllers:

  • a variational latent-variable module that picks the collaboration structure;
  • a probabilistic cascade that assigns roles one after another;
  • a router that treats LLM choice per agent as a multinomial distribution.

Training adds a cost penalty to the objective. Across five benchmarks, MasRouter beats single-agent routers such as RouterDC while cutting spending. It also adapts to newly added LLMs without heavy retraining and works as a plug-in for existing MAS frameworks. This makes heterogeneous, budget-aware multi-agent pipelines more practical.

Key points

  • Evaluation uses MBPP, HumanEval, GSM8K, MATH and MMLU. MasRouter scores on average 3.51% above RouterDC and 1.8–8.2% above the strongest baseline on MBPP.
  • On HumanEval, cost drops from $0.363 to $0.185, a reduction of up to 52.07%.
  • As an add-on to MAD and MacNet, MasRouter lowers overhead by 17.21–28.17% and saves $6.17–7.63 on MMLU.
  • When Deepseek-v3 is added to the model pool, it is chosen 12.17% of the time on MMLU and 27.19% on MATH. MMLU accuracy rises from 84.25% to 85.40%.
  • Ablations on GSM8K and MATH:
    • Replacing the LLM router with random selection causes the largest accuracy losses (2.09% and 4.34%).
    • Removing the cost term increases overhead by 54.09% and 41.62%.
    • The maximum agent count is set to 6.

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

🎓Tongji UniversityShanghai · China19 works · 2,162 citations

 Fields, topics and concepts

📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 works

Cite

Cite as Yanwei Yue, Guibin Zhang, Boyang Liu, Guancheng Wan, Kun Wang, Dawei Cheng and Yiyan Qi. 2025. MasRouter: Learning to Route LLMs for Multi-Agent Systems. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2025.acl-long.757

@inproceedings{yue2025masrouter,
  title = {{MasRouter: Learning to Route LLMs for Multi-Agent Systems}},
  author = {Yanwei Yue, Guibin Zhang, Boyang Liu, Guancheng Wan, Kun Wang, Dawei Cheng and Yiyan Qi},
  booktitle = {Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2025},
  doi = {10.18653/v1/2025.acl-long.757},
  url = {https://doi.org/10.18653/v1/2025.acl-long.757}
}

References

81 references, 28 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Marah Abdin, Jyoti Aneja, Hany Awadalla, Ahmed Awadallah, Ammar Ahmad Awan, Nguyen Bach, Amit Bahree, Arash Bakhtiari, Jianmin Bao, Harkirat Behl, Alon Benhaim, Misha Bilenko, Johan Bjorck, Sébastien Bubeck, Martin Cai, Qin Cai, Vishrav Chaudhary, Dong Chen, Dongdong Chen, Weizhu Chen, Yen-Chun Chen… — [arXiv:2409.06669](https://arxiv.org/abs/2409.06669) find
  2. Marija akota, Maxime Peyrard, and Robert West. 2024. Fly-swat or cannon? cost-effective language model choice via meta-modeling. In Proceedings of the 17th ACM International Conference on Web Search and Data Mining, WSDM ’24, page 606–615. ACM. find
  3. Anthropic. 2024. Model card addendum: Claude 3.5 haiku and upgraded claude 3.5 sonnet. Technical report, Anthropic. find
  4. Jacob Austin, Augustus Odena, Maxwell Nye, Maarten Bosma, Henryk Michalewski, David Dohan, Ellen Jiang, Carrie Cai, Michael Terry, Quoc Le, and Charles Sutton. 2021. Program synthesis with large language models. Preprint, arXiv:2108.07732.
  5. Simone Barandoni, Filippo Chiarello, Lorenzo Cascone, Emiliano Marrale, and Salvatore Puccio. 2024. Automating customer needs analysis: A comparative study of large language models in the travel industry. Preprint, arXiv:2404.17975. — [arXiv:2404.17975](https://arxiv.org/abs/2404.17975) find
  6. Chi-Min Chan, Weize Chen, Yusheng Su, Jianxuan Yu, Wei Xue, Shanghang Zhang, Jie Fu, and Zhiyuan Liu. 2023. ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate. arXiv e-prints.
  7. Yupeng Chang, Xu Wang, Jindong Wang, Yuan Wu, Linyi Yang, Kaijie Zhu, Hao Chen, Xiaoyuan Yi, Cunxiang Wang, Yidong Wang, Wei Ye, Yue Zhang, Yi Chang, Philip S. Yu, Qiang Yang, and Xing Xie. 2023. A survey on evaluation of large language models. Preprint, arXiv:2307.03109.
  8. Lingjiao Chen, Matei Zaharia, and James Zou. 2023a. Frugalgpt: How to use large language models while reducing cost and improving performance. Preprint, arXiv:2305.05176.
  9. Mark Chen, Jerry Tworek, Heewoo Jun, Qiming Yuan, Henrique Ponde de Oliveira Pinto, Jared Kaplan, Harri Edwards, Yuri Burda, Nicholas Joseph, Greg Brockman, Alex Ray, Raul Puri, Gretchen Krueger, Michael Petrov, Heidy Khlaaf, Girish Sastry, Pamela Mishkin, Brooke Chan, Scott Gray, Nick Ryder, Mikhai… — Evaluating Large Language Models Trained on Code
  10. Ruisong Zhang, Ruizhe Pan, Runji Wang, Runxin Xu, Ruoyu Zhang, Ruyi Chen, S. S. Li, Shanghao Lu, Shangyan Zhou, Shanhuang Chen, Shaoqing Wu, Shengfeng Ye, Shengfeng Ye, Shirong Ma, Shiyu Wang, Shuang Zhou, Shuiping Yu, Shunfeng Zhou, Shuting Pan, T. Wang, Tao Yun, Tian Pei, Tianyu Sun, W. L. Xiao, W… find
  11. Shuhao Chen, Weisen Jiang, Baijiong Lin, James T Kwok, and Yu Zhang. 2024. Routerdc: Query-based router by dual contrastive learning for assembling large language models. arXiv preprint arXiv:2409.19886. — [arXiv:2409.19886](https://arxiv.org/abs/2409.19886) find
  12. Weize Chen, Yusheng Su, Jingwei Zuo, Cheng Yang, Chenfei Yuan, Chen Qian, Chi-Min Chan, Yujia Qin, Yaxi Lu, Ruobing Xie, Zhiyuan Liu, Maosong Sun, and Jie Zhou. 2023b. Agentverse: Facilitating multi-agent collaboration and exploring emergent behaviors in agents. Preprint, arXiv:2308.10848.
  13. Karl Cobbe, Vineet Kosaraju, Mohammad Bavarian, Mark Chen, Heewoo Jun, Lukasz Kaiser, Matthias Plappert, Jerry Tworek, Jacob Hilton, Reiichiro Nakano, Christopher Hesse, and John Schulman. 2021. Training verifiers to solve math word problems. arXiv prepring, abs/2110.14168.
  14. Xiangxiang Dai, Jin Li, Xutong Liu, Anqi Yu, and John C. S. Lui. 2024. Cost-effective online multi-llm selection with versatile reward models. Preprint, arXiv:2405.16587. — [arXiv:2405.16587](https://arxiv.org/abs/2405.16587) find
  15. DeepSeek-AI, Aixin Liu, Bei Feng, Bing Xue, Bingxuan Wang, Bochao Wu, Chengda Lu, Chenggang Zhao, Chengqi Deng, Chenyu Zhang, Chong Ruan, Damai Dai, Daya Guo, Dejian Yang, Deli Chen, Dongjie Ji, Erhang Li, Fangyun Lin, Fucong Dai, Fuli Luo, Guangbo Hao, Guanting Chen, Guowei Li, H. Zhang, Han Bao, H… — BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
  16. Dujian Ding, Ankur Mallick, Chi Wang, Robert Sim, Subhabrata Mukherjee, Victor Ruhle, Laks V. S. Lakshmanan, and Ahmed Hassan Awadallah. 2024. Hybrid llm: Cost-efficient and quality-aware query routing. Preprint, arXiv:2404.14618. find
  17. Yilun Du, Shuang Li, Antonio Torralba, Joshua B. Tenenbaum, and Igor Mordatch. 2023. Improving factuality and reasoning in language models through multiagent debate. CoRR, abs/2305.14325.
  18. Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Amy Yang, Angela Fan, et al. 2024. The llama 3 herd of models. arXiv preprint arXiv:2407.21783.
  19. Tao Feng, Yanzhen Shen, and Jiaxuan You. 2024. Graphrouter: A graph-based router for llm selections. Preprint, arXiv:2410.03834. — [arXiv:2410.03834](https://arxiv.org/abs/2410.03834) find
  20. Yao Fu, Hao Peng, Ashish Sabharwal, Peter Clark, and Tushar Khot. 2022. Complexity-based prompting for multi-step reasoning. In The Eleventh International Conference on Learning Representations.
  21. Daya Guo, Qihao Zhu, Dejian Yang, Zhenda Xie, Kai Dong, Wentao Zhang, Guanting Chen, Xiao Bi, Y. Wu, Y. K. Li, Fuli Luo, Yingfei Xiong, and Wenfeng Liang. 2024. Deepseek-coder: When the large language model meets programming – the rise of code intelligence. Preprint, arXiv:2401.14196. find
  22. Rui Hao, Linmei Hu, Weijian Qi, Qingliu Wu, Yirui Zhang, and Liqiang Nie. 2023. Chatllm network: More brains, more intelligence. find
  23. Dan Hendrycks, Collin Burns, Steven Basart, Andy Zou, Mantas Mazeika, Dawn Song, and Jacob Steinhardt. 2021a. Measuring massive multitask language understanding. Proceedings of the International Conference on Learning Representations (ICLR).
  24. Dan Hendrycks, Collin Burns, Saurav Kadavath, Akul Arora, Steven Basart, Eric Tang, Dawn Song, and Jacob Steinhardt. 2021b. Measuring mathematical problem solving with the math dataset. NeurIPS.
  25. Sirui Hong, Xiawu Zheng, Jonathan Chen, Yuheng Cheng, Jinlin Wang, Ceyao Zhang, Zili Wang, Steven Ka Shing Yau, Zijuan Lin, Liyang Zhou, Chenyu Ran, Lingfeng Xiao, and Chenglin Wu. 2023. Metagpt: Meta programming for multi-agent collaborative framework. find
  26. Qitian Jason Hu, Jacob Bieker, Xiuyu Li, Nan Jiang, Benjamin Keigwin, Gaurav Ranganath, Kurt Keutzer, and Shriyash Kaustubh Upadhyay. 2024a. Routerbench: A benchmark for multi-llm routing system. Preprint, arXiv:2403.12031. — [arXiv:2403.12031](https://arxiv.org/abs/2403.12031) find
  27. Shengran Hu, Cong Lu, and Jeff Clune. 2024b. Automated Design of Agentic Systems. arXiv preprint. ArXiv:2408.08435. find
  28. Quzhe Huang, Zhenwei An, Nan Zhuang, Mingxu Tao, Chen Zhang, Yang Jin, Kun Xu, Kun Xu, Liwei Chen, Songfang Huang, and Yansong Feng. 2024. Harder tasks need more experts: Dynamic routing in moe models. Preprint, arXiv:2403.07652. — [arXiv:2403.07652](https://arxiv.org/abs/2403.07652) find
  29. Yoichi Ishibashi and Yoshimasa Nishimura. 2024. Self-organized agents: A llm multi-agent framework toward ultra large-scale code generation and optimization. arXiv preprint arXiv:2404.02183. — [arXiv:2404.02183](https://arxiv.org/abs/2404.02183) find
  30. Can Jin, Hongwu Peng, Qixin Zhang, Yujin Tang, Dimitris N Metaxas, and Tong Che. 2025. Two heads are better than one: Test-time scaling of multi-agent collaborative reasoning. arXiv preprint arXiv:2504.09772. — [arXiv:2504.09772](https://arxiv.org/abs/2504.09772) find
  31. Pierre Lepagnol, Thomas Gerald, Sahar Ghannay, Christophe Servan, and Sophie Rosset. 2024. Small language models are good too: An empirical study of zero-shot classification. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LR… find
  32. Tian Liang, Zhiwei He, Wenxiang Jiao, Xing Wang, Yan Wang, Rui Wang, Yujiu Yang, Zhaopeng Tu, and Shuming Shi. 2023. Encouraging divergent thinking in large language models through multi-agent debate. Work in progress.
  33. Zijun Liu, Yanzhe Zhang, Peng Li, Yang Liu, and Diyi Yang. 2023. Dynamic llm-agent network: An llm-agent collaboration framework with agent team optimization. CoRR, abs/2310.02170. find
  34. Shervin Minaee, Tomas Mikolov, Narjes Nikzad, Meysam Chenaghlu, Richard Socher, Xavier Amatriain, and Jianfeng Gao. 2024. Large language models: A survey. Preprint, arXiv:2402.06196.
  35. Alireza Mohammadshahi, Arshad Rafiq Shaikh, and Majid Yazdani. 2024. Routoo: Learning to route to large language models effectively. Preprint, arXiv:2401.13979. — [arXiv:2401.13979](https://arxiv.org/abs/2401.13979) find
  36. Isaac Ong, Amjad Almahairi, Vincent Wu, Wei-Lin Chiang, Tianhao Wu, Joseph E. Gonzalez, M Waleed Kadous, and Ion Stoica. 2024. Routellm: Learning to route llms with preference data. Preprint, arXiv:2406.18665. find
  37. OpenAI. 2024. Gpt-4o mini: Advancing cost-efficient intelligence. find
  38. Joon Sung Park, Joseph C. O’Brien, Carrie J. Cai, Meredith Ringel Morris, Percy Liang, and Michael S. Bernstein. 2023. Generative agents: Interactive simulacra of human behavior. find
  39. Rafael Pina, Varuna De Silva, and Corentin Ar-taud. 2023. Discovering causality for efficient cooperation in multi-agent environments. CoRR, abs/2306.11846. — [arXiv:2306.11846](https://arxiv.org/abs/2306.11846) find
  40. Chen Qian, Xin Cong, Cheng Yang, Weize Chen, Yusheng Su, Juyuan Xu, Zhiyuan Liu, and Maosong Sun. 2023. Communicative agents for software development. 25 pages, 9 figures, 2 tables. find
  41. Chen Qian, Zihao Xie, Yifei Wang, Wei Liu, Yufan Dang, Zhuoyun Du, Weize Chen, Cheng Yang, Zhiyuan Liu, and Maosong Sun. 2024. Scaling large-language-model-based multi-agent collaboration. arXiv preprint arXiv:2406.07155. find
  42. Frederike Ramin, Christoph Matthies, and Ralf Teusner. 2020. More than code: Contributions in scrum software engineering teams. In Proceedings of the IEEE/ACM 42nd International Conference on Software Engineering Workshops, ICSE ’20, page 137–140. ACM. find
  43. N Reimers. 2019. Sentence-bert: Sentence embeddings using siamese bert-networks. arXiv preprint arXiv:1908.10084.
  44. Reworkd. 2023. Agentgpt. https://github.com/ reworkd/AgentGPT. ↗
  45. Toran Bruce Richards and et al. 2023. Auto-gpt: An autonomous gpt-4 experiment. https://github.com/ Significant-Gravitas/Auto-GPT. ↗
  46. Yu Shang, Yu Li, Keyu Zhao, Likai Ma, Jiahe Liu, Fengli Xu, and Yong Li. 2024. Agentsquare: Automatic llm agent search in modular design space. Preprint, arXiv:2410.06153. — [arXiv:2410.06153](https://arxiv.org/abs/2410.06153) find
  47. Weizhou Shen, Chenliang Li, Hongzhan Chen, Ming Yan, Xiaojun Quan, Hehong Chen, Ji Zhang, and Fei Huang. 2024. Small llms are weak tool learners: A multi-llm agent. arXiv preprint arXiv:2401.07324.
  48. Noah Shinn, Beck Labash, and Ashwin Gopinath. 2023. Reflexion: an autonomous agent with dynamic memory and self-reflection. arXiv preprint, abs/2303.11366.
  49. KV Aditya Srivatsa, Kaushal Kumar Maurya, and Ekaterina Kochmar. 2024. Harnessing the power of multiple minds: Lessons learned from llm routing. Preprint, arXiv:2405.00467. find
  50. Dimitris Stripelis, Zhaozhuo Xu, Zijian Hu, Alay Dilipb-hai Shah, Han Jin, Yuhang Yao, Jipeng Zhang, Tong Zhang, Salman Avestimehr, and Chaoyang He. 2024. TensorOpera router: A multi-model router for efficient LLM inference. In Proceedings of the 2024 Conference on Empirical Methods in Natural Langu… find
  51. Melanie Swan, Takashi Kido, Eric Roland, and Renato P. dos Santos. 2023. Math agents: Computational infrastructure, mathematical embedding, and genomics. Preprint, arXiv:2307.02502. — [arXiv:2307.02502](https://arxiv.org/abs/2307.02502) find
  52. Gemini Team, Petko Georgiev, Ving Ian Lei, Ryan Burnell, Libin Bai, Anmol Gulati, Garrett Tanzer, Damien Vincent, Zhufeng Pan, Shibo Wang, et al. 2024. Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context. Preprint, arXiv:2403.05530.
  53. Jen tse Huang, Eric John Li, Man Ho Lam, Tian Liang, Wenxuan Wang, Youliang Yuan, Wenxiang Jiao, Xing Wang, Zhaopeng Tu, and Michael R. Lyu. 2025a. How far are we on the decision-making of llms? evaluating llms’ gaming ability in multi-agent environments. Preprint, arXiv:2403.11807. — [arXiv:2403.11807](https://arxiv.org/abs/2403.11807) find
  54. Jen tse Huang, Jiaxu Zhou, Tailin Jin, Xuhui Zhou, Zixi Chen, Wenxuan Wang, Youliang Yuan, Michael R. Lyu, and Maarten Sap. 2025b. On the resilience of llm-based multi-agent collaboration with faulty agents. Preprint, arXiv:2408.00989. — [arXiv:2408.00989](https://arxiv.org/abs/2408.00989) find
  55. Guanzhi Wang, Yuqi Xie, Yunfan Jiang, Ajay Mandlekar, Chaowei Xiao, Yuke Zhu, Linxi Fan, and Anima Anandkumar. 2023. Voyager: An Open-Ended Embodied Agent with Large Language Models. arXiv e-prints, arXiv:2305.16291. find
  56. Qian Wang, Zhenheng Tang, ZICHEN JIANG, Nuo Chen, Tianyu Wang, and Bingsheng He. Agenttaxo: Dissecting and benchmarking token distribution of llm multi-agent systems. In ICLR 2025 Workshop on Foundation Models in the Wild. find
  57. Qian Wang, Tianyu Wang, Qinbin Li, Jingsheng Liang, and Bingsheng He. 2024a. Megaagent: A practical framework for autonomous cooperation in large-scale llm agent systems. arXiv preprint arXiv:2408.09955. — [arXiv:2408.09955](https://arxiv.org/abs/2408.09955) find
  58. Qian Wang, Jiaying Wu, Zhenheng Tang, Bingqiao Luo, Nuo Chen, Wei Chen, and Bingsheng He. 2025a. What limits llm-based human simulation: Llms or our design? arXiv preprint arXiv:2501.08579. — [arXiv:2501.08579](https://arxiv.org/abs/2501.08579) find
  59. 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. Advances in Neural Information Processing Systems, 33:5776–5788. find
  60. Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc V Le, Ed H. Chi, Sharan Narang, Aakanksha Chowdhery, and Denny Zhou. 2023a. Self-consistency improves chain of thought reasoning in language models. In The Eleventh International Conference on Learning Representations.
  61. Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc V. Le, Ed H. Chi, Sharan Narang, Aakanksha Chowdhery, and Denny Zhou. 2023b. Self-consistency improves chain of thought reasoning in language models. In ICLR. OpenReview.net.
  62. Yutong Wang, Jiali Zeng, Xuebo Liu, Fandong Meng, Jie Zhou, and Min Zhang. 2024b. TasTe: Teaching large language models to translate through self-reflection. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 6144– 6158, Bangkok,… find
  63. Zhenhailong Wang, Shaoguang Mao, Wenshan Wu, Tao Ge, Furu Wei, and Heng Ji. 2024c. Unleashing the emergent cognitive synergy in large language models: A task-solving agent through multi-persona self-collaboration. In NAACL. Association for Computational Linguistics.
  64. Zhexuan Wang, Yutong Wang, Xuebo Liu, Liang Ding, Miao Zhang, Jie Liu, and Min Zhang. 2025b. Agentdropout: Dynamic agent elimination for token-efficient and high-performance llm-based multi-agent collaboration. Preprint, arXiv:2503.18891.
  65. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Brian Ichter, Fei Xia, Ed Chi, Quoc Le, and Denny Zhou. 2022. Chain-of-thought prompting elicits reasoning in large language models.
  66. Ronald J Williams. 1992. Simple statistical gradient-following algorithms for connectionist reinforcement learning. Machine learning, 8:229–256. find
  67. Anita Williams Woolley, Christopher F. Chabris, Alex Pentland, Nada Hashmi, and Thomas W. Malone. 2010. Evidence for a collective intelligence factor in the performance of human groups. Science, 330(6004):686–688. find
  68. Qinlin Zhao, Jindong Wang, Yixuan Zhang, Yiqiao Jin, Kaijie Zhu, Hao Chen, and Xing Xie. 2023. Competeai: Understanding the competition behaviors in large language model-based agents. arXiv preprint arXiv:2310.17512. find
  69. Qingyun Wu, Gagan Bansal, Jieyu Zhang, Yiran Wu, Shaokun Zhang, Erkang Zhu, Beibin Li, Li Jiang, Xiaoyun Zhang, and Chi Wang. 2023. Autogen: Enabling next-gen llm applications via multi-agent conversation framework.
  70. Xuhui Zhou, Zhe Su, Sophie Feng, Jiaxu Zhou, Jen tse Huang, Hsien-Te Kao, Spencer Lynch, Svitlana Volkova, Tongshuang Sherry Wu, Anita Woolley, Hao Zhu, and Maarten Sap. 2025. Sotopia-s4: a user-friendly system for flexible, customizable, and large-scale social simulation. Preprint, arXiv:2504.16122… find
  71. Yibo Yan, Shen Wang, Jiahao Huo, Philip S Yu, Xuming Hu, and Qingsong Wen. 2025. Mathagent: Leveraging a mixture-of-math-agent framework for real-world multimodal mathematical error detection. arXiv preprint arXiv:2503.18132. find
  72. Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik R Narasimhan, and Yuan Cao. 2023. React: Synergizing reasoning and acting in language models. In The Eleventh International Conference on Learning Representations.
  73. Zhangyue Yin, Qiushi Sun, Cheng Chang, Qipeng Guo, Junqi Dai, Xuanjing Huang, and Xipeng Qiu. 2023. Exchange-of-thought: Enhancing large language model capabilities through cross-model communication. Preprint, arXiv:2312.01823. find
  74. Longhui Yu, Weisen Jiang, Han Shi, Jincheng Yu, Zhengying Liu, Yu Zhang, James T. Kwok, Zhenguo Li, Adrian Weller, and Weiyang Liu. 2024. Metamath: Bootstrap your own mathematical questions for large language models. Preprint, arXiv:2309.12284.
  75. Guibin Zhang, Kaijie Chen, Guancheng Wan, Heng Chang, Hong Cheng, Kun Wang, Shuyue Hu, and Lei Bai. 2025. Evoflow: Evolving diverse agentic workflows on the fly. arXiv preprint arXiv:2502.07373. — [arXiv:2502.07373](https://arxiv.org/abs/2502.07373) find
  76. Guibin Zhang, Yanwei Yue, Zhixun Li, Sukwon Yun, Guancheng Wan, Kun Wang, Dawei Cheng, Jeffrey Xu Yu, and Tianlong Chen. 2024a. Cut the crap: An economical communication pipeline for llm-based multi-agent systems. Preprint, arXiv:2410.02506. — [arXiv:2410.02506](https://arxiv.org/abs/2410.02506) find
  77. Guibin Zhang, Yanwei Yue, Zhixun Li, Sukwon Yun, Guancheng Wan, Kun Wang, Dawei Cheng, Jeffrey Xu Yu, and Tianlong Chen. 2024b. Cut the crap: An economical communication pipeline for llm-based multi-agent systems. arXiv preprint arXiv:2410.02506. — [arXiv:2410.02506](https://arxiv.org/abs/2410.02506) find
  78. Jiayi Zhang, Jinyu Xiang, Zhaoyang Yu, Fengwei Teng, Xionghui Chen, Jiaqi Chen, Mingchen Zhuge, Xin Cheng, Sirui Hong, Jinlin Wang, Bingnan Zheng, Bang Liu, Yuyu Luo, and Chenglin Wu. 2024c. AFlow: Automating Agentic Workflow Generation. arXiv preprint. ArXiv:2410.10762. find
  79. Jintian Zhang, Xin Xu, and Shumin Deng. 2023. Exploring collaboration mechanisms for llm agents: A social psychology view. arXiv preprint arXiv:2310.02124.
  80. Mingchen Zhuge, Wenyi Wang, Louis Kirsch, Francesco Faccio, Dmitrii Khizbullin, and Jürgen Schmidhuber. 2024. Gptswarm: Language agents as optimizable graphs. In Forty-first International Conference on Machine Learning. find
  81. Christian Zingg, Alexander von Gernler, Carsten Arzig, Frank Schweitzer, and Christoph Gote. 2023. Detecting and optimising team interactions in software development. Preprint, arXiv:2302.14609. — [arXiv:2302.14609](https://arxiv.org/abs/2302.14609) find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/yue-2025-masrouter-learning-route-llms-multi/