Learning to break: Knowledge-enhanced reasoning in multi-agent debate system
Open accessThe claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Most multi-agent debate systems rely on parametric knowledge or generic sources without domain-specific retrieval tailored to each agent's role.
“most multi-agent debate systems rely on parametric knowledge or generic sources without domain-specific retrieval tailored to each agent's role.”
From Multi-Agent debate system based on large language models: structured deliberation and validation in satellite communications (2026) · cites this paper as Wang et al., 2025b
Sections 2.1 and 3.1 describe existing multi-agent debates as vulnerable to agents’ limited and differing background knowledge, and Section 2.2 contrasts the authors’ adaptive, personalized knowledge selection with existing methods. The paper does not establish that *most* systems rely on parametric knowledge or generic sources, nor does it specifically characterize prior systems by a lack of domain-specific retrieval tailored to each agent’s role. Page numbers are unavailable in our copy. (LLM, conf=0.82)
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Dense passage retrieval for open-domain question answering
Karpukhin, V., Oguz, B., Min, S., Lewis, P., Wu, L., Edunov, S., Chen, D., & Yih, W.-T. (2020) · Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.550 · Cited by 3,575 · see citing works
Huang, L., Yu, W., Ma, W., Zhong, W., Feng, Z., Wang, H., Chen, Q., Peng, W., Feng, X., Qin, B., et al. (2025) · ACM Transactions on Information Systems · doi:10.1145/3703155 · Cited by 2,142 · see citing works
Self-citationNatural Questions: A benchmark for question answering research
Kwiatkowski, T., Palomaki, J., Redfield, O., Collins, M., Parikh, A., Alberti, C., Epstein, D., Polosukhin, I., Devlin, J., Lee, K., et al. (2019) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00276 · Cited by 2,069 · see citing works
A survey on large language model based autonomous agents
Wang, L., Ma, C., Feng, X., Zhang, Z., Yang, H., Zhang, J., Chen, Z., Tang, J., Chen, X., Lin, Y., et al. (2024) · Frontiers of Computer Science · doi:10.1007/s11704-024-40231-1 · Cited by 1,941 · see citing works
Scaling Laws for Neural Language Models
Kaplan, J., McCandlish, S., Henighan, T., Brown, T. B., Chess, B., Child, R., Gray, S., Radford, A., Wu, J., & Amodei, D. (2020) · arXiv · Cited by 1,749 · cited 1× · see citing works
“From the experimental results, it can be observed that the model performance improves as the model parameter scale increases, validating the positive correlation between parameter scale and performance and further supporting the conclusions of the scaling law (Kaplan et al., 2020).”
ResultTriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension
Joshi, M., Choi, E., Weld, D., & Zettlemoyer, L. (2017) · Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p17-1147 · Cited by 1,690 · see citing works
Jin, D., Pan, E., Oufattole, N., Weng, W.-H., Fang, H., & Szolovits, P. (2021) · Applied Sciences · doi:10.3390/app11146421 · Cited by 718 · see citing works
Active Retrieval Augmented Generation
Jiang, Z., Xu, F., Gao, L., Sun, Z., Liu, Q., Dwivedi-Yu, J., Yang, Y., Callan, J., & Neubig, G. (2023) · Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2023.emnlp-main.495 · Cited by 497 · see citing works
ChatDev: Communicative Agents for Software Development
Qian, C., Liu, W., Liu, H., Chen, N., Dang, Y., Li, J., Yang, C., Chen, W., Su, Y., Cong, X., et al. (2024) · Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2024.acl-long.810 · Cited by 490 · see citing works
In-Context Retrieval-Augmented Language Models
Ram, O., Levine, Y., Dalmedigos, I., Muhlgay, D., Shashua, A., Leyton-Brown, K., & Shoham, Y. (2023) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00605 · Cited by 449 · cited 1× · see citing works
“Additionally, introducing exter-nal knowledge relevant to the query via prompts can improve the model’s reasoning capabilities(Shi et al., 2023; Ram et al., 2023).”
Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate
Liang, T., He, Z., Jiao, W., Wang, X., Wang, Y., Wang, R., Yang, Y., Shi, S., & Tu, Z. (2023) · arXiv · doi:10.48550/arxiv.2305.19118 · Cited by 320 · see citing works
Camel: Communicative agents for" mind" exploration of large language model society
Li, G., Hammoud, H., Itani, H., Khizbullin, D., & Ghanem, B. (2023) · Advances in Neural Information Processing Systems 36 · doi:10.52202/075280-2264 · Cited by 314 · see citing works
Benchmarking Retrieval-Augmented Generation for Medicine
Xiong, G., Jin, Q., Lu, Z., & Zhang, A. (2024) · Findings of the Association for Computational Linguistics ACL 2024 · doi:10.18653/v1/2024.findings-acl.372 · Cited by 310 · see citing works
Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps
Ho, X., Duong Nguyen, A.-K., Sugawara, S., & Aizawa, A. (2020) · Proceedings of the 28th International Conference on Computational Linguistics · doi:10.18653/v1/2020.coling-main.580 · Cited by 287 · see citing works
Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate
Liang, T., He, Z., Jiao, W., Wang, X., Wang, Y., Wang, R., Yang, Y., Shi, S., & Tu, Z. (2024) · Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2024.emnlp-main.992 · Cited by 274 · see citing works
WebGPT: Browser-assisted question-answering with human feedback
Nakano, R., Hilton, J., Balaji, S., Wu, J., Ouyang, L., Kim, C., Hesse, C., Jain, S., Kosaraju, V., Saunders, W., et al. (2021) · arXiv · doi:10.48550/arxiv.2112.09332 · Cited by 272 · see citing works
REPLUG: Retrieval-Augmented Black-Box Language Models
Shi, W., Min, S., Yasunaga, M., Seo, M., James, R., Lewis, M., Zettlemoyer, L., & Yih, W.-T. (2024) · Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers) · doi:10.18653/v1/2024.naacl-long.463 · Cited by 209 · see citing works
Wang, Z., Mao, S., Wu, W., Ge, T., Wei, F., & Ji, H. (2024) · Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers) · doi:10.18653/v1/2024.naacl-long.15 · Cited by 74 · see citing works
Multi-Agent Consensus Seeking via Large Language Models
Chen, H., Ji, W., Xu, L., & Zhao, S. (2023) · arXiv · doi:10.48550/arxiv.2310.20151 · Cited by 16 · see citing works
War and Peace (WarAgent): Large Language Model-based Multi-Agent Simulation of World Wars
Hua, W., Fan, L., Li, L., Mei, K., Ji, J., Ge, Y., Hemphill, L., & Zhang, Y. (2023) · arXiv · doi:10.48550/arxiv.2311.17227 · Cited by 15 · cited 1× · see citing works
“This promotes interdisciplinary collaboration and the fusion of knowledge across different fields, playing a crucial role in medical consultations, judicial debates, and policy-making (Smit et al., 2023; Hua et al., 2023; Williams et al., 2023).”
Background
Flagged first, then by citations
Research works printed but not linked: 39
- Jinze Bai, Shuai Bai, Yunfei Chu, Zeyu Cui, Kai Dang, Xiaodong Deng, Yang Fan, Wenbin Ge, Yu Han, Fei Huang, Binyuan Hui, Luo Ji, Mei Li, Junyang Lin, Runji Lin, Dayiheng Liu, Gao Liu, Chengqiang Lu, Keming Lu, Jianxin Ma, Rui Men, Xingzhang Ren, Xuancheng Ren, Chuanqi Tan, Sinan Tan, Jianhong Tu, Peng Wang, Shijie Wang, Wei Wang, Sheng- guang Wu, Benfeng Xu, Jin Xu, An Yang, Hao Yang, Jian Yang, Shusheng Yang, Yang Yao, Bowen Yu, Hongyi Yuan, Zheng Yuan, Jianwei Zhang, Xingx- uan Zhang, Yichang Zhang, Zhenru Zhang, Chang Zhou, Jingren Zhou, Xiaohuan Zhou, and Tianhang Zhu. 2023. Qwen technical report. arXiv preprint arXiv:2309.16609. · arXiv
- Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel Ziegler, Jeffrey Wu, Clemens Winter, Chris Hesse, Mark Chen, Eric Sigler, Ma- teusz Litwin, Scott Gray, Benjamin Chess, Jack Clark, Christopher Berner, Sam McCandlish, Alec Radford, Ilya Sutskever, and Dario Amodei. 2020. Language models are few-shot learners. In Ad- vances in Neural Information Processing Systems, volume 33, pages 1877-1901.
- Curran Associates, Inc. Chi-Min Chan, Weize Chen, Yusheng Su, Jianxuan Yu, Wei Xue, Shanghang Zhang, Jie Fu, and Zhiyuan Liu. 2023. Chateval: Towards better llm-based eval- uators through multi-agent debate. arXiv preprint arXiv:2308.07201. · arXiv
- Hailin Chen, Fangkai Jiao, Xingxuan Li, Chengwei Qin, Mathieu Ravaut, Ruochen Zhao, Caiming Xiong, and Shafiq Joty. 2023a. Chatgpt's one-year anniversary: Are open-source large language models catching up? arXiv preprint arXiv:2311.16989. · arXiv
- Yilun Du, Shuang Li, Antonio Torralba, Joshua B Tenen- baum, and Igor Mordatch. 2023. Improving factual- ity and reasoning in language models through multia- gent debate. arXiv preprint arXiv:2305.14325. · arXiv
- Zhangyin Feng, Weitao Ma, Weijiang Yu, Lei Huang, Haotian Wang, Qianglong Chen, Weihua Peng, Xi- aocheng Feng, Bing Qin, et al. 2023. Trends in inte- gration of knowledge and large language models: A survey and taxonomy of methods, benchmarks, and applications. arXiv preprint arXiv:2311.05876. · arXiv
- Yao Fu, Hao Peng, Tushar Khot, and Mirella Lapata. 2023. Improving language model negotiation with self-play and in-context learning from ai feedback. arXiv preprint arXiv:2305.10142. · arXiv
- Hangfeng He, Hongming Zhang, and Dan Roth. 2022. Rethinking with retrieval: Faithful large language model inference. arXiv preprint arXiv:2301.00303. · arXiv
- Dan Hendrycks, Collin Burns, Steven Basart, Andy Zou, Mantas Mazeika, Dawn Song, and Jacob Steinhardt. 2021. Measuring massive multitask language under- standing. In International Conference on Learning Representations.
- Gautier Izacard, Patrick Lewis, Maria Lomeli, Lu- cas Hosseini, Fabio Petroni, Timo Schick, Jane Dwivedi-Yu, Armand Joulin, Sebastian Riedel, and Edouard Grave. 2022. Few-shot learning with re- trieval augmented language models. arXiv preprint arXiv:2208.03299. · arXiv
- Yu He Ke, Rui Yang, Sui An Lie, Taylor Xin Yi Lim, Hairil Rizal Abdullah, Daniel Shu Wei Ting, and Nan Liu. 2024. Enhancing diagnostic accuracy through multi-agent conversations: Using large language models to mitigate cognitive bias. arXiv preprint arXiv:2401.14589. · arXiv
- Nitish Shirish Keskar, Bryan McCann, Lav R Varshney, Caiming Xiong, and Richard Socher. 2019. Ctrl: A conditional transformer language model for control- lable generation. arXiv preprint arXiv:1909.05858. · arXiv
- Takeshi Kojima, Shixiang Shane Gu, Machel Reid, Yu- taka Matsuo, and Yusuke Iwasawa. 2022. Large lan- guage models are zero-shot reasoners. In NeurIPS.
- Xiao Liu, Hanyu Lai, Hao Yu, Yifan Xu, Aohan Zeng, Zhengxiao Du, Peng Zhang, Yuxiao Dong, and Jie Tang. 2023. Webglm: Towards an efficient web- enhanced question answering system with human preferences. In KDD, page 4549-4560.
- Hongyin Luo, Tianhua Zhang, Yung-Sung Chuang, Yuan Gong, Yoon Kim, Xixin Wu, Helen Meng, and James Glass. 2023. Search augmented instruction learning. In Findings of EMNLP, pages 3717-3729.
- Joon Sung Park, Joseph O'Brien, Carrie Jun Cai, Mered- ith Ringel Morris, Percy Liang, and Michael S. Bern- stein. 2023. Generative agents: Interactive simulacra of human behavior. In UIST.
- Xiao Pu, Mingqi Gao, and Xiaojun Wan. 2023. Summarization is (almost) dead. arXiv preprint arXiv:2309.09558. · arXiv
- Chen Qian, Xin Cong, Cheng Yang, Weize Chen, Yusheng Su, Juyuan Xu, Zhiyuan Liu, and Maosong Sun. 2023. Communicative agents for software de- velopment. arXiv preprint arXiv:2307.07924. · arXiv
- Zhihong Shao, Yeyun Gong, Yelong Shen, Minlie Huang, Nan Duan, and Weizhu Chen. 2023. Enhanc- ing retrieval-augmented large language models with iterative retrieval-generation synergy. In Findings of EMNLP, pages 9248-9274.
- Kurt Shuster, Spencer Poff, Moya Chen, Douwe Kiela, and Jason Weston. 2021. Retrieval augmentation reduces hallucination in conversation. In Findings of EMNLP, pages 3784-3803.
- Noam Slonim, Yonatan Bilu, Carlos Alzate, Roy Bar-Haim, Ben Bogin, Francesca Bonin, Leshem Choshen, Edo Cohen-Karlik, Lena Dankin, Lilach Edelstein, et al. 2021. An autonomous debating sys- tem. Nature, 591(7850):379-384.
- Andries Smit, Paul Duckworth, Nathan Grinsztajn, Kale-ab Tessera, Thomas D Barrett, and Arnu Preto- rius. 2023. Are we going mad? benchmarking multi- agent debate between language models for medical q&a. arXiv preprint arXiv:2311.17371. · arXiv
- James Thorne, Andreas Vlachos, Christos Christodoulopoulos, and Arpit Mittal. 2018. Fever: a large-scale dataset for fact extraction and verification. In NAACL, pages 809-819.
- Hugo Touvron, Louis Martin, Kevin Stone, Peter Al- bert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava, Shruti Bhosale, et al. 2023. Llama 2: Open founda- tion and fine-tuned chat models. arXiv preprint arXiv:2307.09288. · arXiv
- Harsh Trivedi, Niranjan Balasubramanian, Tushar Khot, and Ashish Sabharwal. 2023. Interleaving retrieval with chain-of-thought reasoning for knowledge- intensive multi-step questions. In ACL, pages 10014- 10037.
- Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc V Le, Ed H Chi, Sharan Narang, Aakanksha Chowdhery, and Denny Zhou. 2022. Self-consistency improves chain of thought reasoning in language models. In ICLR.
- Jason Wei, Yi Tay, Rishi Bommasani, Colin Raffel, Barret Zoph, Sebastian Borgeaud, Dani Yogatama, Maarten Bosma, Denny Zhou, Donald Metzler, et al. 2022. Emergent abilities of large language models. Transactions on Machine Learning Research.
- Ross Williams, Niyousha Hosseinichimeh, Aritra Ma- jumdar, and Navid Ghaffarzadegan. 2023. Epidemic modeling with generative agents. arXiv preprint arXiv:2307.04986. · arXiv
- Zhiheng Xi, Wenxiang Chen, Xin Guo, Wei He, Yiwen Ding, Boyang Hong, Ming Zhang, Junzhe Wang, Senjie Jin, Enyu Zhou, et al. 2023. The rise and potential of large language model based agents: A survey. arXiv preprint arXiv:2309.07864. · arXiv
- Ziyang Xiao, Dongxiang Zhang, Yangjun Wu, Lilin Xu, Yuan Jessica Wang, Xiongwei Han, Xiaojin Fu, Tao Zhong, Jia Zeng, Mingli Song, and Gang Chen. 2024. Chain-of-experts: When LLMs meet complex opera- tions research problems. In The Twelfth International Conference on Learning Representations.
- Kai Xiong, Xiao Ding, Yixin Cao, Ting Liu, and Bing Qin. 2023. Examining inter-consistency of large lan- guage models collaboration: An in-depth analysis via debate. In Findings of EMNLP, pages 7572-7590.
- Xiaohan Xu, Ming Li, Chongyang Tao, Tao Shen, Reynold Cheng, Jinyang Li, Can Xu, Dacheng Tao, and Tianyi Zhou. 2024. A survey on knowledge dis- tillation of large language models. arXiv preprint arXiv:2402.13116. · arXiv
- Zhenran Xu, Senbao Shi, Baotian Hu, Jindi Yu, Dong- fang Li, Min Zhang, and Yuxiang Wu. 2023. To- wards reasoning in large language models via multi- agent peer review collaboration. arXiv preprint arXiv:2311.08152. · arXiv
- Zhilin Yang, Peng Qi, Saizheng Zhang, Yoshua Bengio, William Cohen, Ruslan Salakhutdinov, and Christo- pher D Manning. 2018. Hotpotqa: A dataset for diverse, explainable multi-hop question answering. In EMNLP, pages 2369-2380.
- Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik R Narasimhan, and Yuan Cao. 2022. React: Synergizing reasoning and acting in language models. In ICLR.
- Zhangyue Yin, Qiushi Sun, Qipeng Guo, Jiawen Wu, Xipeng Qiu, and Xuan-Jing Huang. 2023. Do large language models know what they don't know? In Findings of the Association for Computational Lin- guistics: ACL 2023, pages 8653-8665.
- Ceyao Zhang, Kaijie Yang, Siyi Hu, Zihao Wang, Guanghe Li, Yihang Sun, Cheng Zhang, Zhaowei Zhang, Anji Liu, Song-Chun Zhu, et al. 2023. Proa- gent: Building proactive cooperative ai with large language models. arXiv preprint arXiv:2308.11339. · arXiv
- Lianmin Zheng, Wei-Lin Chiang, Ying Sheng, Siyuan Zhuang, Zhanghao Wu, Yonghao Zhuang, Zi Lin, Zhuohan Li, Dacheng Li, Eric Xing, Hao Zhang, Joseph E. Gonzalez, and Ion Stoica. 2023. Judging LLM-as-a-judge with MT-bench and chatbot arena. In NeurIPS Datasets and Benchmarks Track.
- Ao Zou, Wenning Hao, Dawei Jin, Shichen Zou, Yu Zheng, Feiyan Sun, and Li Xiang. 2024. An ef- ficient corpus indexer for dynamic corpora retrieval. Expert Systems with Applications, 254:124306. · DOI
Cited by
Sorted by citations
Scaling Large Language Model-based Multi-Agent Collaboration
Qian, C., Xie, Z., Wang, Y., Liu, W., Zhu, K., Xia, H., Dang, Y., Du, Z., Chen, W., Yang, C., et al. (2024) · arXiv · doi:10.48550/arxiv.2406.07155 · Cited by 8 · see citing works
Self-citationFree-MAD: Consensus-Free Multi-Agent Debate
Cui, Y., Fu, H., Zhang, H., Wang, L., & Zuo, C. (2026) · Findings of the Association for Computational Linguistics: ACL 2026 · doi:10.18653/v1/2026.findings-acl.1600 · Cited by 3 · see citing works
Gómez Álvarez, S., Mozo Quesada, A., Navarro, T., Gálvez Rojas, S., & López Valverde, F. (2026) · Journal of Intelligent Information Systems · doi:10.1007/s10844-026-01086-z
Multi-Agent Debate Strategies: Survey, Taxonomy, and Challenges
Motger, Q., Oriol, M., Marco, J., & Franch, X. (2026) · arXiv · doi:10.48550/arxiv.2607.26212
- Authors
- Wang, H., Du, X., Yu, W., Chen, Q., Zhu, K., Chu, Z., Yan, L., & Guan, Y.
- Affiliations
- Harbin Institute of Technology (CN)
- Sun Yat-sen University (CN)
- Zhejiang University (CN)
- Corresponding author
- Guan, Yi
- Venue
- Neurocomputing
- Publisher
- Elsevier BV
- Published
- 2025-02
- Volume
- 618
- Pages
- 129063
- ISSN
- 0925-2312 (ISSN-L)
- OpenAlex
- W4404958317
- Cited by
- 36
- References
- 20
- Citations by year
- 2026: 14 · 2025: 16 · 2024: 6
- FWCI
- 4.67
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- Neurocomputing (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Key Research and Development Program of China (2021ZD0113302, 2021ZD0110900)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Multi-Agent Systems and Negotiation
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Artificial Intelligence › Logic, Reasoning, and Knowledge
- Keywords
- knowledge consistency, large language models
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
