Exchange-of-Thought: Enhancing Large Language Model Capabilities through Cross-Model Communication
Open accessAbstract
Large Language Models (LLMs) have recently made significant strides in complex reasoning tasks through the Chain-of-Thought technique.Despite this progress, their reasoning is often constrained by their intrinsic understanding, lacking external insights.To address this, we propose Exchange-of-Thought (EoT), a novel framework that enables cross-model communication during problem-solving.Drawing inspiration from network topology, EoT integrates four unique communication paradigms: Memory, Report, Relay, and Debate.This paper delves into the communication dynamics and volume associated with each paradigm.To counterbalance the risks of incorrect reasoning chains, we implement a robust confidence evaluation mechanism within these communications.Our experiments across diverse complex reasoning tasks demonstrate that EoT significantly surpasses established baselines, underscoring the value of external insights in enhancing LLM performance.Furthermore, we show that EoT achieves these superior results in a cost-effective manner, marking a promising advancement for efficient and collaborative AI problem-solving."Two heads are better than one.
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.
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?
More recent studies extend the debate framework by introducing role asymmetry, adjustable debate intensity, and persuasiveness-oriented strategies.
“More recent studies extend this framework by introducing role asymmetry, adjustable debate intensity, and persuasiveness-oriented strategies (Yin et al., 2023; Liang et al., 2024; Khan et al., 2024; Chang, 2024).”
From A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems (2025) · cites this paper as Yin et al., 2023
The Debate description (section 4.1, page unavailable) assigns different functions to child and parent nodes, supporting role asymmetry. The Round Analysis describes more exchanges when consensus is difficult, supporting adjustable debate intensity. Our copy does not describe persuasiveness-oriented strategies; the sentence’s multiple citations do not specify which source supports that part. (LLM, conf=0.86)
Experimental — accuracy not yet measuredEoT was shown to outperform CoT.
“EoT was shown to outperform CoT (Yin et al., 2023).”
From Stop Overvaluing Multi-Agent Debate -- We Must Rethink Evaluation and Embrace Model Heterogeneity (2025) · cites this paper as Yin et al., 2023
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
Training language models to follow instructions with human feedback
Ouyang, L., Wu, J., Jiang, X., Almeida, D., Wainwright, C. L., Mishkin, P., Zhang, C., Agarwal, S., Slama, K., Ray, A., et al. (2022) · arXiv · doi:10.48550/arxiv.2203.02155 · Cited by 4,208 · see citing works
Reflexion: Language Agents with Verbal Reinforcement Learning
Shinn, N., Cassano, F., Berman, E., Gopinath, A., Narasimhan, K., & Yao, S. (2023) · arXiv · doi:10.48550/arxiv.2303.11366 · Cited by 1,087 · see citing works
Sustainable AI: AI for sustainability and the sustainability of AI
van Wynsberghe, A. (2021) · AI and Ethics · doi:10.1007/s43681-021-00043-6 · Cited by 939 · see citing works
Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
Srivastava, A., Rastogi, A., Rao, A., Shoeb, A. A. M., Abid, A., Fisch, A., Brown, A. R., Santoro, A., Gupta, A., Garriga-Alonso, A., et al. (2022) · arXiv · doi:10.48550/arxiv.2206.04615 · Cited by 569 · see citing works
Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
Bai, Y., Jones, A., Ndousse, K., Askell, A., Chen, A., DasSarma, N., Drain, D., Fort, S., Ganguli, D., Henighan, T., et al. (2022) · arXiv · doi:10.48550/arxiv.2204.05862 · Cited by 442 · see citing works
Program Induction by Rationale Generation: Learning to Solve and Explain Algebraic Word Problems
Ling, W., Yogatama, D., Dyer, C., & Blunsom, P. (2017) · Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p17-1015 · Cited by 325 · 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. (2023) · arXiv · doi:10.48550/arxiv.2305.19118 · Cited by 320 · see citing works
Automatic Chain of Thought Prompting in Large Language Models
Zhang, Z., Zhang, A., Li, M., & Smola, A. (2022) · arXiv · doi:10.48550/arxiv.2210.03493 · Cited by 274 · see citing works
Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them
Suzgun, M., Scales, N., Schärli, N., Gehrmann, S., Tay, Y., Chung, H. W., Chowdhery, A., Le, Q., Chi, E., Zhou, D., et al. (2023) · Findings of the Association for Computational Linguistics: ACL 2023 · doi:10.18653/v1/2023.findings-acl.824 · Cited by 253 · see citing works
<i>Did Aristotle Use a Laptop?</i> A Question Answering Benchmark with Implicit Reasoning Strategies
Geva, M., Khashabi, D., Segal, E., Khot, T., Roth, D., & Berant, J. (2021) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00370 · Cited by 242 · see citing works
Self-Refine: Iterative Refinement with Self-Feedback
Madaan, A., Tandon, N., Gupta, P., Hallinan, S., Gao, L., Wiegreffe, S., Alon, U., Dziri, N., Prabhumoye, S., Yang, Y., et al. (2023) · arXiv · doi:10.48550/arxiv.2303.17651 · Cited by 219 · see citing works
PAL: Program-aided Language Models
Gao, L., Madaan, A., Zhou, S., Alon, U., Liu, P., Yang, Y., Callan, J., & Neubig, G. (2022) · arXiv · doi:10.48550/arxiv.2211.10435 · Cited by 155 · see citing works
Improving Factuality and Reasoning in Language Models through Multiagent Debate
Du, Y., Li, S., Torralba, A., Tenenbaum, J. B., & Mordatch, I. (2023) · arXiv · doi:10.48550/arxiv.2305.14325 · Cited by 96 · see citing works
Making Language Models Better Reasoners with Step-Aware Verifier
Li, Y., Lin, Z., Zhang, S., Fu, Q., Chen, B., Lou, J.-G., & Chen, W. (2023) · Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2023.acl-long.291 · Cited by 69 · see citing works
Efficient Streaming Language Models with Attention Sinks
Xiao, G., Tian, Y., Chen, B., Han, S., & Lewis, M. (2023) · arXiv · doi:10.48550/arxiv.2309.17453 · Cited by 55 · see citing works
Large Language Models Cannot Self-Correct Reasoning Yet
Huang, J., Chen, X., Mishra, S., Zheng, H. S., Yu, A. W., Song, X., & Zhou, D. (2023) · arXiv · doi:10.48550/arxiv.2310.01798 · Cited by 36 · see citing works
Focused Transformer: Contrastive Training for Context Scaling
Tworkowski, S., Staniszewski, K., Pacek, M., Wu, Y., Michalewski, H., & Milos, P. (2023) · Advances in Neural Information Processing Systems 36 · doi:10.52202/075280-1849 · Cited by 18 · see citing works
Can Large Language Models Really Improve by Self-critiquing Their Own Plans?
Valmeekam, K., Marquez, M., & Kambhampati, S. (2023) · arXiv · doi:10.48550/arxiv.2310.08118 · Cited by 8 · see citing works
Flagged first, then by citations
Research works printed but not linked: 31
- Yao Fu, Hao Peng, Ashish Sabharwal, Peter Clark, and Tushar Khot. 2023b. Complexity-based prompting for multi-step reasoning. In The Eleventh Interna- tional Conference on Learning Representations.
- Deep Ganguli, Amanda Askell, Nicholas Schiefer, Thomas Liao, Kamilė Lukošiūtė, Anna Chen, Anna Goldie, Azalia Mirhoseini, Catherine Olsson, Danny Hernandez, et al. 2023. The capacity for moral self- correction in large language models. arXiv preprint arXiv:2302.07459. · arXiv
- David Ha and Yujin Tang. 2022. Collective intelligence for deep learning: A survey of recent developments. Collective Intelligence, 1(1):26339137221114874.
- Mohammad Javad Hosseini, Hannaneh Hajishirzi, Oren Etzioni, and Nate Kushman. 2014. Learning to solve arithmetic word problems with verb categorization. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 523-533. Association for Computational Lin- guistics. · DOI
- Tushar Khot, Harsh Trivedi, Matthew Finlayson, Yao Fu, Kyle Richardson, Peter Clark, and Ashish Sab- harwal. 2023. Decomposed prompting: A modular approach for solving complex tasks. In The Eleventh International Conference on Learning Representa- tions.
- Takeshi Kojima, Shixiang Shane Gu, Machel Reid, Yu- taka Matsuo, and Yusuke Iwasawa. 2022. Large lan- guage models are zero-shot reasoners. In Advances in Neural Information Processing Systems.
- Rik Koncel-Kedziorski, Hannaneh Hajishirzi, Ashish Sabharwal, Oren Etzioni, and Siena Dumas Ang. 2015. Parsing algebraic word problems into equa- tions. Transactions of the Association for Computa- tional Linguistics, 3:585-597. · DOI
- Rik Koncel-Kedziorski, Subhro Roy, Aida Amini, Nate Kushman, and Hannaneh Hajishirzi. 2016. MAWPS: A math word problem repository. In Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Hu- man Language Technologies, pages 1152-1157, San Diego, California. Association for Computational Linguistics. · DOI
- Harrison Lee, Samrat Phatale, Hassan Mansoor, Kellie Lu, Thomas Mesnard, Colton Bishop, Victor Car- bune, and Abhinav Rastogi. 2023. Rlaif: Scaling reinforcement learning from human feedback with ai feedback. arXiv preprint arXiv:2309.00267. · arXiv
- Xiaonan Li, Kai Lv, Hang Yan, Tianyang Lin, Wei Zhu, Yuan Ni, Guotong Xie, Xiaoling Wang, and Xipeng Qiu. 2023a. Unified demonstration retriever for in- context learning. ArXiv preprint, abs/2305.04320. · arXiv
- Xiaonan Li and Xipeng Qiu. 2023a. Finding supporting examples for in-context learning. ArXiv preprint, abs/2302.13539. · arXiv
- Xiaonan Li and Xipeng Qiu. 2023b. Mot: Pre- thinking and recalling enable chatgpt to self- improve with memory-of-thoughts. ArXiv preprint, abs/2305.05181. · arXiv
- Qing Lyu, Shreya Havaldar, Adam Stein, Li Zhang, Delip Rao, Eric Wong, Marianna Apidianaki, and Chris Callison-Burch. 2023. Faithful chain-of- thought reasoning. ArXiv preprint, abs/2301.13379. · arXiv
- Arkil Patel, Satwik Bhattamishra, and Navin Goyal. 2021. Are NLP models really able to solve simple math word problems? In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 2080-2094, Online. Association for Computational Linguistics. · DOI · Paper page
- Pragaash Ponnusamy, Alireza Ghias, Yi Yi, Ben- jamin Yao, Chenlei Guo, and Ruhi Sarikaya. 2022. Feedback-based self-learning in large-scale conversa- tional ai agents. AI magazine, 42(4):43-56.
- Nir Ratner, Yoav Levine, Yonatan Belinkov, Ori Ram, Inbal Magar, Omri Abend, Ehud Karpas, Amnon Shashua, Kevin Leyton-Brown, and Yoav Shoham. 2023. Parallel context windows for large language models. In Proceedings of the 61st Annual Meet- ing of the Association for Computational Linguistics (Volume 1: Long Papers), pages 6383-6402, Toronto, Canada. Association for Computational Linguistics. · DOI
- Subhro Roy and Dan Roth. 2015. Solving general arith- metic word problems. In Proceedings of the 2015 Conference on Empirical Methods in Natural Lan- guage Processing, EMNLP 2015, Lisbon, Portugal, September 17-21, 2015, pages 1743-1752. The As- sociation for Computational Linguistics. · DOI
- Yixuan Su, Tian Lan, Yan Wang, Dani Yogatama, Ling- peng Kong, and Nigel Collier. 2022. A contrastive framework for neural text generation. In Advances in Neural Information Processing Systems.
- Alon Talmor, Jonathan Herzig, Nicholas Lourie, and Jonathan Berant. 2019. CommonsenseQA: A ques- tion answering challenge targeting commonsense knowledge. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Tech- nologies, Volume 1 (Long and Short Papers), pages 4149-4158, Minneapolis, Minnesota. Association for Computational Linguistics. · DOI
- Romal Thoppilan, Daniel De Freitas, Jamie Hall, Noam Shazeer, Apoorv Kulshreshtha, Heng-Tze Cheng, Alicia Jin, Taylor Bos, Leslie Baker, Yu Du, et al. 2022. Lamda: Language models for dialog applica- tions. ArXiv preprint, abs/2201.08239. · arXiv
- Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timothée Lacroix, Baptiste Rozière, Naman Goyal, Eric Hambro, Faisal Azhar, et al. 2023a. Llama: Open and effi- cient foundation language models. ArXiv preprint, abs/2302.13971. · arXiv
- Jianing Wang, Qiushi Sun, Nuo Chen, Xiang Li, and Ming Gao. 2023a. Boosting language models rea- soning with chain-of-knowledge prompting. ArXiv preprint, abs/2306.06427. · arXiv
- Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc V Le, Ed H. Chi, Sharan Narang, Aakanksha Chowdhery, and Denny Zhou. 2023c. Self-consistency improves chain of thought reasoning in language models. In The Eleventh International Conference on Learning Representations.
- Jason Wei, Yi Tay, Rishi Bommasani, Colin Raffel, Barret Zoph, Sebastian Borgeaud, Dani Yogatama, Maarten Bosma, Denny Zhou, Donald Metzler, Ed H. Chi, Tatsunori Hashimoto, Oriol Vinyals, Percy Liang, Jeff Dean, and William Fedus. 2022a. Emer- gent abilities of large language models. Transactions on Machine Learning Research.
- Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, brian ichter, Fei Xia, Ed H. Chi, Quoc V Le, and Denny Zhou. 2022b. Chain of thought prompt- ing elicits reasoning in large language models. In Advances in Neural Information Processing Systems.
- Carole-Jean Wu, Ramya Raghavendra, Udit Gupta, Bilge Acun, Newsha Ardalani, Kiwan Maeng, Glo- ria Chang, Fiona Aga, Jinshi Huang, Charles Bai, et al. 2022. Sustainable ai: Environmental implica- tions, challenges and opportunities. Proceedings of Machine Learning and Systems, 4:795-813.
- 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.
- Zhangyue Yin, Qiushi Sun, Qipeng Guo, Jiawen Wu, Xipeng Qiu, and Xuanjing 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, Toronto, Canada. Association for Computational Linguistics. · DOI · Paper page
- Susan Zhang, Stephen Roller, Naman Goyal, Mikel Artetxe, Moya Chen, Shuohui Chen, Christopher De- wan, Mona Diab, Xian Li, Xi Victoria Lin, et al. 2022. Opt: Open pre-trained transformer language models. ArXiv preprint, abs/2205.01068. · arXiv
- Tianjun Zhang, Fangchen Liu, Justin Wong, Pieter Abbeel, and Joseph E. Gonzalez. 2023a. The wisdom of hindsight makes language models better instruc- tion followers. In Proceedings of the 40th Interna- tional Conference on Machine Learning, ICML'23.
- Chuanyang Zheng, Zhengying Liu, Enze Xie, Zhenguo Li, and Yu Li. 2023. Progressive-hint prompting improves reasoning in large language models. ArXiv preprint, abs/2304.09797. · arXiv
Cited by
Sorted by citations
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
Multi-Agent Collaboration Mechanisms: A Survey of LLMs
Tran, K.-T., Dao, D., Nguyen, M.-D., Pham, Q.-V., O'Sullivan, B., & Nguyen, H. D. (2025) · arXiv · doi:10.48550/arxiv.2501.06322 · Cited by 26 · see citing works
Voting or Consensus? Decision-Making in Multi-Agent Debate
Kaesberg, L. B., Becker, J., Wahle, J. P., Ruas, T., & Gipp, B. (2025) · Findings of the Association for Computational Linguistics: ACL 2025 · doi:10.18653/v1/2025.findings-acl.606 · Cited by 14 · see citing works
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
Fang, J., Peng, Y., Zhang, X., Wang, Y., Yi, X., Zhang, G., Xu, Y., Wu, B., Liu, S., Li, Z., et al. (2025) · arXiv · doi:10.48550/arxiv.2508.07407 · Cited by 6 · see citing works
MAgICoRe: Multi-Agent, Iterative, Coarse-to-Fine Refinement for Reasoning
Chen, J., Prasad, A., Saha, S., Stengel-Eskin, E., & Bansal, M. (2025) · Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2025.emnlp-main.1660 · Cited by 3 · see citing works
Language Agents as Optimizable Graphs
Zhuge, M., Wang, W., Kirsch, L., Faccio, F., Khizbullin, D., & Schmidhuber, J. (2024) · arXiv · doi:10.48550/arxiv.2402.16823 · Cited by 3 · see citing works
MDTeamGPT: Mitigating Context Collapse and Enabling Self-Evolution in Medical Multi-Agent Reasoning
Chen, K., Li, X., Yang, T., Wang, H., Yang, G., Huo, J., & Gao, Y. (2026) · Findings of the Association for Computational Linguistics: ACL 2026 · doi:10.18653/v1/2026.findings-acl.1427 · Cited by 1 · 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
Stop Overvaluing Multi-Agent Debate -- We Must Rethink Evaluation and Embrace Model Heterogeneity
Zhang, H., Cui, Z., Chen, J., Wang, X., Zhang, Q., Wang, Z., Wu, D., & Hu, S. (2025) · arXiv · doi:10.48550/arxiv.2502.08788
- Authors
- Yin, Z., Sun, Q., Chang, C., Guo, Q., Dai, J., Huang, X., & Qiu, X.
- Affiliations
- National University of Singapore (SG)
- Corresponding author
- Huang, Xuanjing
- Venue
- Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
- Published
- 2023
- Pages
- 15135-15153
- OpenAlex
- W4389524566
- Cited by
- 26
- References
- 18
- Citations by year
- 2026: 9 · 2025: 13 · 2024: 3 · 2023: 1
- FWCI
- 4.12
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Conference on Empirical Methods in Natural Language Processing (EMNLP) (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Natural Science Foundation of China (62022027)
- National Key Research and Development Program of China
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Multimodal Machine Learning Applications
- Keywords
- large language models, chain-of-thought, complex reasoning, multi-agent systems, confidence estimation, external knowledge
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
