Camel: Communicative agents for" mind" exploration of large language model society
Open accessThe DOI matches its Crossref record; 29 of the 29 references it cites were found in a registry or an index.
Abstract
The rapid advancement of chat-based language models has led to remarkable progress in complex task-solving. However, their success heavily relies on human input to guide the conversation, which can be challenging and time-consuming. This paper explores the potential of building scalable techniques to facilitate autonomous cooperation among communicative agents, and provides insight into their "cognitive" processes. To address the challenges of achieving autonomous cooperation, we propose a novel communicative agent framework named role-playing. Our approach involves using inception prompting to guide chat agents toward task completion while maintaining consistency with human intentions. We showcase how role-playing can be used to generate conversational data for studying the behaviors and capabilities of a society of agents, providing a valuable resource for investigating conversational language models. In particular, we conduct comprehensive studies on instruction-following cooperation in multi-agent settings. Our contributions include introducing a novel communicative agent framework, offering a scalable approach for studying the cooperative behaviors and capabilities of multi-agent systems, and open-sourcing our library to support research on communicative agents and beyond: https://github.com/camel-ai/camel.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
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?
In the citing paper
“The development of medical AI agents can be approached through two primary methodologies: graphical user interface (GUI)-based frameworks and coding-based development.110,111,112”
From A foundational architecture for AI agents in healthcare (2025) · cites this paper as [111]
Citations
Cites
The publisher hasn’t deposited this paper’s reference list.
Cited by
ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate
Chan, C.-M., Chen, W., Su, Y., Yu, J., Xue, W., Zhang, S., Fu, J., & Liu, Z. (2023) · arXiv · doi:10.48550/arxiv.2308.07201 · Cited by 725
A survey on LLM-based multi-agent systems: Workflow, infrastructure, and challenges
Li, X., Wang, S., Zeng, S., Wu, Y., & Yang, Y. (2024) · Vicinagearth · doi:10.1007/s44336-024-00009-2 · Cited by 404
MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoning
Tang, X., Zou, A., Zhang, Z., Li, Z., Zhao, Y., Zhang, X., Cohan, A., & Gerstein, M. (2024) · Findings of the Association for Computational Linguistics ACL 2024 · doi:10.18653/v1/2024.findings-acl.33 · Cited by 376
Empowering biomedical discovery with AI agents
Gao, S., Fang, A., Huang, Y., Giunchiglia, V., Noori, A., Schwarz, J. R., Ektefaie, Y., Kondic, J., & Zitnik, M. (2024) · Cell · doi:10.1016/j.cell.2024.09.022 · Cited by 315
AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenges
Sapkota, R., Roumeliotis, K. I., & Karkee, M. (2025) · arXiv · doi:10.48550/arxiv.2505.10468 · Cited by 295
LLMs for knowledge graph construction and reasoning: recent capabilities and future opportunities
Zhu, Y., Wang, X., Chen, J., Qiao, S., Ou, Y., Yao, Y., Deng, S., Chen, H., & Zhang, N. (2024) · World Wide Web · doi:10.1007/s11280-024-01297-w · Cited by 294
A review of large language models and autonomous agents in chemistry
Ramos, M. C., Collison, C. J., & White, A. D. (2025) · Chemical Science · doi:10.1039/d4sc03921a · Cited by 274
He, J., Treude, C., & Lo, D. (2025) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3712003 · Cited by 246
“Its responsibilities include defining high-level strategic goals, breaking them into actionable sub-tasks, delegating these tasks to the appropriate agents, monitoring progress, and ensuring that workflows align with overall project objectives [17, 56, 60, 75, 76, 106, 155, 158].”
LLM-Based Multi-Agent Systems for Software Engineering: Literature Review, Vision and the Road Ahead
He, J., Treude, C., & Lo, D. (2024) · arXiv · doi:10.48550/arxiv.2404.04834 · Cited by 246
“…• CommunicationParadigms: Styles of interaction, such as Cooperative (i.e., agents work together towards a shared goal) [1], De-bate (i.e., agents engage in discussions to challenge and refine ideas) [26], and Competitive (i.e., agents have conflicting objectives and compete against each other) [43].”
BackgroundAI Agents vs. Agentic AI: A Conceptual taxonomy, applications and challenges
Sapkota, R., Roumeliotis, K. I., & Karkee, M. (2026) · Information Fusion · doi:10.1016/j.inffus.2025.103599 · Cited by 671
Bandi, A., Kongari, B., Naguru, R., Pasnoor, S., & Vilipala, S. V. (2025) · Future Internet · doi:10.3390/fi17090404 · Cited by 207
AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenges
Sapkota, R., Roumeliotis, K. I., & Karkee, M. (2025) · SuperIntelligence - Robotics - Safety & Alignment · doi:10.70777/si.v2i3.15161 · Cited by 186
When Embodied AI Meets Industry 5.0: Human-Centered Smart Manufacturing
Xu, J., Sun, Q., Han, Q., & Tang, Y. S. (2025) · IEEE/CAA Journal of Automatica Sinica · doi:10.1109/jas.2025.125327 · Cited by 168
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 1,202
“Largely concurrent to the work in this paper, a body of recent work has explored how multiagent interaction can be used with large language models (Zhang et al., 2023; Li et al., 2024; Hong et al., 2023).”
Talk Isn't Always Cheap: Understanding Failure Modes in Multi-Agent Debate
Wynn, A., Satija, H., & Hadfield, G. (2025) · arXiv · doi:10.48550/arxiv.2509.05396 · Cited by 96
Xiao, T., & Xu, P. (2024) · Energy and Buildings · doi:10.1016/j.enbuild.2024.114691 · Cited by 95
Should we be going MAD? A Look at Multi-Agent Debate Strategies for LLMs
Smit, A., Duckworth, P., Grinsztajn, N., Barrett, T. D., & Pretorius, A. (2023) · arXiv · doi:10.48550/arxiv.2311.17371 · Cited by 73
Anatomy of an AI-powered malicious social botnet
Yang, K., & Menczer, F. (2024) · Journal of Quantitative Description: Digital Media · doi:10.51685/jqd.2024.icwsm.7 · Cited by 71
Large Language Model based Multi-Agents: A Survey of Progress and Challenges
Guo, T., Chen, X., Wang, Y., Chang, R., Pei, S., Chawla, N. V., Wiest, O., & Zhang, X. (2024) · arXiv · doi:10.48550/arxiv.2402.01680 · Cited by 1,713
Large Language Models as Biomedical Hypothesis Generators: A Comprehensive Evaluation
Qi, B., Zhang, K., Tian, K., Li, H., Chen, Z.-R., Zeng, S., Hua, E., Jinfang, H., & Zhou, B. (2024) · arXiv · doi:10.48550/arxiv.2407.08940 · Cited by 70
AI Reasoning in Deep Learning Era: From Symbolic AI to Neural–Symbolic AI
Liang, B., Wang, Y., & Tong, C. (2025) · Mathematics · doi:10.3390/math13111707 · Cited by 133
D-Bot: Database Diagnosis System using Large Language Models
Zhou, X., Li, G., Sun, Z., Liu, Z., Chen, W., Wu, J., Liu, J., Feng, R., & Zeng, G. (2024) · Proceedings of the VLDB Endowment · doi:10.14778/3675034.3675043 · Cited by 134
Self-citationLLM-Based Multi-Agent Decision-Making: Challenges and Future Directions
Sun, C., Huang, S., & Pompili, D. (2025) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2025.3562371 · Cited by 102
“In addition to LLM-based MADM, several works explored multi-agent interaction [68], [69], [70], e.g., multi-agent conversation and gaming.”
Shi, W., Xu, R., Zhuang, Y., Yu, Y., Zhang, J., Wu, H., Zhu, Y., Ho, J. C., Yang, C., & Wang, M. D. (2024) · Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2024.emnlp-main.1245 · Cited by 54
“We will explore stricter evaluation metrics to assess the cases of misinformation that could pose a risk within clinical settings in our future work.”
MethodChain of Agents: Large Language Models Collaborating on Long-Context Tasks
Zhang, Y., Sun, R., Chen, Y., Pfister, T., Zhang, R., & Arik, S. Ö. (2024) · arXiv · doi:10.48550/arxiv.2406.02818 · Cited by 47
“A large proportion of works focus on social simulation [52, 53] and frameworks [35].”
Evaluating the ability of large language models to emulate personality
Wang, Y., Zhao, J., Öneş, D. S., He, L., & Xin, X. (2025) · Scientific Reports · doi:10.1038/s41598-024-84109-5 · Cited by 111
Can Large Language Models Understand Real-World Complex Instructions?
He, Q., Zeng, J., Huang, W., Chen, L., Xiao, J., He, Q., Zhou, X., Chen, L., Wang, X., Huang, Y., et al. (2023) · arXiv · doi:10.48550/arxiv.2309.09150 · Cited by 43
Zhang, Z., Yao, Y., Zhang, A., Tang, X., Ma, X., He, Z., Wang, Y., Gerstein, M., Wang, R., Liu, G., et al. (2025) · ACM Computing Surveys · doi:10.1145/3719341 · Cited by 51
“Language agents have found extensive applications in practical fields such as engineering [56, 84, 103], natural sciences [11, 49, 78], and social sciences [2, 79].”
InfluentialWickramasekara, A., Breitinger, F., & Scanlon, M. (2025) · Forensic Science International Digital Investigation · doi:10.1016/j.fsidi.2024.301859 · Cited by 88
“Similar limitations are associated with MLLMs. Issues such as over-reliance on training data, sensitivity to word order in the input prompts, and vulnerability to prompts containing extra knowledge represent challenges in the capabilities of MLLMs [85].”
Learning to break: Knowledge-enhanced reasoning in multi-agent debate system
Wang, H., Du, X., Yu, W., Chen, Q., Zhu, K., Chu, Z., Yan, L., & Guan, Y. (2025) · Neurocomputing · doi:10.1016/j.neucom.2024.129063 · Cited by 36
“…requires the construction of agents with different roles, each of which performs its own duties and works together to complete the final task (Li et al., 2023; Zhang et al., 2023 Adversarial interactive methods usually build multiple agents and complete reasoning tasks in a debate manner (Fu…”
BackgroundA foundational architecture for AI agents in healthcare
Liu, F., Niu, Y., Zhang, Q., Wang, K., Dong, Z., Wong, I. N., Cheng, L., Li, T., Duan, L., Li, K., et al. (2025) · Cell Reports Medicine · doi:10.1016/j.xcrm.2025.102374 · Cited by 41
Self-citationA Survey on Trustworthy LLM Agents: Threats and Countermeasures
Yu, M., Meng, F., Zhou, X., Wang, S., Mao, J., Pan, L., Chen, T., Wang, K., Li, X., Zhang, Y., et al. (2025) · Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2 · doi:10.1145/3711896.3736561 · Cited by 34
“Extensive academic research and industry practices have validated this performance hierarchy: MAS > Single Agent > LLM [8, 54, 84, 100].”
A Survey on Trustworthy LLM Agents: Threats and Countermeasures
Yu, M., Meng, F., Zhou, X., Wang, S., Mao, J., Pang, L., Chen, T., Wang, K., Li, X., Zhang, Y., et al. (2025) · arXiv · doi:10.48550/arxiv.2503.09648 · Cited by 34
“Extensive academic research and industry practices have validated this performance hierarchy: MAS > Single Agent > LLM [8, 54, 84, 100].”
Domain-specific chatbots for science using embeddings
Yager, K. G. (2023) · Digital Discovery · doi:10.1039/d3dd00112a · Cited by 37
Bai, X., Huang, S., Wei, C., & Wang, R. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.126357 · Cited by 47
Mitigating reasoning hallucination through Multi-agent Collaborative Filtering
Shi, J., Zhao, J., Wu, X., Xu, R., Jiang, Y.-H., & He, L. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.125723 · Cited by 47
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 680
“There are recent open-source frameworks allowing for experimentation with cooperative LLM-based MASs. CAMEL [74] provides a role-playing framework where a task-specific agent and two cooperating AI agents (User and Assistant) work to complete tasks via role-based conversations.”
InfluentialXu, Z., Chen, T., Huang, Z., Xing, Y., & Chen, S. (2025) · IEEE Intelligent Transportation Systems Magazine · doi:10.1109/mits.2025.3551736 · Cited by 44
“It has been demonstrated that large language models (LLMs) have impressive capabilities for acquiring knowledge, reasoning, and interacting with humans [37], [38], [39].”
Can Large Language Models Understand Real-World Complex Instructions?
He, Q., Zeng, J., Huang, W., Chen, L., Xiao, J., He, Q., Zhou, X., Liang, J., & Xiao, Y. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i16.29777 · Cited by 125
Efficient Training and Inference: Techniques for Large Language Models Using LlamaPreprint
Cunningham, S. R., Archambault, D., & Kung, A. (2024) · doi:10.36227/techrxiv.171651876.65094225/v1 · Cited by 32
Taming Unleashed Large Language Models With Blockchain for Massive Personalized Reliable Healthcare
Sun, L., Liu, D., Wang, M., Han, Y., Zhang, Y., Zhou, B., Ren, Y. C., & zhu, P. (2025) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2025.3528526 · Cited by 27
“Recent research has demonstrated that AI agent technologies can enhance LLM performance in handling complex tasks like CAME [29], AgentVerse [30], MetaGPT [31], Chat-Dev [32], and AutoGen [33].”
Automating quantum computing laboratory experiments with an agent-based AI framework
Cao, S., Zhang, Z., Alghadeer, M., Fasciati, S. D., Piscitelli, M., Bakr, M. S., Leek, P., & Aspuru‐Guzik, A. (2025) · Patterns · doi:10.1016/j.patter.2025.101372 · Cited by 75
Liu, Y., Liu, Y., Zhang, X., Chen, X., & Yan, R. (2025) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3726302.3730092 · Cited by 69
“Other studies emphasize diversifying agent roles to enrich the debate process [24, 33].”
A Survey on Agent Workflow – Status and Future
Yu, C., Cheng, Z., Cui, H., Gao, Y., Luo, Z., Wang, Y., Zheng, H., & Zhao, Y. (2025) · International Conference on Artificial Intelligence and Big Data (ICAIBD) · doi:10.1109/icaibd64986.2025.11082076 · Cited by 69
MedAide: Information fusion and anatomy of medical intents via LLM-based agent collaboration
Yang, D., Wei, J., Li, M., Liu, J., Liu, L., Hu, M., He, J., Ju, Y., Zhou, W., Liu, Y., et al. (2025) · Information Fusion · doi:10.1016/j.inffus.2025.103743 · Cited by 68
“In this context, LLM-based automated agents are proposed to provide effective perception and decision-making skilfulness by incorporating external tools and databases [22].”
Nechesov, A. V., & Ruponen, J. (2024) · Technologies · doi:10.3390/technologies12120271 · Cited by 36
A Survey of Reasoning with Foundation ModelsPreprint
Sun, J., Zheng, C., Xie, E., Liu, Z., Chu, R., Liu, J., Xu, J., Ding, M., Li, H., Geng, M., et al. (2023) · OSF Preprints (OSF Preprints) · doi:10.31219/osf.io/ac4sp · Cited by 158
Agentic AI for Scientific Discovery: A Survey of Progress, Challenges, and Future Directions
Gridach, M., Nanavati, J., Abidine, K. Z. E., Mendes, L., & Mack, C. (2025) · arXiv · doi:10.48550/arxiv.2503.08979 · Cited by 18
RescueADI: Adaptive Disaster Interpretation in Remote Sensing Images With Autonomous Agents
Liu, Z., Zhao, D., Yuan, B., & Jiang, Z. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3532594 · Cited by 42
“Camel [49] proposes that allowing an LLM to engage in role-playing and multiagent cooperation can enhance its ability to solve complex problems.”
GenAINet: Enabling Wireless Collective Intelligence via Knowledge Transfer and Reasoning
Zou, H., Zhao, Q., Lasaulce, S., Bariah, L., Bennis, M., & Debbah, M. A. (2025) · IEEE Access · doi:10.1109/access.2025.3565859 · Cited by 40
“There are three main advantages possessed by LLMs compared to conventional Deep Neural Networks (DNNs): emerging abilities [11], [12], [13], reasoning & planning [14], and autonomous cooperation [15], [16] as a potential enabler for CI in 6G era.”
Towards LLM-Based Failure Localization in Production-Scale Networks
Wang, C., Zhang, X., Lu, R., Lin, X., Zeng, X., Zhang, X., An, Z., Wu, G., Gao, J., Tian, C., et al. (2025) · ACM SIGCOMM Conference (SIGCOMM) · doi:10.1145/3718958.3750505 · Cited by 44
Why Do Multi-Agent LLM Systems Fail?
Cemri, M., Pan, M. Z., Yang, S., Agrawal, L. A., Chopra, B., Tiwari, R., Keutzer, K., Parameswaran, A., Klein, D., Ramchandran, K., et al. (2025) · arXiv · doi:10.48550/arxiv.2503.13657 · Cited by 630
Iterative Prompt Refinement for Mining Gene Relationships from ChatGPT
Chen, Y., Gao, J., Petruc, M., Hammer, R., Popescu, M., & Xu, D. H. (2024) · International Journal of Artificial Intelligence and Robotics Research · doi:10.1142/s2972335324500054 · Cited by 16
AgentSpec: Customizable Runtime Enforcement for Safe and Reliable LLM Agents
Wang, H., Poskitt, C. M., & Sun, J. (2026) · Proceedings of the 2026 IEEE/ACM 48th International Conference on Software Engineering · doi:10.1145/3744916.3764546 · Cited by 14
“Large Language Model (LLM) agents [6, 14, 19, 28, 31, 35, 39, 48] extend the capabilities of LLMs by autonomously perceiving, planning, and acting within interactive environments.”
ChatLLM network: More brains, more intelligence
Hao, R., Hu, L., Qi, W., Wu, Q., Zhang, Y., & Nie, L. (2025) · AI Open · doi:10.1016/j.aiopen.2025.01.001 · Cited by 65
Wang, D., Cheng, T., Wang, S., Chen, Y., & Yin, Y. (2025) · Information Processing & Management · doi:10.1016/j.ipm.2025.104297 · Cited by 19
Towards A Holistic Landscape of Situated Theory of Mind in Large Language Models
Ma, Z., Sansom, J., Peng, R., & Chai, J. Y. (2023) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2023.findings-emnlp.72 · Cited by 108
Kim, J. H., & Kim, H. R. (2024) · Research Square · doi:10.21203/rs.3.rs-4328966/v1 · Cited by 49
Yager, K. G. (2024) · Digital Discovery · doi:10.1039/d4dd00178h · Cited by 12
Project Sid: Many-agent simulations toward AI civilization
AL, A., Ahn, A., Becker, N., Carroll, S., Christie, N., Cortes, M., Demirci, A., Du, M., Li, F., Luo, S., et al. (2024) · arXiv · doi:10.48550/arxiv.2411.00114 · Cited by 12
“Multi-agent frameworks have been deployed in software development (43; 27), cooperative robotic control (60), scientific experiments (12; 47), and debates (3).”
BackgroundYang, L., Wu, Y., Xu, R., Zhang, K., Yang, X., & Wu, K. (2025) · International Conference on Electronic Communication, Computer Science and Technology (ECCST) · doi:10.1109/eccst68196.2025.11441200 · Cited by 12
Takata, R., Masumori, A., & Ikegami, T. (2024) · Entropy · doi:10.3390/e26121092 · Cited by 37
Helpful assistant or fruitful facilitator? Investigating how personas affect language model behavior
de Araujo, P. H. L., & Roth, B. (2025) · PLoS ONE · doi:10.1371/journal.pone.0325664 · Cited by 41
“To this end, we query models with data from the following datasets: BBQ (Parrish et al., 2022) is a question-answering dataset that highlights 11 social bias categories concerning, for example, race, gender, and socioeconomic status.”
Multi-Agentic LLMs for Personalizing STEM Texts
Vaccaro, M., Friday, M., & Zaghi, A. E. (2025) · Applied Sciences · doi:10.3390/app15137579 · Cited by 23
CFDAgent: A language-guided, zero-shot multi-agent system for complex flow simulation
Xu, Z., wang, L., Wang, C., Chen, Y., Luo, Q. Z., Yao, H.-D., Wang, S., & He, G. (2025) · Physics of Fluids · doi:10.1063/5.0294696 · Cited by 33
“Despite their impressive capabilities, current standalone LLMs remain limited in tasks requiring extensive, precise, and systematic content generation—particularly in computational physics and simulation [7] due to persistent challenges such as hallu-cination [8].”
Zero-shot Knowledge Graph Question Generation via Multi-agent LLMs and Small Models Synthesis
Zhao, R., Tang, J., Zeng, W., Chen, Z., & Zhao, X. H. (2024) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3627673.3679805 · Cited by 45
Higher Performance of Mistral Large on MMLU Benchmark through Two-Stage Knowledge DistillationPreprint
Wilkins, J., & Rodriguez, M. (2024) · Research Square · doi:10.21203/rs.3.rs-4410506/v1 · Cited by 16
SmartControl: Interactive PID controller design powered by LLM agents and control system expertise
Tohma, K., OKUR, H. İ., Gürsoy-Demir, H., Aydın, M. N., & Yeroğlu, C. (2025) · SoftwareX · doi:10.1016/j.softx.2025.102194 · Cited by 19
Real-GPT: Efficiently Tailoring LLMs for Informed Decision-Making in the Real Estate Industry
Gloria, B., Melsbach, J. W., Bienert, S., & Schoder, D. (2024) · Journal of Real Estate Portfolio Management · doi:10.1080/10835547.2024.2372748 · Cited by 12
Generative AI Agents for Knowledge Work Augmentation in Finance
Ganesh, S., Ardon, L., Borrajo, D., Garg, D., Madhushani, U., Narayanan, A. L., Canonaco, G., & Veloso, M. (2024) · Annual Review of Control Robotics and Autonomous Systems · doi:10.1146/annurev-control-022823-033813 · Cited by 16
Peng, Z., Kuai, X., Ke, S., Dong, X., & Guo, R. (2025) · Big Earth Data · doi:10.1080/20964471.2025.2483541 · Cited by 14
“In recent times, MAS have showcased their efficacy in addressing complex scenario challenges, such as role-playing (Li et al., 2023), interactive environmental simulation with users (Park et al., 2023), and collaborative reasoning (Chen et al., 2023a).”
Mushtaq, A., Naeem, R., Ghaznavi, I., Taj, I., Hashmi, I., & Qadir, J. (2025) · IEEE Global Engineering Education Conference (EDUCON) · doi:10.1109/educon62633.2025.11016653 · Cited by 46
“Systems such as LangChain [30], AutoGen [31], and ReAct [32] enhance agent autonomy by reducing human input, while Camel AI [16] employs role-playing and inception prompting for minimal intervention in agent collaboration.”
InfluentialHe, Z.-T., Cao, P., Chen, Y., Liu, K., Li, R., Sun, M., & Zhao, J. (2023) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2023.findings-emnlp.613 · Cited by 59
Nonomura, R., & Mori, H. (2025) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2025.1582287 · Cited by 20
“The CAMEL framework [27] demonstrates how agents with distinct roles can collaborate to solve problems.”
DAWN: Designing Distributed Agents in a Worldwide Network
Aminiranjbar, Z., Tang, J., Wang, Q., Pant, S., & Viswanathan, M. (2025) · IEEE Access · doi:10.1109/access.2025.3588425 · Cited by 19
“Issues such as inefficient communication [11], increased computational costs, unreliable execution and communication sequences [15], and vulnerability to attacks [33] have underscored the need for a reliable platform to support agent collaboration.”
BackgroundGeneral-Purpose Models for the Chemical Sciences: LLMs and Beyond
Alampara, N., Aneesh, A., Ríos-García, M., Mirza, A., Schilling-Wilhelmi, M., Aghajani, A. A., Sun, M., Prastalo, G., & Jablonka, K. M. (2026) · Chemical Reviews · doi:10.1021/acs.chemrev.5c00583 · Cited by 35
Cooper: Coordinating Specialized Agents towards a Complex Dialogue Goal
Cheng, Y., Liu, W., Wang, J., Leong, C. T., Ouyang, Y., Li, W., Wu, X., & Zheng, Y. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i16.29739 · Cited by 39
DAWN: Designing Distributed Agents in a Worldwide Network
Aminiranjbar, Z., Tang, J., Wang, Q., Pant, S., & Viswanathan, M. (2024) · arXiv · doi:10.48550/arxiv.2410.22339 · Cited by 8
“Issues such as inefficient communication [11], increased computational costs, unreliable execution and communication sequences [15], and vulnerability to attacks [33] have underscored the need for a reliable platform to support agent collaboration.”
BackgroundCooperate or Collapse: Emergence of Sustainable Cooperation in a Society of LLM Agents
Piatti, G., Jin, Z., Kleiman-Weiner, M., Schölkopf, B., Sachan, M., & Mihalcea, R. (2024) · Advances in Neural Information Processing Systems 37 · doi:10.52202/079017-3548 · Cited by 14
“For these complex tasks, recent work has started deploying generative agents [59, 60] for task-specific simulations, such as collaborative agent systems for software engineering [32, 46, 53, 72] and other domains [33, 36, 49, 69].”
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
“…each node: where ρ ( x ) represents the agentization operation on an element x , achieved by equipping a foundation model with professional roles (Li et al., 2023a), ex-ternal tools (Schick et al., 2023), and context-aware memory (Park et al., 2023); a i and a ij denote an assistant agent…”
InfluentialExternalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineering
Zhou, C., Chai, H., Chen, W., Guo, Z., Shan, R., Song, Y., Xu, T., Yang, Y., Yu, A., Zhang, W., et al. (2026) · arXiv · doi:10.48550/arxiv.2604.08224 · Cited by 1
Miao, Y., Wen, J., Luo, Y., & Li, J. (2026) · International Journal of Medical Informatics · doi:10.1016/j.ijmedinf.2025.106136 · Cited by 10
Optimization methods in fully cooperative scenarios: a review of multiagent reinforcement learning
Yang, T., Shi, X., Zeng, Q., Yang, Y., Xu, C., & Liu, H. (2025) · Frontiers of Information Technology & Electronic Engineering · doi:10.1631/fitee.2400259 · Cited by 8
“For instance, incorporating principles from the social choice theory could ensure that agent decisions reflect fairness (Li GH et al., 2023), while the cooperative game theory could be leveraged to harmonize the pursuit of individual optimization with maximization of collective rewards.”
Beyond Manual Media Coding: Evaluating Large Language Models and Agents for News Content Analysis
Doropoulos, S., Karapalidou, E., Charitidis, P., Karakeva, S., & Vologiannidis, S. D. (2025) · Applied Sciences · doi:10.3390/app15148059 · Cited by 15
Zhao, Z., Yue, X., Xie, J., Fang, C., Shao, Z., & Guo, S. (2025) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2025.3533476 · Cited by 17
Cognitive Echo: Enhancing think‐aloud protocols with LLM ‐based simulated students
Zheng, L., He, A., Qi, C., Zhang, H., & Gu, X. (2025) · British Journal of Educational Technology · doi:10.1111/bjet.13590 · Cited by 17
Han, Z., Wang, J., Yan, X., Jiang, Z., Zhang, Y., Liu, S., Gong, Q., & Song, C. (2025) · Applied Sciences · doi:10.3390/app15105663 · Cited by 8
“To alleviate these challenges, it is often necessary for team members to cooperate and negotiate with one another, whereas a single agent as an individual lacks the ability to synergize their resources in executing the task [19].”
Mushtaq, A., Naeem, R., Taj, I., Ghaznavi, I., & Qadir, J. (2025) · IEEE Global Engineering Education Conference (EDUCON) · doi:10.1109/educon62633.2025.11016405 · Cited by 17
“We implemented this approach using the Camel AI [29] framework, though due to its design limitations fully supporting only OpenAI’s models, we utilized GPT-4o as the backend for all agents, as illustrated in Fig.”
An LLM-based multi-agent system for remote sensing analysis
Sun, Z., Zhou, Y.-Y., & Yang, J. (2026) · Big Earth Data · doi:10.1080/20964471.2025.2600178 · Cited by 7
“These tasks can be simplified by using existing frameworks for multi-agent system development, such as CAMEL (Li et al., 2023), AutoGen (Wu et al., 2023), and AgentLite (Liu et al., 2024a).”
Liu, Y., Sun, H., Liu, W., Luan, J., Du, B., & Yan, R. (2025) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3690624.3709171 · Cited by 30
“CAMEL [18] and AutoGen [50] focuses on complex solutions through communication among agents.”
Collaborative garment design through group chatting with generative industrial large models
Harish, A. R., Yuan, Z., Li, M., Yang, H., & Huang, G. Q. (2025) · Advanced Engineering Informatics · doi:10.1016/j.aei.2025.103366 · Cited by 10
ChatCam: Embracing LLMs for Contextual Chatting-to-Camera with Interest-Oriented Video Summarization
Xiao, K., Gao, Y. C., Li, F., Xu, W., Chen, P., & Dong, W. (2024) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3699731 · Cited by 9
Prompt Sapper: LLM-Empowered Software Engineering Infrastructure for AI-Native ServicesPreprint
Xing, Z., Huang, Q., Cheng, Y., Zhu, L., Lu, Q., & Xu, X. (2023) · doi:10.36227/techrxiv.23298488.v1 · Cited by 6
Zhang, X., Wang, Y., He, A., Wang, H., & Li, T. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.129423 · Cited by 10
Liu, J., Hao, W., Cheng, K., & Jin, D. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.110319 · Cited by 5
SwarmSys: Decentralized Swarm-Inspired Agents for Scalable and Adaptive Reasoning
Li, R., Liu, H., Zhao, L., Li, Z., Li, J., Jiang, J., Xu, L., Zhao, C., Fan, M., & Liang, C. (2025) · arXiv · doi:10.48550/arxiv.2510.10047 · Cited by 5
Piao, J., Lu, Z., Gao, C., & Li, Y. (2025) · International World Wide Web Conference (WWW) · doi:10.1145/3696410.3714537 · Cited by 13
Sak, M. E., Sonlu, S., & Güdükbay, U. (2025) · Computer Animation and Virtual Worlds · doi:10.1002/cav.70033 · Cited by 5
“While other studies, too, utilize LLM-based dialogue in conversational agent systems [42, 43], we differ in our application and analysis.”
EXAR: A Unified Experience-Grounded Agentic Reasoning Architecture
Bergmann, R., Brand, F., Lenz, M., & Malburg, L. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-96559-3_1 · Cited by 8
Meta-X design: from tools to partners in human–machine co–creation for industry 5.0
Yu, C., Yan, T., & Chen, Y. (2025) · Journal of Engineering Design · doi:10.1080/09544828.2025.2571005 · Cited by 4
“Recent methods–including GraphRAG (Edge et al. 2025) for knowledge–grounded inference and CAMEL Agents (Li et al. 2023) for collaborative multi–step decomposition–demonstrate how symbolic rigor and neural flexibility can be synergistically fused.”
Metadata
- Authors
- Li, G., Hammoud, H., Itani, H., Khizbullin, D., & Ghanem, B.
- Venue
- Advances in Neural Information Processing Systems 36
- Published
- 2023
- Pages
- 51991-52008
- ISSN
- 1049-5258 (ISSN-L)
- OpenAlex
- W7133220405
- Cited by
- 314
- References
- 0
- Citations by year
- 2026: 197 · 2025: 77 · 2024: 32 · 2023: 8
- FWCI
- 78.60
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- cc-by
- Locations
- neural information processing systems (publishedVersion)
- arXiv (Cornell University) (submittedVersion, cc-by)
- arXiv (Cornell University) (cc-by)
- Funders
- King Abdullah University of Science and Technology
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Ethics and Social Impacts of AI
- Social Sciences › Arts and Humanities › History and Philosophy of Science › Cybernetics and Technology in Society
- Physical Sciences › Computer Science › Artificial Intelligence › Multi-Agent Systems and Negotiation
- Keywords
- large language models, multi-agent systems, agent communication, emergent behavior, collective intelligence
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
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.