Beyond self-talk: a communication-centric survey of LLM-based multi-agent systems

Abstract

Large language model-based multi-agent systems have recently gained significant attention due to their potential for complex, collaborative, and intelligent problem-solving capabilities. Existing surveys typically categorize LLM-based multi-agent systems (LLM-MAS) according to their application domains or architectures, overlooking the central role of communication in coordinating agent behaviors and interactions. To address this gap, this paper presents a comprehensive survey of LLM-MAS from a communication-centric perspective. Specifically, we propose a structured framework that integrates system-level communication (architecture, goals, and protocols) with system internal communication (strategies, paradigms, objects, and content), enabling a detailed exploration of how agents interact, negotiate, and achieve collective intelligence. Through an extensive analysis of recent literature, we identify key components in multiple dimensions and summarize their strengths and limitations. In addition, we highlight current challenges, including communication efficiency, security vulnerabilities, inadequate benchmarking, and scalability issues, and outline promising future research directions. This review aims to help researchers and practitioners gain a clear understanding of the communication mechanisms in LLM-MAS, thereby facilitating the design and deployment of robust, scalable, and secure multi-agent systems.

Graphical abstract

Keywords

large language model / LLM-based multi-agent systems / communication-centric framework / agent communication protocols

References

[1] Wang L, Ma C, Feng X, Zhang Z, Yang H, Zhang J, Chen Z, Tang J, Chen X, Lin Y, Zhao W X, Wei Z, Wen J . A survey on large language model based autonomous agents. Frontiers of Computer Science, 2024, 18( 6): 186345

[2] Talebirad Y, Nadiri A. Multi-agent collaboration: harnessing the power of intelligent LLM agents. 2023, arXiv preprint arXiv: 2306.03314

[3] Cai J, Li J, Zhang M, Li M, Wang C S, Tei K. Language evolution for evading social media regulation via LLM-based multi-agent simulation. In: Proceedings of 2024 IEEE Congress on Evolutionary Computation (CEC). 2024, 1−10

[4] Hong S, Zhuge M, Chen J, Zheng X, Cheng Y, Wang J, Zhang C, Wang Z, Yau S K S, Lin Z, Zhou L, Ran C, Xiao L, Wu C, Schmidhuber J. MetaGPT: meta programming for a multi-agent collaborative framework. In: Proceedings of the 12th International Conference on Learning Representations. 2024

[5] Nie G, Zhi R, Yan X, Du Y, Zhang X, Chen J, Zhou M, Chen H, Li T, Cheng Z, Xu S, Hu J. A hybrid multi-agent conversational recommender system with LLM and search engine in E-commerce. In: Proceedings of the 18th ACM Conference on Recommender Systems. 2024, 745−747

[6] Li X, Wang S, Zeng S, Wu Y, Yang Y . A survey on LLM-based multi-agent systems: workflow, infrastructure, and challenges. Vicinagearth, 2024, 1( 1): 9

[7] Guo T, Chen X, Wang Y, Chang R, Pei S, Chawla N V, Wiest O, Zhang X. Large language model based multi-agents: a survey of progress and challenges. In: Proceedings of the 33rd International Joint Conference on Artificial Intelligence. 2024, 8048−8057

[8] Han S, Zhang Q, Yao Y, Jin W, Xu Z, He C. LLM multi-agent systems: challenges and open problems. 2024, arXiv preprint arXiv: 2402.03578

[9] Gao C, Lan X, Li N, Yuan Y, Ding J, Zhou Z, Xu F, Li Y . Large language models empowered agent-based modeling and simulation: a survey and perspectives. Humanities and Social Sciences Communications, 2024, 11( 1): 1259

[10] Jin H, Huang L, Cai H, Yan J, Li B, Chen H. From LLMs to LLM-based agents for software engineering: a survey of current, challenges and future. 2025, arXiv preprint arXiv: 2408.02479

[11] Liu J, Wang K, Chen Y, Peng X, Chen Z, Zhang L, Lou Y. Large language model-based agents for software engineering: a survey. 2025, arXiv preprint arXiv: 2409.02977

[12] Shannon C E . A mathematical theory of communication. The Bell System Technical Journal, 1948, 27( 3): 379–423

[13] Smith R G . The contract net protocol: high-level communication and control in a distributed problem solver. IEEE Transactions on Computers, 1980, C-29( 12): 1104–1113

[14] Cheng Y, Zhang C, Zhang Z, Meng X, Hong S, Li W, Wang Z, Wang Z, Yin F, Zhao J, He X. Exploring large language model based intelligent agents: definitions, methods, and prospects. 2024, arXiv preprint arXiv: 2401.03428

[15] Zhang Q, Chen S, Bei Y, Yuan Z, Zhou H, Hong Z, Dong J, Chen H, Chang Y, Huang X. A survey of graph retrieval-augmented generation for customized large language models. 2025, arXiv preprint arXiv: 2501.13958

[16] Chen S, Zhang Q, Dong J, Hua W, Li Q, Huang X. Entity alignment with noisy annotations from large language models. In: Proceedings of the 38th International Conference on Neural Information Processing Systems, 2024, 482

[17] Qin Y, Liang S, Ye Y, Zhu K, Yan L, Lu Y, Lin Y, Cong X, Tang X, Qian B, Zhao A, Hong L, Tian R, Xie R, Zhou J, Gerstein M, Li D, Liu Z, Sun M. ToolLLM: facilitating large language models to master 16000+ real-world APIs. In: Proceedings of the 12th International Conference on Learning Representations. 2024

[18] Mu Y, Zhang Q, Hu M, Wang W, Ding M, Jin J, Wang B, Dai J, Qiao Y, Luo P. EmbodiedGPT: vision-language pre-training via embodied chain of thought. In: Proceedings of the 37th International Conference on Neural Information Processing Systems. 2023, 1090

[19] Zhang L, Zhang X, Yan B, Zhou Z, Zhang B, Guan Z, Zhang X, Li C. LLMs are introvert. 2025, arXiv preprint arXiv: 2507.05638

[20] Wooldridge M. An Introduction to MultiAgent Systems. 2nd ed. Hoboken: John Wiley & Sons, 2009

[21] Oliehoek F A, Amato C. A Concise Introduction to Decentralized POMDPs. Cham: Springer, 2016

[22] Hu J, Bhowmick P, Jang I, Arvin F, Lanzon A . A decentralized cluster formation containment framework for multirobot systems. IEEE Transactions on Robotics, 2021, 37( 6): 1936–1955

[23] Ulmer D, Mansimov E, Lin K, Sun J, Gao X, Zhang Y. Bootstrapping LLM-based task-oriented dialogue agents via self-talk. In: Proceedings of Findings of the Association for Computational Linguistics: ACL 2024. 2024, 9500−9522

[24] Abdullin Y, Molla-Aliod D, Ofoghi B, Yearwood J, Li Q. Synthetic dialogue dataset generation using LLM agents. 2024, arXiv preprint arXiv: 2401.17461

[25] Du Y, Li S, Torralba A, Tenenbaum J B, Mordatch I. Improving factuality and reasoning in language models through multiagent debate. In: Proceedings of the 41st International Conference on Machine Learning. 2024, 467

[26] Hsu C J, Buffelli D, McGowan J, Liao F T, Chen Y C, Vakili S, Shiu D S. Group think: Multiple concurrent reasoning agents collaborating at token level granularity. 2025, arXiv preprint arXiv: 2505.11107

[27] Huang J T, Li E J, Lam M H, Liang T, Wang W, Yuan Y, Jiao W, Wang X, Tu Z, Lyu M R. How far are we on the decision-making of LLMs? Evaluating LLMs’ gaming ability in multi-agent environments. 2025, arXiv preprint arXiv: 2403.11807

[28] Chuang Y S, Goyal A, Harlalka N, Suresh S, Hawkins R, Yang S, Shah D, Hu J, Rogers T T. Simulating opinion dynamics with networks of LLM-based agents. In: Proceedings of Findings of the Association for Computational Linguistics: NAACL 2024. 2024, 3326−3346

[29] Mahadevan V, Zhang S, Chandra R. GameChat: multi-LLM dialogue for safe, agile, and socially optimal multi-agent navigation in constrained environments. In: Proceedings of 2025 IEEE International Symposium on Multi-Robot and Multi-Agent Systems (MRS). 2025, 1−7

[30] Qian C, Liu W, Liu H, Chen N, Dang Y, Li J, Yang C, Chen W, Su Y, Cong X, Xu J, Li D, Liu Z, Sun M. ChatDev: communicative agents for software development. In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024, 15174−15186

[31] Zeng Y, Wu Y, Zhang X, Wang H, Wu Q. AutoDefense: multi-agent LLM defense against jailbreak attacks. 2024, arXiv preprint arXiv: 2403.04783

[32] Tang Z, Wang R, Chen W, Wang K, Liu Y, Chen T, Lin L. Towards CausalGPT: a multi-agent approach for faithful knowledge reasoning via promoting causal consistency in LLMs. 2024, arXiv preprint arXiv: 2308.11914

[33] Ishibashi Y, Nishimura Y. Self-organized agents: a LLM multi-agent framework toward ultra large-scale code generation and optimization. 2024, arXiv preprint arXiv: 2404.02183

[34] Yu Y, Yao Z, Li H, Deng Z, Jiang Y, Cao Y, Chen Z, Suchow J W, Cui Z, Liu R, Xu Z, Zhang D, Subbalakshmi K, Xiong G, He Y, Huang J, Li D, Xie Q. FINCON: a synthesized LLM multi-agent system with conceptual verbal reinforcement for enhanced financial decision making. In: Proceedings of the 38th International Conference on Neural Information Processing Systems. 2024, 4354

[35] Wang S, Long Z, Fan Z, Huang X, Wei Z. Benchmark self-evolving: a multi-agent framework for dynamic LLM evaluation. In: Proceedings of the 31st International Conference on Computational Linguistics. 2025, 3310−3328

[36] Zhang Y, Sun R, Chen Y, Pfister T, Zhang R, Arik S. Chain of agents: large language models collaborating on long-context tasks. In: Proceedings of the 38th International Conference on Neural Information Processing Systems. 2024, 132208−132237

[37] Ma T, Qian Y, Zhang Z, Wang Z, Qian X, Bai F, Ding Y, Luo X, Zhang S, Murugesan K, Zhang C, Ye Y. AutoData: a multi-agent system for open web data collection. In: Proceedings of the 39th International Conference on Computational Linguistics. 2025

[38] Yang T, Feng P, Guo Q, Zhang J, Zhang X, Ning J, Wang X, Mao Z . AutoHMA-LLM: efficient task coordination and execution in heterogeneous multi-agent systems using hybrid large language models. IEEE Transactions on Cognitive Communications and Networking, 2025, 11( 2): 987–998

[39] Wang S, Zhang G, Yu M, Wan G, Meng F, Guo C, Wang K, Wang Y. G-safeguard: a topology-guided security lens and treatment on LLM-based multi-agent systems. In: Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025, 7261−7276

[40] Li H, Xu T, Chang E, Wen Q. Knowledge tagging with large language model based multi-agent system. In: Proceedings of the 39th AAAI Conference on Artificial Intelligence. 2025, 28775−28782

[41] Kalyuzhnaya A, Mityagin S, Lutsenko E, Getmanov A, Aksenkin Y, Fatkhiev K, Fedorin K, Nikitin N O, Chichkova N, Vorona V, Boukhanovsky A . LLM agents for smart city management: enhancing decision support through multi-agent AI systems. Smart Cities, 2025, 8( 1): 19

[42] Zhang K, Zhang C, Wang C, Zhang C, Wu Y, Xing Z, Liu Y, Li Q, Peng X. LogiAgent: automated logical testing for REST systems with LLM-based multi-agents. 2025, arXiv preprint arXiv: 2503.15079

[43] Lei B, Zhang Y, Zuo S, Payani A, Ding C. MACM: utilizing a multi-agent system for condition mining in solving complex mathematical problems. In: Proceedings of the 38th International Conference on Neural Information Processing Systems. 2024, 1692

[44] Islam M A, Ali M E, Parvez M R. CodeSim: multi-agent code generation and problem solving through simulation-driven planning and debugging. In: Proceedings of Findings of the Association for Computational Linguistics: NAACL 2025. 2025, 5128−5154

[45] Shen M, Shu R, Pratik A, Gung J, Ge Y, Sunkara M, Zhang Y. Optimizing LLM-based multi-agent system with textual feedback: a case study on software development. 2025, arXiv preprint arXiv: 2505.16086

[46] Hu Y, Cai Y, Du Y, Zhu X, Liu X, Yu Z, Hou Y, Tang S, Chen S. Self-evolving multi-agent collaboration networks for software development. In: Proceedings of the 13th International Conference on Learning Representations. 2025

[47] Wang Z, Moriyama S, Wang W Y, Gangopadhyay B, Takamatsu S. Talk structurally, act hierarchically: a collaborative framework for LLM multi-agent systems. 2025, arXiv preprint arXiv: 2502.11098

[48] Ju T, Wang Y, Ma X, Cheng P, Zhao H, Wang Y, Liu L, Xie J, Zhang Z, Liu G. Flooding spread of manipulated knowledge in LLM-based multi-agent communities. 2024, arXiv preprint arXiv: 2407.07791

[49] Wu D, Shi H, Sun Z, Liu B. Deciphering digital detectives: understanding LLM behaviors and capabilities in multi-agent mystery games. In: Proceedings of Findings of the Association for Computational Linguistics: ACL 2024. 2024, 8225−8291

[50] Tao W, Zhou Y, Wang Y, Zhang W, Zhang H, Cheng Y. MAGIS: LLM-based multi-agent framework for GitHub issue resolution. In: Proceedings of the 38th International Conference on Neural Information Processing Systems. 2024, 51963−51993

[51] Pan B, Lu J, Wang K, Zheng L, Wen Z, Feng Y, Zhu M, Chen W . AgentCoord: visually exploring coordination strategy for LLM-based multi-agent collaboration. Computers & Graphics, 2025, 132: 104338

[52] Chen G, Dong S, Shu Y, Zhang G, Sesay J, Karlsson B, Fu J, Shi Y. AutoAgents: a framework for automatic agent generation. In: Proceedings of the 33rd International Joint Conference on Artificial Intelligence. 2024, 22−30

[53] Qian C, Dang Y, Li J, Liu W, Xie Z, Wang Y, Chen W, Yang C, Cong X, Che X, Liu Z, Sun M. Experiential co-learning of software-developing agents. In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024, 5628−5640

[54] Zhang Z, Zhang-Li D, Yu J, Gong L, Zhou J, Hao Z, Jiang J, Cao J, Liu H, Liu Z, Hou L, Li J. Simulating classroom education with LLM-empowered agents. In: Proceedings of 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025, 10364−10379

[55] Fan Y, Xue K, Li Z, Zhang X, Ruan T. An LLM-based framework for biomedical terminology normalization in social media via multi-agent collaboration. In: Proceedings of the 31st International Conference on Computational Linguistics. 2025, 10712−10726

[56] Ma W, Zhang H, Yang I, Ji S, Chen J, Hashemi F, Mohole S, Gearey E, Macy M, Hassanpour S, Vosoughi S. Communication makes perfect: persuasion dataset construction via multi-LLM communication. In: Proceedings of 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025, 4017−4045

[57] Zhang Q W, Li F, Wang J, Qiao L, Yu Y, Yin D, Sun X. FactGuard: leveraging multi-agent systems to generate answerable and unanswerable questions for enhanced long-context LLM extraction. 2025, arXiv preprint arXiv: 2504.05607

[58] Luo Y, Feng Y, Xu J, Tasca P, Liu Y. LLM-powered multi-agent system for automated crypto portfolio management. 2026, arXiv preprint arXiv: 2501.00826

[59] Chen K, Li X, Yang T, Wang H, Dong W, Gao Y. MDTeamGPT: a self-evolving LLM-based multi-agent framework for multi-disciplinary team medical consultation. 2025, arXiv preprint arXiv: 2503.13856

[60] Tang X, Zou A, Zhang Z, Li Z, Zhao Y, Zhang X, Cohan A, Gerstein M. MedAgents: large language models as collaborators for zero-shot medical reasoning. In: Proceedings of Findings of the Association for Computational Linguistics: ACL 2024. 2024, 599−621

[61] Qiao T, Walker C, Cunningham C, Koh Y S. Thematic-LM: a LLM-based multi-agent system for large-scale thematic analysis. In: Proceedings of the ACM on Web Conference 2025. 2025, 649−658

[62] Moghimifar F, Li Y F, Thomson R, Haffari G. Modelling political coalition negotiations using LLM-based agents. 2024, arXiv preprint arXiv: 2402.11712

[63] Wang S, Liu C, Zheng Z, Qi S, Chen S, Yang Q, Zhao A, Wang C, Song S, Huang G. Boosting LLM agents with recursive contemplation for effective deception handling. In: Proceedings of Findings of the Association for Computational Linguistics: ACL 2024. 2024, 9909−9953

[64] Park J S, O’Brien J, Cai C J, Morris M R, Liang P, Bernstein M S. Generative agents: interactive simulacra of human behavior. In: Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology. 2023, 2

[65] Piatti G, Jin Z, Kleiman-Weiner M, Schölkopf B, Sachan M, Mihalcea R. Cooperate or collapse: emergence of sustainable cooperation in a society of LLM agents. In: Proceedings of the 38th International Conference on Neural Information Processing Systems. 2024, 3548

[66] Yue S, Huang T, Jia Z, Wang S, Liu S, Song Y, Huang X, Wei Z. Multi-agent simulator drives language models for legal intensive interaction. In: Proceedings of Findings of the Association for Computational Linguistics: NAACL 2025. 2025, 6552−6585

[67] Sreedhar K, Cai A, Ma J, Nickerson J V, Chilton L B. Simulating cooperative prosocial behavior with multi-agent LLMs: evidence and mechanisms for AI agents to inform policy decisions. In: Proceedings of the 30th International Conference on Intelligent User Interfaces. 2025, 1272−1286

[68] Dai G, Zhang W, Li J, Yang S, Onochie Lbe C, Rao S, Caetano A, Sra M, others. Artificial leviathan: exploring social evolution of LLM agents through the lens of Hobbesian social contract theory. 2024, arXiv preprint arXiv: 2406.14373

[69] Li N, Gao C, Li M, Li Y, Liao Q. EconAgent: large language model-empowered agents for simulating macroeconomic activities. In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024, 15523−15536

[70] Guan Z, Kong X, Zhong F, Wang Y. Richelieu: self-evolving LLM-based agents for AI diplomacy. In: Proceedings of the 38th International Conference on Neural Information Processing Systems. 2024, 3925

[71] Mou X, Qian C, Liu W, Yan L, Hu Y, Huang X, Wei Z. EcoLANG: efficient and effective agent communication language induction for social simulation. In: Proceedings of Findings of the Association for Computational Linguistics: EMNLP 2025. 2025, 5287−5304

[72] Lee C, Xia C S, Yang L, Huang J T, Zhu Z, Zhang L, Lyu M R. A unified debugging approach via LLM-based multi-agent synergy. 2024, arXiv preprint arXiv: 2404.17153

[73] Liu J, Yao Y, An P, Wang Q. PeerGPT: probing the roles of LLM-based peer agents as team moderators and participants in children’s collaborative learning. In: Proceedings of Extended Abstracts of the CHI Conference on Human Factors in Computing Systems. 2024, 263

[74] Wei Y, Wang Z, Lu Y, Xu C, Liu C, Zhao H, Chen S, Wang Y. Editable scene simulation for autonomous driving via collaborative LLM-agents. In: Proceedings of 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2024, 15077−15087

[75] Ocker F, Tanneberg D, Eggert J, Gienger M. Tulip agent -- enabling LLM-based agents to solve tasks using large tool libraries. 2024, arXiv preprint arXiv: 2407.21778

[76] Kim K, Lee S, Huang K H, Chan H P, Li M, Ji H. Can LLMs produce faithful explanations for fact-checking? Towards faithful explainable fact-checking via multi-agent debate. 2024, arXiv preprint arXiv: 2402.07401

[77] Zhang L, Zhai Y, Jia T, Huang X, Duan C, Li Y. AgentFM: role-aware failure management for distributed databases with LLM-driven multi-agents. In: Proceedings of the 33rd ACM International Conference on the Foundations of Software Engineering. 2025, 525−529

[78] Ronanki K. Facilitating trustworthy human-agent collaboration in LLM-based multi-agent system oriented software engineering. In: Proceedings of the 33rd ACM International Conference on the Foundations of Software Engineering. 2025, 1333−1337

[79] Zhang Y, Hao J, Wang Z, Sheng H, Zeng W. Facilitating video story interaction with multi-agent collaborative system. 2025, arXiv preprint arXiv: 2505.03807

[80] Pei C, Wang Z, Liu F, Li Z, Liu Y, He X, Kang R, Zhang T, Chen J, Li J, Xie G, Pei D. Flow-of-action: SOP enhanced LLM-based multi-agent system for root cause analysis. In: Proceedings of the ACM on Web Conference 2025. 2025, 422−431

[81] Wang T, Zhan Y, Lian J, Hu Z, Yuan N J, Zhang Q, Xie X, Xiong H. LLM-powered multi-agent framework for goal-oriented learning in intelligent tutoring system. In: Proceedings of the ACM on Web Conference 2025. 2025, 510−519

[82] Zhang Y, Yang X, Feng S, Wang D, Zhang Y, Song K. Can LLMS beat humans in debating? A dynamic multi-agent framework for competitive debate. In: Proceedings of 2026 IEEE International Conference on Acoustics, Speech and Signal Processing. 2026, 19377−19381

[83] Zhang R, Eger S. LLM-based multi-agent poetry generation in non-cooperative environments. 2024, arXiv preprint arXiv: 2409.03659

[84] Wu Z, Peng R, Zheng S, Liu Q, Han X, Kwon B I, Onizuka M, Tang S, Xiao C. Shall we team up: exploring spontaneous cooperation of competing LLM agents. In: Proceedings of Findings of the Association for Computational Linguistics: EMNLP 2024. 2024, 5163−5186

[85] Chen B, Li G, Lin X, Wang Z, Li J. BlockAgents: towards byzantine-robust LLM-based multi-agent coordination via blockchain. In: Proceedings of the ACM Turing Award Celebration Conference - China 2024. 2024, 187−192

[86] Xu Q, Tian Z, Wu H, Huang Z, Song Y, Liu F, Li D. Learn to disguise: avoid refusal responses in LLM’s defense via a multi-agent attacker-disguiser game. 2024, arXiv preprint arXiv: 2404.02532

[87] Yim Y, Chan C, Shi T, Deng Z, Fan W, Zheng T, Song Y. Evaluating and enhancing LLMs agent based on theory of mind in Guandan: a multi-player cooperative game under imperfect information. In: Proceedings of 2024 IEEE/WIC International Conference on Web Intelligence and Intelligent Agent Technology. 2024, 461−465

[88] Liu Y, Liu Y, Zhang X, Chen X, Yan R. The truth becomes clearer through debate! Multi-agent systems with large language models unmask fake news. In: Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval. 2025, 504−514

[89] Dorri A, Kanhere S S, Jurdak R . Multi-agent systems: a survey. IEEE Access, 2018, 6: 28573–28593

[90] Model Context Protocol. What is the model context protocol (MCP). Website at modelcontextprotocol.io/introduction, 2024

[91] Google. Agent2Agent (A2A) protocol. Website at Google.github.io/A2A/, 2024

[92] Agent Network Protocol. Agent network protocol official website. Website at agent-network-protocol, 2024

[93] Ehtesham A, Singh A, Gupta G K, Kumar S. A survey of agent interoperability protocols: model context protocol (MCP), agent communication protocol (ACP), agent-to-agent protocol (A2A), and agent network protocol (ANP). 2025, arXiv preprint arXiv: 2505.02279

[94] BeeAI Contributors. Agent Communication Protocol (ACP). See github.com/i-am-bee/acp website, 2025

[95] NEAR. AITP: agent interaction & transaction protocol. See Aitp.dev/ website, 2025

[96] AGNTCY Collective. Agent Connect Protocol Specification. See spec.acp.agntcy.ory/ website, 2025

[97] Yao S, Zhao J, Yu D, Du N, Shafran I, Narasimhan K R, Cao Y. ReAct: synergizing reasoning and acting in language models. In: Proceedings of the 11th International Conference on Learning Representations. 2023

[98] He P, Lin Y, Dong S, Xu H, Xing Y, Liu H. Red-teaming LLM multi-agent systems via communication attacks. In: Proceedings of Findings of the Association for Computational Linguistics: ACL 2025. 2025, 6726−6747

[99] Yan B, Zhang X, Zhou Z, Li C, Zeng R, Qi Y, Wang T, Zhang L. Attack the messages, not the agents: a multi-round adaptive stealthy tampering framework for LLM-MAS. In: Proceedings of the 40th AAAI Conference on Artificial Intelligence. 2026, 29784−29792

[100] Zhou Z, Li Z, Zhang J, Zhang Y, Wang K, Liu Y, Guo Q. CORBA: contagious recursive blocking attacks on multi-agent systems based on large language models. 2025, arXiv preprint arXiv: 2502.14529

[101] Zou A, Phan L, Wang J, Duenas D, Lin M, Andriushchenko M, Wang R, Kolter Z, Fredrikson M, Hendrycks D. Improving alignment and robustness with circuit breakers. In: Proceedings of the 38th International Conference on Neural Information Processing Systems. 2024, 2651

[102] Jain N, Schwarzschild A, Wen Y, Somepalli G, Kirchenbauer J, Chiang P Y, Goldblum M, Saha A, Geiping J, Goldstein T. Baseline defenses for adversarial attacks against aligned language models. 2023, arXiv preprint arXiv: 2309.00614

[103] Zhou J, Wang L, Yang X. GUARDIAN: safeguarding LLM multi-agent collaborations with temporal graph modeling. 2025, arXiv preprint arXiv: 2505.19234

[104] Zhu K, Du H, Hong Z, Yang X, Guo S, Wang Z, Wang Z, Qian C, Tang X, Ji H, You J. MultiAgentBench: evaluating the collaboration and competition of LLM agents. In: Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025, 8580−8622

[105] Geng L, Chang E Y. REALM-bench: a real-world planning benchmark for LLMs and multi-agent systems. 2025, arXiv preprint arXiv: 2502.18836

[106] Wang W, Zhang D, Feng T, Wang B, Tang J. BattleAgentBench: a benchmark for evaluating cooperation and competition capabilities of language models in multi-agent systems. 2024, arXiv preprint arXiv: 2408.15971

[107] Li T, Chu C, Zheng Y, Zhang B, Gong N Z, Xiao C. A2ASecBench: a protocol-aware security benchmark for agent-to-agent multi-agent systems. In: Proceedings of the 14th International Conference on Learning Representations. 2026

Rights & permissions

Higher Education Press