{"work":{"id":"fb905249-ea5f-4765-80f0-2428ea66f15f","openalex_id":null,"doi":null,"arxiv_id":"2402.01680","raw_key":null,"title":"Large Language Model based Multi-Agents: A Survey of Progress and Challenges","authors":null,"authors_text":"Taicheng Guo, Xiuying Chen, Yaqi Wang, Ruidi Chang, Shichao Pei, Nitesh V. Chawla","year":2024,"venue":"cs.CL","abstract":"Large Language Models (LLMs) have achieved remarkable success across a wide array of tasks. Due to the impressive planning and reasoning abilities of LLMs, they have been used as autonomous agents to do many tasks automatically. Recently, based on the development of using one LLM as a single planning or decision-making agent, LLM-based multi-agent systems have achieved considerable progress in complex problem-solving and world simulation. To provide the community with an overview of this dynamic field, we present this survey to offer an in-depth discussion on the essential aspects of multi-agent systems based on LLMs, as well as the challenges. Our goal is for readers to gain substantial insights on the following questions: What domains and environments do LLM-based multi-agents simulate? How are these agents profiled and how do they communicate? What mechanisms contribute to the growth of agents' capacities? For those interested in delving into this field of study, we also summarize the commonly used datasets or benchmarks for them to have convenient access. To keep researchers updated on the latest studies, we maintain an open-source GitHub repository, dedicated to outlining the research on LLM-based multi-agent systems.","external_url":"https://arxiv.org/abs/2402.01680","cited_by_count":null,"metadata_source":"pith","metadata_fetched_at":"2026-05-25T04:00:19.134509+00:00","pith_arxiv_id":"2402.01680","created_at":"2026-05-08T19:49:05.653506+00:00","updated_at":"2026-05-25T04:00:19.134509+00:00","title_quality_ok":true,"display_title":"Large Language Model based Multi-Agents: A Survey of Progress and Challenges","render_title":"Large Language Model based Multi-Agents: A Survey of Progress and Challenges"},"hub":{"state":{"work_id":"fb905249-ea5f-4765-80f0-2428ea66f15f","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":72,"external_cited_by_count":null,"distinct_field_count":14,"first_pith_cited_at":"2024-04-21T01:49:46+00:00","last_pith_cited_at":"2026-05-22T06:27:18+00:00","author_build_status":"not_needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"not_needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-06-01T06:33:09.919867+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":22},{"context_role":"dataset","n":1}],"polarity_counts":[{"context_polarity":"background","n":22},{"context_polarity":"use_dataset","n":1}],"runs":{"context_extract":{"job_type":"context_extract","status":"succeeded","result":{"enqueued_papers":25},"error":null,"updated_at":"2026-05-14T21:06:24.128340+00:00"},"graph_features":{"job_type":"graph_features","status":"succeeded","result":{"co_cited":[{"title":"ReAct: Synergizing Reasoning and Acting in Language Models","work_id":"407a2351-25f1-497d-b611-f77d0292a8e6","shared_citers":7},{"title":"AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation","work_id":"92b7eb9c-c3d8-4518-a376-06fa15dd895b","shared_citers":6},{"title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","work_id":"d0effe15-a689-441a-8e3f-ea35f1c4e4b1","shared_citers":6},{"title":"Training Verifiers to Solve Math Word Problems","work_id":"acab1aa8-b4d6-40e0-a3ee-25341701dca2","shared_citers":6},{"title":"ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate","work_id":"eac74d79-d8d1-49dd-8565-53d713a84fff","shared_citers":5},{"title":"Multi-Agent Collaboration Mechanisms: A Survey of LLMs","work_id":"34627f75-81fe-465e-bca5-d2a93270aa1d","shared_citers":5},{"title":"ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs","work_id":"3c555b48-a4d9-42dd-9fdd-0f6018fbe9cb","shared_citers":4},{"title":"Towards a Science of Scaling Agent Systems","work_id":"df1c366f-f1cf-469a-b862-5d59229b6b8f","shared_citers":4},{"title":"Why Do Multi-Agent LLM Systems Fail?","work_id":"b186294a-cda7-4df0-9a28-27d379af92b2","shared_citers":4},{"title":"AgentBench: Evaluating LLMs as Agents","work_id":"a37549b4-4c94-412d-acc4-4efeb08509be","shared_citers":3},{"title":"AI agents that matter","work_id":"07877e57-5393-47ee-ae5f-563ff8f9a6b2","shared_citers":3},{"title":"Automated design of agentic systems","work_id":"100d6cbf-e729-4ef1-828a-0bb6cb04b7d5","shared_citers":3},{"title":"ChatDev: Communicative Agents for Software Development","work_id":"5d8a3650-ab78-4991-b0d3-5309b59c690f","shared_citers":3},{"title":"findings-emnlp.479/","work_id":"e53e94fb-b997-445d-a68a-82922fe08e68","shared_citers":3},{"title":"Gsm-symbolic: Understanding the limitations of mathematical reasoning in large language models","work_id":"7d26909d-cb69-48f7-b93e-7d6fcc281415","shared_citers":3},{"title":"Improving Factuality and Reasoning in Language Models through Multiagent Debate","work_id":"a543e65c-1cf8-4182-b03b-33c0cd2c65d5","shared_citers":3},{"title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","work_id":"d0c30cd7-81e1-4159-a87f-f6adca77ff08","shared_citers":3},{"title":"Measuring Mathematical Problem Solving With the MATH Dataset","work_id":"50652ac6-fb7c-4675-a2c2-159c241feb17","shared_citers":3},{"title":"MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework","work_id":"891b9780-a800-4e3c-bba0-53597ab8dc98","shared_citers":3},{"title":"OpenHands: An Open Platform for AI Software Developers as Generalist Agents","work_id":"f1762ea0-e382-4f38-a28c-adc643789859","shared_citers":3},{"title":"Qwen3 Technical Report","work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e","shared_citers":3},{"title":"Scaling large language model-based multi-agent collabora- tion","work_id":"8c6b62a4-4ade-4a58-958c-9035f4524b6e","shared_citers":3},{"title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","work_id":"8c6d5a6b-b5cc-4105-9c84-9c34bb9375bb","shared_citers":3},{"title":"Xu He, Di Wu, Yan Zhai, and Kun Sun","work_id":"5c63297e-2866-40b6-878d-2bdbe3c0fdc7","shared_citers":3}],"time_series":[{"n":1,"year":2025},{"n":34,"year":2026}],"dependency_candidates":[]},"error":null,"updated_at":"2026-05-14T21:06:24.156961+00:00"},"identity_refresh":{"job_type":"identity_refresh","status":"succeeded","result":{"items":[{"title":"Qwen3 Technical Report","outcome":"unchanged","work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e","resolver":"local_arxiv","confidence":0.98,"old_work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e"}],"counts":{"fixed":0,"merged":0,"unchanged":1,"quarantined":0,"needs_external_resolution":0},"errors":[],"attempted":1},"error":null,"updated_at":"2026-05-14T21:06:22.839940+00:00"},"summary_claims":{"job_type":"summary_claims","status":"succeeded","result":{"title":"Large Language Model based Multi-Agents: A Survey of Progress and Challenges","claims":[{"claim_text":"Large Language Models (LLMs) have achieved remarkable success across a wide array of tasks. Due to the impressive planning and reasoning abilities of LLMs, they have been used as autonomous agents to do many tasks automatically. Recently, based on the development of using one LLM as a single planning or decision-making agent, LLM-based multi-agent systems have achieved considerable progress in complex problem-solving and world simulation. To provide the community with an overview of this dynamic field, we present this survey to offer an in-depth discussion on the essential aspects of multi-age","claim_type":"abstract","evidence_strength":"source_metadata"}],"why_cited":"Pith tracks Large Language Model based Multi-Agents: A Survey of Progress and Challenges because it crossed a citation-hub threshold.","role_counts":[]},"error":null,"updated_at":"2026-05-14T21:06:19.196771+00:00"}},"summary":{"title":"Large Language Model based Multi-Agents: A Survey of Progress and Challenges","claims":[{"claim_text":"Large Language Models (LLMs) have achieved remarkable success across a wide array of tasks. Due to the impressive planning and reasoning abilities of LLMs, they have been used as autonomous agents to do many tasks automatically. Recently, based on the development of using one LLM as a single planning or decision-making agent, LLM-based multi-agent systems have achieved considerable progress in complex problem-solving and world simulation. To provide the community with an overview of this dynamic field, we present this survey to offer an in-depth discussion on the essential aspects of multi-age","claim_type":"abstract","evidence_strength":"source_metadata"}],"why_cited":"Pith tracks Large Language Model based Multi-Agents: A Survey of Progress and Challenges because it crossed a citation-hub threshold.","role_counts":[]},"graph":{"co_cited":[{"title":"ReAct: Synergizing Reasoning and Acting in Language Models","work_id":"407a2351-25f1-497d-b611-f77d0292a8e6","shared_citers":7},{"title":"AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation","work_id":"92b7eb9c-c3d8-4518-a376-06fa15dd895b","shared_citers":6},{"title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","work_id":"d0effe15-a689-441a-8e3f-ea35f1c4e4b1","shared_citers":6},{"title":"Training Verifiers to Solve Math Word Problems","work_id":"acab1aa8-b4d6-40e0-a3ee-25341701dca2","shared_citers":6},{"title":"ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate","work_id":"eac74d79-d8d1-49dd-8565-53d713a84fff","shared_citers":5},{"title":"Multi-Agent Collaboration Mechanisms: A Survey of LLMs","work_id":"34627f75-81fe-465e-bca5-d2a93270aa1d","shared_citers":5},{"title":"ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs","work_id":"3c555b48-a4d9-42dd-9fdd-0f6018fbe9cb","shared_citers":4},{"title":"Towards a Science of Scaling Agent Systems","work_id":"df1c366f-f1cf-469a-b862-5d59229b6b8f","shared_citers":4},{"title":"Why Do Multi-Agent LLM Systems Fail?","work_id":"b186294a-cda7-4df0-9a28-27d379af92b2","shared_citers":4},{"title":"AgentBench: Evaluating LLMs as Agents","work_id":"a37549b4-4c94-412d-acc4-4efeb08509be","shared_citers":3},{"title":"AI agents that matter","work_id":"07877e57-5393-47ee-ae5f-563ff8f9a6b2","shared_citers":3},{"title":"Automated design of agentic systems","work_id":"100d6cbf-e729-4ef1-828a-0bb6cb04b7d5","shared_citers":3},{"title":"ChatDev: Communicative Agents for Software Development","work_id":"5d8a3650-ab78-4991-b0d3-5309b59c690f","shared_citers":3},{"title":"findings-emnlp.479/","work_id":"e53e94fb-b997-445d-a68a-82922fe08e68","shared_citers":3},{"title":"Gsm-symbolic: Understanding the limitations of mathematical reasoning in large language models","work_id":"7d26909d-cb69-48f7-b93e-7d6fcc281415","shared_citers":3},{"title":"Improving Factuality and Reasoning in Language Models through Multiagent Debate","work_id":"a543e65c-1cf8-4182-b03b-33c0cd2c65d5","shared_citers":3},{"title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","work_id":"d0c30cd7-81e1-4159-a87f-f6adca77ff08","shared_citers":3},{"title":"Measuring Mathematical Problem Solving With the MATH Dataset","work_id":"50652ac6-fb7c-4675-a2c2-159c241feb17","shared_citers":3},{"title":"MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework","work_id":"891b9780-a800-4e3c-bba0-53597ab8dc98","shared_citers":3},{"title":"OpenHands: An Open Platform for AI Software Developers as Generalist Agents","work_id":"f1762ea0-e382-4f38-a28c-adc643789859","shared_citers":3},{"title":"Qwen3 Technical Report","work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e","shared_citers":3},{"title":"Scaling large language model-based multi-agent collabora- tion","work_id":"8c6b62a4-4ade-4a58-958c-9035f4524b6e","shared_citers":3},{"title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","work_id":"8c6d5a6b-b5cc-4105-9c84-9c34bb9375bb","shared_citers":3},{"title":"Xu He, Di Wu, Yan Zhai, and Kun Sun","work_id":"5c63297e-2866-40b6-878d-2bdbe3c0fdc7","shared_citers":3}],"time_series":[{"n":1,"year":2025},{"n":34,"year":2026}],"dependency_candidates":[]},"authors":[]}}