{"type":"ScholarlyArticle","title":"AutoAgents: A Framework for Automatic Agent Generation","authors":[{"name":"Guangyao Chen","slug":"guangyao-chen","given":"Guangyao","family":"Chen","affiliation":"Peking University"},{"name":"Siwei Dong","slug":"siwei-dong","given":"Siwei","family":"Dong","affiliation":"Peking University"},{"name":"Yu Shu","slug":"yu-shu","given":"Yu","family":"Shu","affiliation":"Peking University"},{"name":"Ge Zhang","slug":"ge-zhang","given":"Ge","family":"Zhang","affiliation":"University of Waterloo"},{"name":"Jaward Sesay","slug":"jaward-sesay","given":"Jaward","family":"Sesay","affiliation":"Beijing Academy of Artificial Intelligence"},{"name":"Börje Karlsson","slug":"borje-karlsson","given":"Börje","family":"Karlsson","affiliation":"Beijing Academy of Artificial Intelligence"},{"name":"Jie Fu","slug":"jie-fu","given":"Jie","family":"Fu","affiliation":"Hong Kong University of Science and Technology"},{"name":"Yemin Shi","slug":"yemin-shi","given":"Yemin","family":"Shi","affiliation":"Peking University"}],"abstract":"Large language models (LLMs) have enabled remarkable advances in automated task-solving with multi-agent systems. However, most existing LLM-based multi-agent approaches rely on predefined agents to handle simple tasks, limiting the adaptability of multi-agent collaboration to different scenarios. Therefore, we introduce AutoAgents, an innovative framework that adaptively generates and coordinates multiple specialized agents to build an AI team according to different tasks. Specifically, AutoAgents couples the relationship between tasks and roles by dynamically generating multiple required agents based on task content and planning solutions for the current task based on the generated expert agents. Multiple specialized agents collaborate with each other to efficiently accomplish tasks. Concurrently, an observer role is incorporated into the framework to reflect on the designated plans and agents' responses and improve upon them. Our experiments on various benchmarks demonstrate that AutoAgents generates more coherent and accurate solutions than the existing multi-agent methods. This underscores the significance of assigning different roles to different tasks and of team cooperation, offering new perspectives for tackling complex tasks. The repository of this project is available at https://github.com/Link-AGI/AutoAgents.","doi":"10.24963/ijcai.2024/3","url":"https://ijcai.org/proceedings/2024/3","pdf":"https://ijcai.org/proceedings/2024/0003.pdf","markdown":"https://ijcai.org/proceedings/2024/3.md","bibtex":"https://ijcai.org/proceedings/2024/bibtex/3","volume":{"slug":"2024","title":"Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2024","url":"https://ijcai.org/proceedings/2024/","year":2024,"location":"Jeju, Korea","dates":"3-9 August 2024","editors":"Kate Larson","isbn":"978-1-956792-04-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2024"},"section":"Agent-based and Multi-agent Systems","track":"Main Track","number":3,"pages":{"first":22,"last":30},"keywords":["Agent-based and Multi-agent Systems: MAS: Applications","Natural Language Processing: NLP: Applications"],"videos":[],"references":[{"position":1,"raw":"[Achiam et al., 2023] Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Ale- man, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al. Gpt-4 technical report. arXiv preprint arXiv:2303.08774, 2023.","title":"Gpt-4 technical report","authors":"Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Barron, 2000] Brigid Barron. Achieving coordination in col- laborative problem-solving groups. The journal of the learning sciences, 9(4):403-436, 2000.","title":"Achieving coordination in collaborative problem-solving groups","authors":"Brigid Barron, Barron","year":"2000","venue":"The journal of the learning sciences","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Bubeck et al., 2023] Sébastien Bubeck, Varun Chan- drasekaran, Ronen Eldan, Johannes Gehrke, Eric Horvitz, Ece Kamar, Peter Lee, Yin Tat Lee, Yuanzhi Li, Scott Lund- berg, et al. Sparks of artificial general intelligence: Early experiments with gpt-4. arXiv preprint arXiv:2303.12712, 2023.","title":"Sparks of artificial general intelligence: Early experiments with gpt-4","authors":"Sébastien Bubeck, Varun Chandrasekaran, Ronen Eldan, Johannes Gehrke, Eric Horvitz, Ece Kamar, Peter Lee, Yin Tat Lee, Yuanzhi Li, Scott Lundberg","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Chan et al., 2023] Chi-Min Chan, Weize Chen, Yusheng Su, Jianxuan Yu, Wei Xue, Shanghang Zhang, Jie Fu, and Zhiyuan Liu. Chateval: Towards better llm-based evaluators through multi-agent debate. arXiv preprint arXiv:2308.07201, 2023.","title":"Chateval: Towards better llm-based evaluators through multi-agent debate","authors":"Chan","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Chen et al., 2023a] Weize Chen, Yusheng Su, Jingwei Zuo, Cheng Yang, Chenfei Yuan, Chen Qian, Chi-Min Chan, Yujia Qin, Yaxi Lu, Ruobing Xie, et al. Agentverse: Facili- tating multi-agent collaboration and exploring emergent be- haviors in agents. arXiv preprint arXiv:2308.10848, 2023.","title":"Agentverse: Facilitating multi-agent collaboration and exploring emergent behaviors in agents","authors":"Chen","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Chen et al., 2023b] Xinyun Chen, Maxwell Lin, Nathanael Schärli, and Denny Zhou. Teaching large language models to self-debug. arXiv preprint arXiv:2304.05128, 2023.","title":"Teaching large language models to self-debug","authors":"Chen","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Du et al., 2023] Yilun Du, Shuang Li, Antonio Torralba, Joshua B Tenenbaum, and Igor Mordatch. Improving factu- ality and reasoning in language models through multiagent debate. arXiv preprint arXiv:2305.14325, 2023.","title":"Improving factuality and reasoning in language models through multiagent debate","authors":"Yilun Du, Shuang Li, Antonio Torralba, Joshua B Tenenbaum, Igor Mordatch","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Fu et al., 2023] Yao Fu, Hao Peng, Tushar Khot, and Mirella Lapata. Improving language model negotiation with self- play and in-context learning from ai feedback. arXiv preprint arXiv:2305.10142, 2023.","title":"Improving language model negotiation with selfplay and in-context learning from ai feedback","authors":"Yao Fu, Hao Peng, Tushar Khot, Mirella Lapata","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Gou et al., 2023] Zhibin Gou, Zhihong Shao, Yeyun Gong, Yelong Shen, Yujiu Yang, Nan Duan, and Weizhu Chen. Critic: Large language models can self-correct with tool- interactive critiquing, 2023. [Gravitas, 2023] Significant Gravitas. Auto-gpt: An au- tonomous gpt-4 experiment, 2023. URL https://github. com/Significant-Gravitas/Auto-GPT, 2023.","title":"Critic: Large language models can self-correct with toolinteractive critiquing","authors":"Zhibin Gou, Zhihong Shao, Yeyun Gong, Yelong Shen, Yujiu Yang, Nan Duan, Weizhu Chen","year":"2023","venue":"Significant Gravitas. Auto-gpt: An autonomous gpt-4 experiment","doi":null,"url":"https://github.com/Significant-Gravitas/Auto-GPT","internal_url":null},{"position":10,"raw":"[Hao et al., 2023] Rui Hao, Linmei Hu, Weijian Qi, Qingliu Wu, Yirui Zhang, and Liqiang Nie. Chatllm network: More brains, more intelligence. arXiv preprint arXiv:2304.12998, 2023.","title":"Chatllm network: More brains, more intelligence","authors":"Rui Hao, Linmei Hu, Weijian Qi, Qingliu Wu, Yirui Zhang, Liqiang Nie","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Hong et al., 2023] Sirui Hong, Xiawu Zheng, Jonathan Chen, Yuheng Cheng, Ceyao Zhang, Zili Wang, Steven Ka Shing Yau, Zijuan Lin, Liyang Zhou, Chenyu Ran, et al. Metagpt: Meta programming for multi-agent collaborative framework. arXiv preprint arXiv:2308.00352, 2023.","title":"Metagpt: Meta programming for multi-agent collaborative framework","authors":"Sirui Hong, Xiawu Zheng, Jonathan Chen, Yuheng Cheng, Ceyao Zhang, Zili Wang, Steven Ka, Shing Yau, Zijuan Lin, Liyang Zhou, Chenyu Ran","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Huang et al., 2022] Wenlong Huang, Fei Xia, Ted Xiao, Har- ris Chan, Jacky Liang, Pete Florence, Andy Zeng, Jonathan Tompson, Igor Mordatch, Yevgen Chebotar, et al. Inner monologue: Embodied reasoning through planning with language models. arXiv preprint arXiv:2207.05608, 2022.","title":"Inner monologue: Embodied reasoning through planning with language models","authors":"Wenlong Huang, Fei Xia, Ted Xiao, Harris Chan, Jacky Liang, Pete Florence, Andy Zeng, Jonathan Tompson, Igor Mordatch, Yevgen Chebotar","year":"2022","venue":null,"doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Joshi et al., 2017] Mandar Joshi, Eunsol Choi, Daniel Weld, and Luke Zettlemoyer. TriviaQA: A large scale distantly supervised challenge dataset for reading comprehension. In Proceedings of the 55th Annual Meeting of the Asso- ciation for Computational Linguistics, pages 1601-1611. Association for Computational Linguistics, July 2017.","title":"TriviaQA: A large scale distantly supervised challenge dataset for reading comprehension","authors":"Mandar Joshi, Eunsol Choi, Daniel Weld, Luke Zettlemoyer","year":"2017","venue":"Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Li et al., 2023] Guohao Li, Hasan Abed Al Kader Ham- moud, Hani Itani, Dmitrii Khizbullin, and Bernard Ghanem. Camel: Communicative agents for\" mind\" exploration of large scale language model society. arXiv preprint arXiv:2303.17760, 2023.","title":"Camel: Communicative agents for\" mind\" exploration of large scale language model society","authors":"Li","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Liang et al., 2023] Tian Liang, Zhiwei He, Wenxiang Jiao, Xing Wang, Yan Wang, Rui Wang, Yujiu Yang, Zhaopeng Tu, and Shuming Shi. Encouraging divergent thinking in large language models through multi-agent debate. arXiv preprint arXiv:2305.19118, 2023.","title":"Encouraging divergent thinking in large language models through multi-agent debate","authors":"Tian Liang, Zhiwei He, Wenxiang Jiao, Xing Wang, Yan Wang, Rui Wang, Yujiu Yang, Zhaopeng Tu, Shuming Shi","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Madaan et al., 2023] Aman Madaan, Niket Tandon, Prakhar Gupta, Skyler Hallinan, Luyu Gao, Sarah Wiegreffe, Uri Alon, Nouha Dziri, Shrimai Prabhumoye, Yiming Yang, et al. Self-refine: Iterative refinement with self-feedback. arXiv preprint arXiv:2303.17651, 2023.","title":"Self-refine: Iterative refinement with self-feedback","authors":"Aman Madaan, Niket Tandon, Prakhar Gupta, Skyler Hallinan, Luyu Gao, Sarah Wiegreffe, Uri Alon, Nouha Dziri, Shrimai Prabhumoye, Yiming Yang","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Maynez et al., 2020] Joshua Maynez, Shashi Narayan, Bernd Bohnet, and Ryan McDonald. On faithfulness and factuality in abstractive summarization. In Proceedings of the 58th Annual Meeting of the Association for Compu- tational Linguistics, pages 1906-1919, Online, July 2020. Association for Computational Linguistics.","title":"On faithfulness and factuality in abstractive summarization","authors":"Joshua Maynez, Shashi Narayan, Bernd Bohnet, Ryan Mcdonald","year":"2020","venue":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Nakajima, 2023] Yohei Nakajima. Task-driven autonomous agent utilizing gpt-4, pinecone, and langchain for diverse applications. See https://yoheinakajima. com/task- driven-autonomous-agent-utilizing-gpt-4-pinecone-and- langchain-for-diverse-applications (accessed 18 April 2023), 2023.","title":"Task-driven autonomous agent utilizing gpt-4, pinecone, and langchain for diverse applications","authors":"Yohei Nakajima, Nakajima","year":"2023","venue":null,"doi":null,"url":"https://yoheinakajima.com/task-driven-autonomous-agent-utilizing-gpt-4-pinecone-and-langchain-for-diverse-applications","internal_url":null},{"position":19,"raw":"[Nelson, 2013] Laurie Miller Nelson. Collaborative problem solving. In Instructional-design theories and models, pages 241-267. Routledge, 2013.","title":"Collaborative problem solving","authors":"Laurie Miller, Nelson","year":"2013","venue":"Instructional-design theories and models","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Park et al., 2022] Joon Sung Park, Lindsay Popowski, Carrie Cai, Meredith Ringel Morris, Percy Liang, and Michael S Bernstein. Social simulacra: Creating populated prototypes for social computing systems. In Proceedings of the 35th Annual ACM Symposium on User Interface Software and Technology, pages 1-18, 2022.","title":"Social simulacra: Creating populated prototypes for social computing systems","authors":"Sung Joon, Lindsay Park, Carrie Popowski, Meredith Ringel Cai, Percy Morris, Michael S Liang, Bernstein","year":"2022","venue":"Proceedings of the 35th Annual ACM Symposium on User Interface Software and Technology","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Park et al., 2023] Joon Sung Park, Joseph C O'Brien, Car- rie J Cai, Meredith Ringel Morris, Percy Liang, and Michael S Bernstein. Generative agents: Interactive simu- lacra of human behavior. arXiv preprint arXiv:2304.03442, 2023.","title":"Generative agents: Interactive simulacra of human behavior","authors":"Sung Joon, Park, C O' Joseph, Carrie J Brien, Meredith Ringel Cai, Percy Morris, Michael S Liang, Bernstein","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Qian et al., 2023] Chen Qian, Xin Cong, Cheng Yang, Weize Chen, Yusheng Su, Juyuan Xu, Zhiyuan Liu, and Maosong Sun. Communicative agents for software development. arXiv preprint arXiv:2307.07924, 2023.","title":"Communicative agents for software development","authors":"Chen Qian, Xin Cong, Cheng Yang, Weize Chen, Yusheng Su, Juyuan Xu, Zhiyuan Liu, Maosong Sun","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Qin et al., 2023] Chengwei Qin, Aston Zhang, Zhuosheng Zhang, Jiaao Chen, Michihiro Yasunaga, and Diyi Yang. Is chatgpt a general-purpose natural language processing task solver? arXiv preprint arXiv:2302.06476, 2023.","title":"Is chatgpt a general-purpose natural language processing task solver","authors":"Chengwei Qin, Aston Zhang, Zhuosheng Zhang, Jiaao Chen, Michihiro Yasunaga, Diyi Yang","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Roschelle and Teasley, 1995] Jeremy Roschelle and Stephanie D Teasley. The construction of shared knowl- edge in collaborative problem solving. In Computer supported collaborative learning, pages 69-97. Springer, 1995.","title":"The construction of shared knowledge in collaborative problem solving","authors":"Jeremy Roschelle, Stephanie D Teasley","year":"1995","venue":"Computer supported collaborative learning","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Shinn et al., 2023] Noah Shinn, Beck Labash, and Ash- win Gopinath. Reflexion: an autonomous agent with dynamic memory and self-reflection. arXiv preprint arXiv:2303.11366, 2023.","title":"Reflexion: an autonomous agent with dynamic memory and self-reflection","authors":"Shinn","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Sloman, 1996] Steven A Sloman. The empirical case for two systems of reasoning. Psychological bulletin, 119(1):3, 1996.","title":"The empirical case for two systems of reasoning","authors":"Steven A Sloman","year":"1996","venue":"Psychological bulletin","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Talebirad and Nadiri, 2023] Yashar Talebirad and Amirhos- sein Nadiri. Multi-agent collaboration: Harnessing the power of intelligent llm agents. arXiv preprint arXiv:2306.03314, 2023.","title":"Yashar Talebirad and Amirhossein Nadiri. Multi-agent collaboration: Harnessing the power of intelligent llm agents","authors":"Nadiri Talebirad","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Wang et al., 2023a] Boxin Wang, Weixin Chen, Hengzhi Pei, Chulin Xie, Mintong Kang, Chenhui Zhang, Chejian Xu, Zidi Xiong, Ritik Dutta, Rylan Schaeffer, et al. Decod- ingtrust: A comprehensive assessment of trustworthiness in gpt models. arXiv preprint arXiv:2306.11698, 2023.","title":"Decodingtrust: A comprehensive assessment of trustworthiness in gpt models","authors":"Wang","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Wang et al., 2023b] Peiyi Wang, Lei Li, Liang Chen, Dawei Zhu, Binghuai Lin, Yunbo Cao, Qi Liu, Tianyu Liu, and Zhifang Sui. Large language models are not fair evaluators. arXiv preprint arXiv:2305.17926, 2023.","title":"Large language models are not fair evaluators","authors":"Wang","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Wang et al., 2023c] Zhenhailong Wang, Shaoguang Mao, Wenshan Wu, Tao Ge, Furu Wei, and Heng Ji. Unleashing cognitive synergy in large language models: A task-solving agent through multi-persona self-collaboration. arXiv preprint arXiv:2307.05300, 2023.","title":"Unleashing cognitive synergy in large language models: A task-solving agent through multi-persona self-collaboration","authors":"Wang","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Williams et al., 2023] Ross Williams, Niyousha Hos- seinichimeh, Aritra Majumdar, and Navid Ghaffarzadegan. Epidemic modeling with generative agents. arXiv preprint arXiv:2307.04986, 2023.","title":"Epidemic modeling with generative agents","authors":"Ross Williams, Niyousha Hosseinichimeh, Aritra Majumdar, Navid Ghaffarzadegan","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Woolley et al., 2015] Anita Williams Woolley, Ishani Aggar- wal, and Thomas W Malone. Collective intelligence and group performance. Current Directions in Psychological Science, 24(6):420-424, 2015.","title":"Collective intelligence and group performance","authors":"Anita Williams Woolley, Ishani Aggarwal, Thomas W Malone","year":"2015","venue":"Current Directions in Psychological Science","doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Wu et al., 2023] Qingyun Wu, Gagan Bansal, Jieyu Zhang, Yiran Wu, Shaokun Zhang, Erkang Zhu, Beibin Li, Li Jiang, Xiaoyun Zhang, and Chi Wang. Autogen: Enabling next- gen llm applications via multi-agent conversation frame- work. arXiv preprint arXiv:2308.08155, 2023.","title":"Autogen: Enabling nextgen llm applications via multi-agent conversation framework","authors":"Qingyun Wu, Gagan Bansal, Jieyu Zhang, Yiran Wu, Shaokun Zhang, Erkang Zhu, Beibin Li, Li Jiang, Xiaoyun Zhang, Chi Wang","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":34,"raw":"[Xu et al., 2023] Benfeng Xu, An Yang, Junyang Lin, Quan Wang, Chang Zhou, Yongdong Zhang, and Zhendong Mao. Expertprompting: Instructing large language models to be distinguished experts. arXiv preprint arXiv:2305.14688, 2023.","title":"Expertprompting: Instructing large language models to be distinguished experts","authors":"Xu","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":35,"raw":"[Yao et al., 2022] Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik Narasimhan, and Yuan Cao. Re- act: Synergizing reasoning and acting in language models. arXiv preprint arXiv:2210.03629, 2022.","title":"React: Synergizing reasoning and acting in language models","authors":"Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik Narasimhan, Yuan Cao","year":"2022","venue":null,"doi":null,"url":null,"internal_url":null},{"position":36,"raw":"[Yao et al., 2023] Shunyu Yao, Dian Yu, Jeffrey Zhao, Izhak Shafran, Thomas L Griffiths, Yuan Cao, and Karthik Narasimhan. Tree of thoughts: Deliberate problem solving with large language models. arXiv preprint arXiv:2305.10601, 2023.","title":"Tree of thoughts: Deliberate problem solving with large language models","authors":"Shunyu Yao, Dian Yu, Jeffrey Zhao, Izhak Shafran, Thomas L Griffiths, Yuan Cao, Karthik Narasimhan","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":37,"raw":"[Zheng et al., 2023] Lianmin Zheng, Wei-Lin Chiang, Ying Sheng, Siyuan Zhuang, Zhanghao Wu, Yonghao Zhuang, Zi Lin, Zhuohan Li, Dacheng Li, Eric Xing, et al. Judging llm-as-a-judge with mt-bench and chatbot arena. arXiv preprint arXiv:2306.05685, 2023.","title":"Judging llm-as-a-judge with mt-bench and chatbot arena","authors":"Zheng","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}