Skip to main content

Collaborative Problem-Solving with LLM: A Multi-agent System Approach to Solve Complex Tasks Using Autogen

  • Conference paper
  • First Online:
Highlights in Practical Applications of Agents, Multi-Agent Systems, and Digital Twins: The PAAMS Collection (PAAMS 2024)

Abstract

This paper explores the utilization of Large Language Models (LLMs) in Multi-Agent Systems (MAS) in scenarios where the agents are expected to collaborate and negotiate their preferences, creating temporary alliances to achieve a common goal (complex task). MAS have been acknowledged for their potential in facilitating collaboration to solve complex problems. However, widespread adoption of MAS is impeded by challenges related to defining communication languages and developing frameworks that balance specificity for complex use cases with general applicability across different domains. The emergence of LLMs, such as GPT-4, presents a novel approach to MAS, offering advanced natural language processing capabilities that (potentially) circumventing the need for explicit communication language definitions. This paper proposes an MAS implementation utilizing LLMs within the Autogen framework, emphasizing collaboration and negotiation among agents, through a case study involving a product manufacturing scenario where agents are tasked with intricate decision-making. Results from three test scenarios demonstrate the efficacy of this approach, that can be used to enhance further developments in MAS scenarios of application. However, despite the promise, challenges remain, including the cost of running LLMs and the need for further exploration of their capabilities.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

Notes

  1. 1.

    https://github.com/microsoft/autogen.git#main.

References

  1. Agostini, L., Filippini, R.: Organizational and managerial challenges in the path toward industry 4.0. Eur. J. Innov. Manage. 22, 406–421 (2019)

    Google Scholar 

  2. Aknine, S., Pinson, S., Shakun, M.F.: A multi-agent coalition formation method based on preference models. Group Decis. Negot. 13(6), 513–538 (2004). https://doi.org/10.1007/s10726-005-3074-5

    Article  MATH  Google Scholar 

  3. Allen, J., Galescu, L., Teng, C.M., Perera, I.: Conversational agents for complex collaborative tasks. AI Mag. 41(4), 54–78 (2020). https://doi.org/10.1609/aimag.v41i4.7384

    Article  Google Scholar 

  4. Cardoso, R.C., Ferrando, A.: A review of agent-based programming for multi-agent systems. First Comput. 10(2), 16 (2021). https://doi.org/10.3390/computers10020016

    Article  MATH  Google Scholar 

  5. Chang, Y., et al.: A survey on evaluation of large language models. ACM Trans. Intell. Syst. Technol. 15(3), 1–45 (2024). https://doi.org/10.1145/3641289

    Article  MATH  Google Scholar 

  6. Finin, T., McKay, D., Fritzson, R.: An overview of kqml: a knowledge query and manipulation language (1992)

    Google Scholar 

  7. Friedman, L., et al.: Leveraging large language models in conversational recommender systems. arXiv.org (2023). https://doi.org/10.48550/ARXIV.2305.07961

  8. Horling, B., Lesser, V.: A survey of multi-agent organizational paradigms. Knowl. Eng. Rev. 19(4), 281–316 (2004). https://doi.org/10.1017/s0269888905000317

    Article  MATH  Google Scholar 

  9. Lau, H.C., Zhang, L.: Task allocation via multi-agent coalition formation: taxonomy, algorithms and complexity. In: Proceedings. 15th IEEE International Conference on Tools with Artificial Intelligence, pp. 346–350. TAI-03, IEEE Comput. Soc (2003). https://doi.org/10.1109/tai.2003.1250210

  10. Nori, H., King, N., McKinney, S.M., Carignan, D., Horvitz, E.: Capabilities of gpt-4 on medical challenge problems. null (2023). https://doi.org/10.48550/ARXIV.2303.13375

  11. O’Brien, P.D., Nicol, R.C.: Fipa—towards a standard for software agents. BT Technol. J. 16, 51–59 (1998)

    Article  MATH  Google Scholar 

  12. Olsen, T., Tomlin, B.: Industry 4.0: Opportunities and challenges for operations management. Manuf. Serv. Oper. Manage. 22, 113–122 (2020)

    Google Scholar 

  13. Sarkar, S., Curado Malta, M., Dutta, A.: A survey on applications of coalition formation in multi-agent systems. Concurrency Comput. Pract. Exp. 34(11), e6876 (2022). https://doi.org/10.1002/cpe.6876

    Article  MATH  Google Scholar 

  14. Singhal, K., et al.: Towards expert-level medical question answering with large language models. arXiv.org (2023). https://doi.org/10.48550/ARXIV.2305.09617

  15. Soon, G.K., On, C.K., Anthony, P., Hamdan, A.R.: A review on agent communication language. Computational Science and Technology: 5th ICCST 2018, Kota Kinabalu, Malaysia, 29–30 August 2018 pp. 481–491 (2019)

    Google Scholar 

  16. Stone, P., Veloso, M.: Multiagent systems: a survey from a machine learning perspective. Auton. Robot. 8(3), 345–383 (2000). https://doi.org/10.1023/a:1008942012299

    Article  MATH  Google Scholar 

  17. Wang, L., Lyu, C., Ji, T., Zhang, Z., Yu, D., Shi, S., Tu, Z.: Document-level machine translation with large language models. In: Conference on Empirical Methods in Natural Language Processing (2023). https://doi.org/10.48550/ARXIV.2304.02210

  18. Wang, S., Wan, J., Zhang, D., Li, D., Zhang, C.: Towards smart factory for industry 4.0: a self-organized multi-agent system with big data based feedback and coordination. Comput. Netw. 101, 158–168 (2016). https://doi.org/10.1016/j.comnet.2015.12.017

  19. Wooldridge, M., Jennings, N.R.: Intelligent agents: theory and practice. Knowl. Eng. Rev. 10(2), 115–152 (1995). https://doi.org/10.1017/s0269888900008122

    Article  MATH  Google Scholar 

  20. Wu, Q., et al.: Autogen: enabling next-gen llm applications via multi-agent conversation framework (2023)

    Google Scholar 

  21. Zhao, W.X., et al.: A survey of large language models, March 2023. https://doi.org/10.48550/ARXIV.2303.18223

Download references

Acknowledgements

This work has been supported by national funds through FCT – Fundação para a Ciência e Tecnologia (Portuguese Foundation for Science and Technology) through the Projects UIDB/04728/2020, UIDP/04728/2020, and the Ricardo Barbosa doctoral Grant with the reference UI/BD/154187/2022. The work of Paulo Novais is supported through the Project UIDB/00319/2020.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Ricardo Barbosa .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2025 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Barbosa, R., Santos, R., Novais, P. (2025). Collaborative Problem-Solving with LLM: A Multi-agent System Approach to Solve Complex Tasks Using Autogen. In: González-Briones, A., et al. Highlights in Practical Applications of Agents, Multi-Agent Systems, and Digital Twins: The PAAMS Collection. PAAMS 2024. Communications in Computer and Information Science, vol 2149. Springer, Cham. https://doi.org/10.1007/978-3-031-73058-0_17

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-73058-0_17

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-73057-3

  • Online ISBN: 978-3-031-73058-0

  • eBook Packages: Artificial Intelligence (R0)

Publish with us

Policies and ethics