Skip to main content
Springer Nature Link
Log in

SPARKIT: A Mind Map-Based MAS for Idea Generation Support

  • Conference paper
  • First Online:
Engineering Multi-Agent Systems (EMAS 2024)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 15152))

Included in the following conference series:

  • 243 Accesses

Abstract

Innovative solutions to societal challenges require the generation of creative ideas. Collaboration between humans and multi-agent systems (MAS) is a promising approach for idea generation, yet fostering creative discussions remains a challenge. This paper proposes Synergistic Platform for Advancing and Reinforcing Knowledge through Interactive Tools (SPARKIT) and SPARK-flow leveraging mind maps to facilitate idea generation within a MAS framework. SPARKIT supports idea generation with two types of large language model (LLM)-based agents: Debater Agents and the Moderator Agent. Debater Agents offer varied perspectives from their expertise, while the Moderator Agent structures discussions into a mind map to enhance user-agent collaboration. SPARK-flow is designed to stimulate creative idea generation by orchestrating discussions among these agents. A distinctive aspect of SPARKIT and SPARK-flow is that the agents facilitate the discussion and its structuring into a mind map, reducing the user’s burden compared to existing methods. This paper compares different methods of discussion using language models and reveals that the impact of the discussion method on the creativity of ideas is consistent between humans and language models, with mind maps significantly enhancing creativity.

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

Access this chapter

Log in via an institution

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

References

  1. Achiam, J., et al.: GPT-4 technical report. arXiv preprint arXiv:2303.08774 (2023)

  2. Al-Samarraie, H., Hurmuzan, S.: A review of brainstorming techniques in higher education. Thinking Skills Creat. 27, 78–91 (2018)

    Article  Google Scholar 

  3. Andolina, S., Klouche, K., Cabral, D., Ruotsalo, T., Jacucci, G.: Inspirationwall: supporting idea generation through automatic information exploration. In: Proceedings of the 2015 ACM SIGCHI Conference on Creativity and Cognition, pp. 103–106 (2015)

    Google Scholar 

  4. Andolina, S., Schneider, H., Chan, J., Klouche, K., Jacucci, G., Dow, S.: Crowdboard: augmenting in-person idea generation with real-time crowds. In: Proceedings of the 2017 ACM SIGCHI Conference on Creativity and Cognition, pp. 106–118 (2017)

    Google Scholar 

  5. Benedek, M., Neubauer, A.C.: Revisiting mednick’s model on creativity-related differences in associative hierarchies: evidence for a common path to uncommon thought. J. Creat. Behav. 47(4), 273–289 (2013)

    Article  Google Scholar 

  6. Buzan, T., Buzan, B.: The Mind Map Book. Pearson Education, Boston (2006)

    Google Scholar 

  7. Camburn, B., et al.: Computer-aided mind map generation via crowdsourcing and machine learning. Res. Eng. Design 31, 383–409 (2020)

    Article  Google Scholar 

  8. Cer, D., Yang, Y., Kong, S.y., Hua, N., Limtiaco, N., St. John, R., Constant, N., Guajardo-Cespedes, M., Yuan, S., Tar, C., Strope, B., Kurzweil, R.: Universal sentence encoder for English. In: Blanco, E., Lu, W. (eds.) Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pp. 169–174. Association for Computational Linguistics, Brussels, Belgium (Nov 2018). https://doi.org/10.18653/v1/D18-2029. https://aclanthology.org/D18-2029

  9. Chan, C.M., et al.: Chateval: towards better llm-based evaluators through multi-agent debate. arXiv preprint arXiv:2308.07201 (2023)

  10. Chan, J., Dow, S.P., Schunn, C.D.: Do the best design ideas (really) come from conceptually distant sources. In: Engineering a Better Future: Interplay between Engineering, Social Sciences, and Innovation, p. 111 (2018)

    Google Scholar 

  11. Chan, J., Schunn, C.D.: The importance of iteration in creative conceptual combination. Cognition 145, 104–115 (2015)

    Article  Google Scholar 

  12. Chen, T.J., Krishnamurthy, V.R.: Investigating a mixed-initiative workflow for digital mind-mapping. J. Mech. Des. 142(10), 101404 (2020)

    Article  Google Scholar 

  13. Di Fede, G., Rocchesso, D., Dow, S.P., Andolina, S.: The idea machine: LLM-based expansion, rewriting, combination, and suggestion of ideas. In: Proceedings of the 14th Conference on Creativity and Cognition, pp. 623–627 (2022)

    Google Scholar 

  14. Diedrich, J., Benedek, M., Jauk, E., Neubauer, A.C.: Are creative ideas novel and useful? Psychol. Aesthet. Creat. Arts 9(1), 35 (2015)

    Article  Google Scholar 

  15. Dow, S.P., Heddleston, K., Klemmer, S.R.: The efficacy of prototyping under time constraints. In: Proceedings of the Seventh ACM Conference on Creativity and Cognition, pp. 165–174 (2009)

    Google Scholar 

  16. Du, Y., Li, S., Torralba, A., Tenenbaum, J.B., Mordatch, I.: Improving factuality and reasoning in language models through multiagent debate. arXiv preprint arXiv:2305.14325 (2023)

  17. Georgiev, G.V., Georgiev, D.D.: Enhancing user creativity: semantic measures for idea generation. Knowl.-Based Syst. 151, 1–15 (2018). https://doi.org/10.1016/j.knosys.2018.03.016. https://www.sciencedirect.com/science/article/pii/S0950705118301394

  18. Girotra, K., Terwiesch, C., Ulrich, K.T.: Idea generation and the quality of the best idea. Manag. Sci. 56(4), 591–605 (2010)

    Article  Google Scholar 

  19. Guilford, J.P.: Creative abilities in the arts. Psychol. Rev. 64(2), 110 (1957)

    Article  Google Scholar 

  20. Hackl, V., Müller, A.E., Granitzer, M., Sailer, M.: Is GPT-4 a reliable rater? evaluating consistency in gpt-4 text ratings. arXiv preprint arXiv:2308.02575 (2023)

  21. Hao, N., et al.: Reflection enhances creativity: beneficial effects of idea evaluation on idea generation. Brain Cogn. 103, 30–37 (2016)

    Article  Google Scholar 

  22. Kern, F.B., Wu, C.T., Chao, Z.C.: Assessing novelty, feasibility, and value of creative ideas with an unsupervised approach using GPT-4 (2023)

    Google Scholar 

  23. Kim, D., Cerigo, D.B., Jeong, H., Youn, H.: Technological novelty profile and invention’s future impact. EPJ Data Sci. 5(1), 1–15 (2016)

    Article  Google Scholar 

  24. Leeds, A.J., Kudrowitz, B., Kwon, J.: Mapping associations: exploring divergent thinking through mind mapping. Int. J. Des. Creat. Innov. 7(1–2), 16–29 (2019)

    Google Scholar 

  25. Luo, J., Sarica, S., Wood, K.L.: Computer-aided design ideation using innogps. In: International Design Engineering Technical Conferences and Computers and Information in Engineering Conference, vol. 59186, p. V02AT03A011. American Society of Mechanical Engineers (2019)

    Google Scholar 

  26. Ma, K., Grandi, D., McComb, C., Goucher-Lambert, K.: Conceptual design generation using large language models. arXiv preprint arXiv:2306.01779 (2023)

  27. Rafailov, R., Sharma, A., Mitchell, E., Ermon, S., Manning, C.D., Finn, C.: Direct preference optimization: your language model is secretly a reward model. arXiv preprint arXiv:2305.18290 (2023)

  28. Reiter-Palmon, R., Forthmann, B., Barbot, B.: Scoring divergent thinking tests: a review and systematic framework. Psychol. Aesthet. Creat. Arts 13(2), 144 (2019)

    Article  Google Scholar 

  29. Runco, M.A., Acar, S.: Divergent thinking as an indicator of creative potential. Creat. Res. J. 24(1), 66–75 (2012)

    Article  Google Scholar 

  30. Setiyawan, D.: Improving students’ speaking skills in generating idea through new concept of mind mapping technique. In: International Conference on Educational Research and Innovation (ICERI 2019), pp. 227–231. Atlantis Press (2020)

    Google Scholar 

  31. Shih, P.C., Nguyen, D.H., Hirano, S.H., Redmiles, D.F., Hayes, G.R.: GroupMind: supporting idea generation through a collaborative mind-mapping tool. In: Proceedings of the 2009 ACM International Conference on Supporting Group Work, pp. 139–148 (2009)

    Google Scholar 

  32. Sun, M., Wang, M., Wegerif, R., Peng, J.: How do students generate ideas together in scientific creativity tasks through computer-based mind mapping? Comput. Educ. 176, 104359 (2022)

    Article  Google Scholar 

  33. Tao, M., Xie, R.: Mind map based computer network knowledge graph visualization research and application. In: Jia, W., et al. (eds.) SETE 2021. LNCS, vol. 13089, pp. 3–12. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-92836-0_1

    Chapter  Google Scholar 

  34. Wahl, J., Hutter, K., Füller, J.: How ai-supported searches through other perspectives affect ideation outcomes. Int. J. Innov. Manag. 26(09), 2240028 (2022)

    Article  Google Scholar 

  35. Wang, H.C., Cosley, D., Fussell, S.R.: Idea expander: supporting group brainstorming with conversationally triggered visual thinking stimuli. In: Proceedings of the 2010 ACM Conference on Computer Supported Cooperative Work, pp. 103–106 (2010)

    Google Scholar 

  36. Wen, Y., Wang, Z., Sun, J.: Mindmap: knowledge graph prompting sparks graph of thoughts in large language models. arXiv preprint arXiv:2308.09729 (2023)

  37. Xu, B., et al.: Expertprompting: instructing large language models to be distinguished experts. arXiv preprint arXiv:2305.14688 (2023)

  38. Zampetakis, L.A., Tsironis, L., Moustakis, V.: Creativity development in engineering education: the case of mind mapping. J. Manag. Dev. 26(4), 370–380 (2007)

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Grad. Sch. Aoyama Gakuin University, Sagamihara, Japan

    Masaki Ishizaka & Yoshito Tobe

  2. The University of Tokyo, Meguro, Japan

    Akihito Taya

Authors
  1. Masaki Ishizaka
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Akihito Taya
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yoshito Tobe
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Masaki Ishizaka .

Editor information

Editors and Affiliations

  1. University of Milano-Bicocca, Milan, Italy

    Daniela Briola

  2. University of Aberdeen, Aberdeen, UK

    Rafael C. Cardoso

  3. Utrecht University, Utrecht, The Netherlands

    Brian Logan

Appendix

Appendix

1.1 Promptes

In this section, we provide examples of the prompts used in experiments. These prompts are critical for understanding the input that was provided to the language model (Table 2).

Table 2. Prompt Templates
Full size table
Table 3. Examples of Themes
Full size table

1.2 Themes

In this section, we present subset of themes used in experiments (Table 3).

Rights and permissions

Reprints and permissions

Copyright information

© 2024 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

Ishizaka, M., Taya, A., Tobe, Y. (2024). SPARKIT: A Mind Map-Based MAS for Idea Generation Support. In: Briola, D., Cardoso, R.C., Logan, B. (eds) Engineering Multi-Agent Systems. EMAS 2024. Lecture Notes in Computer Science(), vol 15152. Springer, Cham. https://doi.org/10.1007/978-3-031-71152-7_1

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-71152-7_1

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-71151-0

  • Online ISBN: 978-3-031-71152-7

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics