A Novel Multi-agent-based Chatbot Approach to Orchestrate Conversational Assistants

Conference paper
Part of the Lecture Notes in Business Information Processing book series (LNBIP, volume 389)


Nowadays, chatbots have become more and more prominent in various domains. Nevertheless, designing a versatile chatbot, giving reasonable answers, is a challenging task. Thereby, the major drawback of most chatbots is their limited scope. Multi-agent-based systems offer approaches to solve problems in a cooperative manner following the “divide and conquer” paradigm. Consequently, it seems promising to design a multi-agent-based chatbot approach scaling beyond the scope of a single application context. To address this research gap, we propose a novel approach orchestrating well-established conversational assistants. We demonstrate and evaluate our approach using six chatbots, providing higher quality than competing artifacts.


Conversational agent Chatbot Multi-agent-based system Orchestration Collaboration Mediation Divide and conquer 


  1. 1.
    Ahmad, N.A., Che, M.H., Zainal, A., et al.: Review of chatbots design techniques. IJACSA 181(8), 7–10 (2018)Google Scholar
  2. 2.
    Klopfenstein, L.C., Delpriori, S., Malatini, S., et al.: The rise of bots: a survey of conversational interfaces, patterns, and paradigms. In: Proceedings of the 12th Conference on Designing Interactive Systems, pp. 555–565 (2017)Google Scholar
  3. 3.
    Chaves, A.P., Gerosa, M.A.: Single or multiple conversational agents? An interactional coherence comparison. In: Proceedings of the 36th CHI (2018)Google Scholar
  4. 4.
    Masche, J., Le, N.-T.: A review of technologies for conversational systems. In: Proceedings of the 5th ICCSAMA, pp. 212–225 (2017)Google Scholar
  5. 5.
    Dhanda, S.: How chatbots will transform the retail industry. Juniper Research (2018)Google Scholar
  6. 6.
    Abdul-Kader, S.A., Woods, J.C.: Survey on chatbot design techniques in speech conversation systems. IJACSA 6(7), 72–80 (2015)Google Scholar
  7. 7.
    Chen, H., Liu, X., Yin, D., et al.: A survey on dialogue systems: recent advances and new frontiers. ACM SIGKDD Explor. Newslett. 19(2), 25–35 (2017)CrossRefGoogle Scholar
  8. 8.
    Ramesh, K., Ravishankaran, S., Joshi, A., Chandrasekaran, K.: A survey of design techniques for conversational agents. In: Kaushik, S., Gupta, D., Kharb, L., Chahal, D. (eds.) ICICCT 2017. CCIS, vol. 750, pp. 336–350. Springer, Singapore (2017). Scholar
  9. 9.
    Wallace, R.S.: The anatomy of ALICE. In: Epstein, R., Roberts, G., Beber, G. (eds.) Parsing the Turing Test, pp. 181–210. Springer, Dordrecht (2009). Scholar
  10. 10.
    Serban, I.V., Sankar, C., Germain, M., et al.: A deep reinforcement learning chatbot (2017)Google Scholar
  11. 11.
    Pichl, J., Marek, P., Konrád, J., et al.: Alquist: the Alexa prize socialbot. In: Proceedings of the 1st Alexa Prize (2017)Google Scholar
  12. 12.
    Huang, T.-H.K., Chang, J.C., Bigham, J.P.: Evorus: a crowd-powered conversational assistant built to automate itself over time. In: Proceedings of the 36th CHI (2018)Google Scholar
  13. 13.
    Papaioannou, I., Curry, A.C., Part, J.L., et al.: Alana: social dialogue using an ensemble model and a ranker trained on user feedback. In: Proceedings of the 1st Alexa Prize (2017)Google Scholar
  14. 14.
    Pinhanez, C.S., Candello, H., Pichiliani, M.C., et al.: Different but equal: comparing user collaboration with digital personal assistants vs. teams of expert agents (2018)Google Scholar
  15. 15.
    Janarthanam, S.: Hands-On Chatbots and Conversational UI Development. Packt Publishing, Birmingham (2017)Google Scholar
  16. 16.
    Chandar, P., et al.: Leveraging conversational systems to assists new hires during onboarding. In: Bernhaupt, R., Dalvi, G., Joshi, A., Balkrishan, D., O’Neill, J., Winckler, M. (eds.) INTERACT 2017. LNCS, vol. 10514, pp. 381–391. Springer, Cham (2017). Scholar
  17. 17.
    Jennings, N.R.: Commitments and conventions: the foundation of coordination in multi-agent systems. Knowl. Eng. Rev. 8(3), 223–250 (1993)MathSciNetCrossRefGoogle Scholar
  18. 18.
    Jennings, N.R.: An agent-based approach for building complex software systems. Commun. ACM 44(4), 35–41 (2001)CrossRefGoogle Scholar
  19. 19.
    Klusch, M., Sycara, K.: Brokering and matchmaking for coordination of agent societies. a survey. In: Omicini, A., Zambonelli, F., Klusch, M. (eds.) Coordination of Internet Agents, pp. 197–224. Springer, Heidelberg (2001).
  20. 20.
    Peffers, K., Tuunanen, T., Rothenberger, M.A., et al.: A design science research methodology for information systems research. JMIS 24(3), 45–77 (2007)Google Scholar
  21. 21.
    Maglio, P.P., Matlock, T., Campbell, C.S., Zhai, S., Smith, B.A.: Gaze and speech in attentive user interfaces. In: Tan, T., Shi, Y., Gao, W. (eds.) ICMI 2000. LNCS, vol. 1948, pp. 1–7. Springer, Heidelberg (2000). Scholar
  22. 22.
    Cui, L., Huang, S., Wei, F., et al.: Superagent. A customer service chatbot for e-commerce websites. In: Proceedings of the 55th Annual Meeting of the ACL, pp. 97–102 (2017)Google Scholar
  23. 23.
    Arentze, T., Timmermans, H.: Modeling the formation of activity agendas using reactive agents. Environ. Plan. B 29(5), 719–728 (2002)CrossRefGoogle Scholar
  24. 24.
    Ehlert, P., Rothkrantz, L.J.M.: Microscopic traffic simulation with reactive driving agents. In: 4th Proceedings of IEEE Intelligent Transportation Systems, pp. 861–866 (2001)Google Scholar
  25. 25.
    Rao, A.S., Georgeff, M.P.: BDI agents. In: 1st ICMAS, pp. 312–319 (1995)Google Scholar
  26. 26.
    Barua, A., Whinston, A.B., Yin, F.: Value and productivity in the internet economy. Computer 33(5), 102–105 (2000)CrossRefGoogle Scholar
  27. 27.
    Decker, K., Sycara, K., Williamson, M.: Middle-agents for the internet. In: Proceedings of the 15th IJCAI, pp. 578–583 (1997)Google Scholar
  28. 28.
    Hettige, B., Karunananda, A.S.: Octopus: a multi agent chatbot. In: Proceedings of the 8th International Research Conference, pp. 41–47 (2015)Google Scholar
  29. 29.
    Gregor, S., Hevner, A.R.: Positioning and presenting design science research for maximum impact. MIS Q. 37, 337–355 (2013)CrossRefGoogle Scholar
  30. 30.
    Baskerville, R., Baiyere, A., Gregor, S., et al.: Design science research contributions: finding a balance between artifact and theory. JAIS 19, 358–376 (2018)CrossRefGoogle Scholar
  31. 31.
    Hevner, A.R., March, S.T., Park, J., et al.: Design science in information systems research. MIS Q. 28, 75–105 (2004)CrossRefGoogle Scholar
  32. 32.
    Labrou, Y., Finin, T., Peng, Y.: Agent communication languages: the current landscape. Intell. Syst. Appl. 14(2), 45–52 (1999)CrossRefGoogle Scholar
  33. 33.
    Park, S., An, D.U.: Automatic e-mail classification using dynamic category hierarchy and semantic features. IETE Tech. Rev. 27(6), 478–492 (2010)CrossRefGoogle Scholar
  34. 34.
    Li, N., Wu, D.D.: Using text mining and sentiment analysis for online forums hotspot detection and forecast. DSS 48(2), 354–368 (2010)Google Scholar
  35. 35.
    Storn, R., Price, K.: Differential evolution – a simple and efficient heuristic for global optimization over continuous spaces. J. Global Optim. 11(4), 341–359 (1997). Scholar
  36. 36.
    Russell, S.J., Norvig, P.: AI. A Modern Approach. Pearson Education, London (2010)Google Scholar
  37. 37.
    Sokolova, M., Japkowicz, N., Szpakowicz, S.: Beyond accuracy, F-score and ROC: a family of discriminant measures for performance evaluation. In: Sattar, A., Kang, B. (eds.) AI 2006. LNCS (LNAI), vol. 4304, pp. 1015–1021. Springer, Heidelberg (2006). Scholar
  38. 38.
    Skorochod’ko, E.F.: Adaptive method of automatic abstracting and indexing. In: Proceedings of the 5th Information Processing Congress, pp. 1179–1182 (1972)Google Scholar
  39. 39.
    Beeferman, D., Berger, A., Lafferty, J.: Statistical models for text segmentation. Mach. Learn. 34(1–3), 177–210 (1999). Scholar
  40. 40.
    Wooldridge, M., Jennings, N.R.: Intelligent agents: theory and practice. Knowl. Eng. Rev. 10(2), 115–152 (1995)CrossRefGoogle Scholar
  41. 41.
    Fikes, R.E., Nilsson, N.J.: STRIPS: a new approach to the application of theorem proving to problem solving. Artif. Intell. 2(3–4), 189–208 (1971)CrossRefGoogle Scholar
  42. 42.
    Dang, V., Croft, B.W.: Query reformulation using anchor text. In: Proceedings of the 3rd WSDM, pp. 41–50 (2010)Google Scholar
  43. 43.
    Mitsuku Dataset. Accessed 06 Dec 2019
  44. 44.
    Rosie Dataset. Accessed 06 Dec 2019
  45. 45.
    Quora Dataset. Accessed 06 Dec 2019
  46. 46.
    Wikipedia Dataset. Accessed 06 Dec 2019
  47. 47.
    Ling, W., Yogatama, D., Dyer, C., et al.: Program induction by rationale generation: learning to solve and explain algebraic word problems. In: Proceedings of the 55th Annual Meeting of the ACL, pp. 158–167 (2017)Google Scholar
  48. 48.
    Bedué, P., Graef, R., Klier, M., et al.: A novel hybrid knowledge retrieval approach for online customer service platforms. In: Proceedings of the 26th ECIS (2018)Google Scholar
  49. 49.
    Aimpulse Spectrum. Accessed 23 Aug 2019
  50. 50.
    Kohavi, R.: A study of cross-validation and bootstrap for accuracy estimation and model selection. In: Proceedings of the 14th IJCAI, vol. 14, no. 2, pp. 1137–1145 (1995)Google Scholar
  51. 51.
    Venable, J., Pries-Heje, J., Baskerville, R.: FEDS: a framework for evaluation in design science research. Eur. J. Inf. Syst. 25, 77–89 (2016)CrossRefGoogle Scholar
  52. 52.
    Stoeckli, E., Uebernickel, F., Brenner, W.: Exploring affordances of slack integrations and their actualization within enterprises-towards an understanding of how chatbots create value. In: Proceedings of the 51st HICSS (2018)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.University UlmUlmGermany

Personalised recommendations