- Thomas Sepanosian ORCID:orcid.org/0009-0001-7342-379812,
- Zoran Milosevic ORCID:orcid.org/0000-0002-1364-742313 &
- Andrew Blair ORCID:orcid.org/0009-0000-0254-506114
Part of the book series:Lecture Notes in Business Information Processing ((LNBIP,volume 537))
Included in the following conference series:
72Accesses
Abstract
There is an increasing potential for using AI applications in finance, ranging from simpler Generative AI applications to more complex, agent oriented solutions. This paper reports on our experience in applying early AI solutions in an Australian fintech landscape. We first present a framework developed to support industry experts and practitioners in adopting AI solutions in a scaleable manner, to ensure the adoption of fit-for-purpose AI systems. We then focus on a longer term research dimension, which addresses more complex business problems for which the emerging multi-agent AI technologies may offer more value. We experimented with these technologies, including their integration with more mature approaches such as RAG. Our proof of concept for retirement planning application, highlights benefits and directions for LLM-powered AI agents, and also identifies limitations of current technologies. Specifically, deploying multi-agent technologies on low-powered infrastructure presents challenges. These limitations can hinder the implementation of solutions that require reliable reasoning and collaboration. Our proof of concept highlights both the potential of multi-agent technologies, and the limitations that need to be addressed.
This is a preview of subscription content,log in via an institution to check access.
Access this chapter
Subscribe and save
- Get 10 units per month
- Download Article/Chapter or eBook
- 1 Unit = 1 Article or 1 Chapter
- Cancel anytime
Buy Now
- Chapter
- JPY 3498
- Price includes VAT (Japan)
- eBook
- JPY 7549
- Price includes VAT (Japan)
- Softcover Book
- JPY 9437
- Price includes VAT (Japan)
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Implementation available at GitHub:https://github.com/Thomas-mp4/Multi-Agent-Retirement-Planning.
References
Australian Banking Association: Positioning Australia as a Leader in Digital Economy Regulation - Automated Decision Making and AI Regulation (2022).https://www.ausbanking.org.au/submission/automated-decision-making-and-ai-regulation/. Accessed 07 July 2024
Australian Government: Superannuation Industry (Supervision) Act 1993 (1993).https://www.legislation.gov.au/C2004A04633/latest/text
Australian Taxation Office: Understanding concessional and non-concessional contributions (2023).https://www.ato.gov.au/individuals-and-families/super-for-individuals-and-families/super/growing-and-keeping-track-of-your-super/caps-limits-and-tax-on-super-contributions/understanding-concessional-and-non-concessional-contributions. Accessed 07 July 2024
Australian Taxation Office: Concessional contributions cap (2024).https://www.ato.gov.au/individuals-and-families/super-for-individuals-and-families/super/growing-and-keeping-track-of-your-super/caps-limits-and-tax-on-super-contributions/concessional-contributions-cap. Accessed 07 July 2024
Australian Taxation Office: Non-concessional contributions cap (2024).https://www.ato.gov.au/individuals-and-families/super-for-individuals-and-families/super/growing-and-keeping-track-of-your-super/caps-limits-and-tax-on-super-contributions/non-concessional-contributions-cap. Accessed 23 June 2024
Australian Taxation Office: Restrictions on non-voluntary contributions (2024).https://www.ato.gov.au/individuals-and-families/super-for-individuals-and-families/super/growing-and-keeping-track-of-your-super/caps-limits-and-tax-on-super-contributions/restrictions-on-voluntary-contributions. Accessed 23 June 2024
Chase, H.: LangChain (2022).https://github.com/langchain-ai/langchain
David, W.: David Walker’s tech trends to watch in 2024 (2024).https://www.westpac.com.au/news/in-depth/2024/02/david-walkers-tech-trends-to-watch-in-2024/. Accessed 07 July 2024
Dodig-Crnkovic, G., Burgin, M.: A systematic approach to autonomous agents. Philosophies9(2), 44 (2024).https://doi.org/10.3390/philosophies9020044
Gao, Y., et al.: Retrieval-Augmented Generation for Large Language Models: A Survey (2024).http://arxiv.org/abs/2312.10997
Groq: Fast AI inference (2024).https://groq.com/. Accessed 07 July 2024
João, M.: CrewAI documentation.https://docs.crewai.com/. Accessed 05 July 2024
João, M.: CrewAI (2024).https://github.com/joaomdmoura/crewAI
João, M.: CrewAI tools (2024).https://github.com/joaomdmoura/crewai-tools
Kasisto: Conversational AI solutions for banking and finance.https://kasisto.com/. Accessed 07 July 2024
King & Wood Mallesons: Australian government interim response on the regulation of AI: inching towards safe and responsible AI (2024).https://www.kwm.com/au/en/home.html. Accessed 07 July 2024
Mistral AI: Function calling (2024).https://docs.mistral.ai/capabilities/function_calling/. Accessed 07 July 2024
Ollama: Ollama (2024).https://github.com/ollama/ollama
OpenAI: OpenAI API platform (2024).https://openai.com/api/. Accessed 07 July 2024
Ouyang, S., Zhang, J.M., Harman, M., Wang, M.: LLM is Like a Box of Chocolates: The Non-determinism of ChatGPT in Code Generation (2023)
Park, J.S., O’Brien, J.C., Cai, C.J., Morris, M.R., Liang, P., Bernstein, M.S.: Generative Agents: Interactive Simulacra of Human Behavior (2023).https://doi.org/10.48550/arXiv.2304.03442
Posh.AI: Ai built for banking.https://www.posh.ai/. Accessed 07 July 2024
Takyar, A.: Agentic RAG: What it is, its types, applications and implementation (2024).https://www.leewayhertz.com/agentic-rag/
Wang, L., et al.: A survey on large language model based autonomous agents. Front. Comput. Sci.18(6), 186345 (2024).https://doi.org/10.1007/s11704-024-40231-1
Weng, L.: LLM Powered Autonomous Agents (2023).https://lilianweng.github.io/posts/2023-06-23-agent/. Accessed 07 July 2024
Wu, Q., et al.: AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation Framework (2023)
Xu, B., et al.: ExpertPrompting: Instructing Large Language Models to be Distinguished Experts (2023)
Acknowledgements
We would like to express our gratitude to the anonymous reviewers for their valuable feedback and constructive comments. Their insights contributed to the improvement of this paper during the revision process.
Author information
Authors and Affiliations
University of Twente, Enschede, The Netherlands
Thomas Sepanosian
Deontik, Brisbane, Australia
Zoran Milosevic
Westpac, Sydney, Australia
Andrew Blair
- Thomas Sepanosian
You can also search for this author inPubMed Google Scholar
- Zoran Milosevic
You can also search for this author inPubMed Google Scholar
- Andrew Blair
You can also search for this author inPubMed Google Scholar
Corresponding author
Correspondence toThomas Sepanosian.
Editor information
Editors and Affiliations
University of Duisburg-Essen, Essen, Germany
Monika Kaczmarek-Heß
Niederrhein University of Applied Sciences, Mönchengladbach, Germany
Kristina Rosenthal
Czech Technical University in Prague, Prague, Czech Republic
Marek Suchánek
Universidade de Lisboa, Lisbon, Portugal
Miguel Mira Da Silva
TU Wien, Vienna, Austria
Henderik A. Proper
TU Wien, Vienna, Austria
Marianne Schnellmann
Ethics declarations
Disclosure of Interests
The authors declare no competing interests relevant to the content of this article.
Rights and permissions
Copyright information
© 2025 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Sepanosian, T., Milosevic, Z., Blair, A. (2025). Scaling AI Adoption in Finance: Modelling Framework and Implementation Study. In: Kaczmarek-Heß, M., Rosenthal, K., Suchánek, M., Da Silva, M.M., Proper, H.A., Schnellmann, M. (eds) Enterprise Design, Operations, and Computing. EDOC 2024 Workshops . EDOC 2024. Lecture Notes in Business Information Processing, vol 537. Springer, Cham. https://doi.org/10.1007/978-3-031-79059-1_14
Download citation
Published:
Publisher Name:Springer, Cham
Print ISBN:978-3-031-79058-4
Online ISBN:978-3-031-79059-1
eBook Packages:Computer ScienceComputer Science (R0)
Share this paper
Anyone you share the following link with will be able to read this content:
Sorry, a shareable link is not currently available for this article.
Provided by the Springer Nature SharedIt content-sharing initiative