Multi-Agent Systems with Generative AI In Public Innovation Funding Programs: Architecture and Evaluation

Luiz Gustavo Trufilho; Fábio Luís Falchi de Magalhães; João de Paula Ribeiro Neto

doi:10.4067/s0718-2724202600025049

Authors

Luiz Gustavo Trufilho Postgraduate Program in Technological Innovation, Universidade Federal de São Paulo , São José dos Campos, Brazil. https://orcid.org/0009-0008-9900-7726
Fábio Luís Falchi de Magalhães Postgraduate Program in Technological Innovation, Universidade Federal de São Paulo , São José dos Campos, Brazil.
João de Paula Ribeiro Neto Postgraduate Program in Administration, Universidade Municipal de São Caetano do Sul , São Caetano do Sul, Brazil.

DOI:

https://doi.org/10.4067/s0718-2724202600025049

Keywords:

public innovation funding, generative artificial intelligence, multi-agent systems, design science research, Centelha Program

Abstract

Public innovation funding programs are central instruments of innovation policy across economies, with initiatives such as the Small Business Innovation Research (SBIR) in the United States, the European Innovation Council under Horizon Europe and the Centelha Program in Brazil. Despite robust instrumental designs, proposal preparation for these programs constitutes a systemic barrier for small and medium-sized enterprises. This paper describes the development and exploratory empirical evaluation of a technical-technological product in the Software category: a multi-agent system based on generative artificial intelligence, organized in five functional layers and fifteen hierarchical agents. The interface runs on WhatsApp and orchestration is handled by the low-code platform n8n. The research adopted Design Science Research and the artifact was evaluated, in an exploratory qualitative study of the Centelha Program case, through semi-structured interviews with ten specialists, analyzed using the Gioia, Corley and Hamilton method. Four aggregate dimensions and four research propositions emerged from this analysis. Results indicate adherence to the program's official criteria and high adoption intent. The articulation between multi-agent systems, large language models and ubiquitous communication channels offers a concrete path to democratize access to public innovation funding, with potential transferability to other programs and human review safeguards to mitigate hallucinations and ethical risks identified.

Downloads

Download data is not yet available.

References

Acharya, D. B., Kuppan, K., & Divya, B. (2025). Agentic AI: Autonomous intelligence for complex goals—A comprehensive survey. IEEE Access, 13, 18912–18936. https://doi.org/10.1109/ACCESS.2025.3532853

Arrow, K. J. (1962). Economic welfare and the allocation of resources for invention. In R. R. Nelson (Ed.), The rate and direction of inventive activity: Economic and social factors (pp. 609–626). Princeton University Press. https://doi.org/10.1515/9781400879762-024

Author. (2026). Multi-agent system based on generative AI to support innovation funding projects: Institutional hotsite [Reference redacted for blind review].

Bender, E. M., Gebru, T., McMillan-Major, A., & Shmitchell, S. (2021). On the dangers of stochastic parrots: Can language models be too big? Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency, 610–623. https://doi.org/10.1145/3442188.3445922

Bezerra Borges, D., Meyer Soares, P., & Santana Silva, M. (2021). Programs and instruments for promoting innovation with technology-based companies in Brazil. Journal of Technology Management & Innovation, 16(2), 28–40. https://doi.org/10.4067/S0718-27242021000200028

Brooke, J. (1996). SUS: A “quick and dirty” usability scale. In P. W. Jordan, B. Thomas, B. A. Weerdmeester, & I. L. McClelland (Eds.), Usability evaluation in industry (pp. 189–194). Taylor & Francis.

Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J. D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., Agarwal, S., Herbert-Voss, A., Krueger, G., Henighan, T., Child, R., Ramesh, A., Ziegler, D. M., Wu, J., Winter, C., … Amodei, D. (2020). Language models are few-shot learners. Advances in Neural Information Processing Systems, 33, 1877–1901. https://proceedings.neurips.cc/paper/2020/hash/1457c0d6bfcb4967418bfb8ac142f64a-Abstract.html

Castro, G. F. O., Rosário, F. J. P., & Lima, A. A. (2022). O Programa Centelha AL como fonte de inovação frugal [The Centelha AL Program as a source of frugal innovation]. Diversitas Journal, 7(1), 376–389. https://doi.org/10.48017/dj.v7i1.2066

Creswell, J. W., & Creswell, J. D. (2018). Research design: Qualitative, quantitative, and mixed methods approaches (5th ed.). Sage.

Dorri, A., Kanhere, S. S., & Jurdak, R. (2018). Multi-agent systems: A survey. IEEE Access, 6, 28573–28593. https://doi.org/10.1109/ACCESS.2018.2831228

Dresch, A., Lacerda, D. P., & Antunes Júnior, J. A. V. (2015a). Design science research: Método de pesquisa para avanço da ciência e tecnologia [Design science research: A research method for the advancement of science and technology]. Bookman.

Dresch, A., Lacerda, D. P., & Miguel, P. A. C. (2015b). Uma análise distintiva entre o estudo de caso, a pesquisa-ação e a design science research [A distinctive analysis of case study, action research and design science research]. Revista Brasileira de Gestão de Negócios, 17(56), 1116–1133. https://doi.org/10.7819/rbgn.v17i56.2069

Edler, J., & Fagerberg, J. (2017). Innovation policy: What, why, and how. Oxford Review of Economic Policy, 33(1), 2–23. https://doi.org/10.1093/oxrep/grx001

Fabiani, S., & Sbragia, R. (2014). Tax incentives for technological business innovation in Brazil: The use of the Good Law – Lei do Bem (Law No. 11196/2005). Journal of Technology Management & Innovation, 9(4), 53–63. https://doi.org/10.4067/S0718-27242014000400004

Gama, F., & Magistretti, S. (2025). Artificial intelligence in innovation management: A review of innovation capabilities and a taxonomy of AI applications. Journal of Product Innovation Management, 42(1), 76–111. https://doi.org/10.1111/jpim.12698

Gioia, D. A., Corley, K. G., & Hamilton, A. L. (2013). Seeking qualitative rigor in inductive research: Notes on the Gioia methodology. Organizational Research Methods, 16(1), 15–31. https://doi.org/10.1177/1094428112452151

Guo, T., Chen, X., Wang, Y., Chang, R., Pei, S., Chawla, N. V., Wiest, O., & Zhang, X. (2024). Large language model based multi-agents: A survey of progress and challenges. arXiv. https://doi.org/10.48550/arXiv.2402.01680

He, J., Treude, C., & Lo, D. (2025). LLM-based multi-agent systems for software engineering: Literature review, vision, and the road ahead. ACM Transactions on Software Engineering and Methodology, 34(5), Article 124. https://doi.org/10.1145/3712003

Hevner, A. R., March, S. T., Park, J., & Ram, S. (2004). Design science in information systems research. MIS Quarterly, 28(1), 75–105. https://doi.org/10.2307/25148625

Howell, S. T. (2017). Financing innovation: Evidence from R&D grants. American Economic Review, 107(4), 1136–1164. https://doi.org/10.1257/aer.20150808

Ji, Z., Lee, N., Frieske, R., Yu, T., Su, D., Xu, Y., Ishii, E., Bang, Y. J., Madotto, A., & Fung, P. (2023). Survey of hallucination in natural language generation. ACM Computing Surveys, 55(12), Article 248. https://doi.org/10.1145/3571730

Lerner, J. (2010). The future of public efforts to boost entrepreneurship and venture capital. Small Business Economics, 35(3), 255–264. https://doi.org/10.1007/s11187-010-9298-z

Lima, G. L., & Aguiar, M. S. (2024). Towards a Docker-based architecture for open multi-agent systems. IAES International Journal of Artificial Intelligence, 13(1), 45–56. https://doi.org/10.11591/ijai.v13.i1.pp45-56

Liu, N. F., Lin, K., Hewitt, J., Paranjape, A., Bevilacqua, M., Petroni, F., & Liang, P. (2024). Lost in the middle: How language models use long contexts. Transactions of the Association for Computational Linguistics, 12, 157–173. https://doi.org/10.1162/tacl_a_00638

Liu, Y., Lo, S. K., Lu, Q., Zhu, L., Zhao, D., Xu, X., Harrer, S., & Whittle, J. (2025). Agent design pattern catalogue: A collection of architectural patterns for foundation model based agents. Journal of Systems and Software, 220, Article 112278. https://doi.org/10.1016/j.jss.2024.112278

Lu, Q., Zhu, L., Xu, X., Xing, Z., Harrer, S., & Whittle, J. (2024). Towards responsible generative AI: A reference architecture for designing foundation model based agents. 2024 IEEE 21st International Conference on Software Architecture Companion (ICSA-C), 119–126. https://doi.org/10.1109/ICSA-C63560.2024.00028

Mazzucato, M. (2018). Mission-oriented innovation policies: Challenges and opportunities. Industrial and Corporate Change, 27(5), 803–815. https://doi.org/10.1093/icc/dty034

Ministério da Ciência, Tecnologia, Inovações e Comunicações. (2018). Portaria nº 4.082, de 10 de agosto de 2018: Institui o Programa Nacional de Apoio à Geração de Empreendimentos Inovadores (Programa Centelha) [Ordinance No. 4,082 of August 10, 2018: Establishing the National Program to Support the Generation of Innovative Enterprises (Centelha Program)]. https://antigo.mctic.gov.br/mctic/opencms/legislacao/portarias/Portaria_MCTIC_n_4082_de_10082018.html

Ooi, K.-B., Tan, G. W.-H., Al-Emran, M., Al-Sharafi, M. A., Capatina, A., Chakraborty, A., Dwivedi, Y. K., Huang, T.-L., Kar, A. K., Lee, V.-H., Loh, X.-M., Micu, A., Mikalef, P., Mogaji, E., Pandey, N., Raman, R., Rana, N. P., Sarker, P., Sharma, A., … Wong, L.-W. (2025). The potential of generative artificial intelligence across disciplines: Perspectives and future directions. Journal of Computer Information Systems, 65(1), 76–107. https://doi.org/10.1080/08874417.2023.2261010

Rapini, M. S., & Rocha, B. P. (2014). Bancos de desenvolvimento e o financiamento da inovação [Development banks and the financing of innovation]. Caderno Econômico BDMG, (2), 7–58. https://www.bdmg.mg.gov.br/wp-content/uploads/2018/10/BDMG-Caderno-Econ%C3%B4mico-Dezembro-2014-N%C2%B0-2.pdf

Scala da Rocha, L., & De Oliveira Matias, Í. (2026). Industry 4.0 research in emerging economies: A bibliometric comparison of Brazil and globally leading countries. Journal of Technology Management & Innovation, 21(1), 112–125. https://doi.org/10.4067/S0718-27242026000100112

Schumpeter, J. A. (1934). The theory of economic development: An inquiry into profits, capital, credit, interest, and the business cycle (R. Opie, Trans.). Harvard University Press.

Topsakal, O., & Akinci, T. C. (2023). Creating large language model applications utilizing LangChain: A primer on developing LLM apps fast. Proceedings of the 5th International Conference on Applied Engineering and Natural Sciences (ICAENS), 1050–1056. https://doi.org/10.59287/icaens.1127

Valmeekam, K., Marquez, M., Olmo, A., Sreedharan, S., & Kambhampati, S. (2023). PlanBench: An extensible benchmark for evaluating large language models on planning and reasoning about change. Advances in Neural Information Processing Systems, 36, 38975–38987. https://proceedings.neurips.cc/paper_files/paper/2023/hash/7a92bcdede88c7afd108072faf5485c8-Abstract-Datasets_and_Benchmarks.html

Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, Ł., & Polosukhin, I. (2017). Attention is all you need. Advances in Neural Information Processing Systems, 30. https://proceedings.neurips.cc/paper/2017/hash/3f5ee243547dee91fbd053c1c4a845aa-Abstract.html

Wang, L., Ma, C., Feng, X., Zhang, Z., Yang, H., Zhang, J., Chen, Z., Tang, J., Chen, X., Lin, Y., Zhao, W. X., Wei, Z., & Wen, J. (2024). A survey on large language model based autonomous agents. Frontiers of Computer Science, 18(6), Article 186345. https://doi.org/10.1007/s11704-024-40231-1

Wooldridge, M. (2009). An introduction to multiagent systems (2nd ed.). John Wiley & Sons.

Wu, Q., Bansal, G., Zhang, J., Wu, Y., Li, B., Zhu, E., Jiang, L., Zhang, X., Zhang, S., Liu, J., Awadallah, A. H., White, R. W., Burger, D., & Wang, C. (2024). AutoGen: Enabling next-gen LLM applications via multi-agent conversations. Proceedings of the 1st Conference on Language Modeling (COLM). https://openreview.net/forum?id=BAakY1hNKS

Xi, Z., Chen, W., Guo, X., He, W., Ding, Y., Hong, B., Zhang, M., Wang, J., Jin, S., Zhou, E., Zheng, R., Fan, X., Wang, X., Xiong, L., Zhou, Y., Wang, W., Jiang, C., Zou, Y., Liu, X., … Gui, T. (2023). The rise and potential of large language model based agents: A survey. arXiv. https://doi.org/10.48550/arXiv.2309.07864