An LLMs-Enhanced Multi-Agent Feedback Modeling Framework for Intelligent Public Funding Allocation_Vol. 4 No. 1 (JBDC 2026)_Journal of Big Data and Computing (ISSN: 2959-0590)

Home > Journal of Big Data and Computing (ISSN: 2959-0590) > Vol. 4 No. 1 (JBDC 2026) >

An LLMs-Enhanced Multi-Agent Feedback Modeling Framework for Intelligent Public Funding Allocation

DOI: https://doi.org/10.62517/jbdc.202601111

Author(s)

Junqiao Gong1, Jiaxiao Wang2, Gang Wang1, Jian Ma2*, Xuansong Tam3

Affiliation(s)

1School of Management, Hefei University of Technology, Hefei, China, 2Department of Information Systems, City University of Hong Kong, Hong Kong, China, 3Department of Economics and Finance, City University of Hong Kong, Hong Kong, China *Corresponding Author

Abstract

With the continuous improvement of e-government platforms and the rapid development of artificial intelligence technology, an innovative, government-led model for public funding allocation has emerged, which achieves precise allocation of public fundings through automatic filling of application forms and intelligent verification of enterprise qualifications. However, existing studies still lacks systematic modeling of the implementation mechanism of this public fund allocation model. In response to the inherent complexity of the operating logic of this model and the multi-source heterogeneity of policy texts and enterprise data, this paper innovatively proposes a large language models-based multi-agent feedback modeling framework for intelligent public funding allocation. This method consists of three core intelligent agents: the policy agent, enterprise agent, and matching agent. Among them, the policy agent is responsible for parsing policy texts and simulating government decision-making processes. The enterprise agent automatically generates funding application forms by integrating structured and unstructured enterprise data. The match agent is responsible for outputting the matching results and their decision reasons. Experimental evaluation conducted on a real-world dataset confirms the efficacy and practical value of the proposed framework, demonstrating its superiority over the baseline methods.

Keywords

Public Funding Allocation; Multi-Agent Feedback Modeling; Large Language Models

References

[1] P. Aroca and P. Fierro, "Identifying gatekeepers in the allocation of public funds: a spatial econometric analysis". 2024. [2] K. Nataliia, N. Mardus, O. Davydov, V. Yevtushenko, O. Melen, and A. Kharchenko, "Devising the policy of funds allocation in the decision-making process under the budget and tax management", Eastern-European Journal of Enterprise Technologies, vol. 1, pp. 69-79, 02/28 2022. [3] W. Walters, "A Regression-based Approach to Library Fund Allocation," Library Resources & Technical Services, vol. 51, pp. 263-278, 10/01 2007. [4] L. Bower, AI Decision Making for Allocating Government Grant Funds. 2022. [5] E. Newman, "Budgeting and Fund Allocation in Higher Education in Ghana," Journal of Education and Vocational Research, vol. 4, pp. 275-286, 09/30 2013. [6] X. Su, "The allocation of public funds in a hierarchical educational system," Journal of Economic Dynamics and Control, vol. 28, no. 12, pp. 2485-2510, 2004/12/01/ 2004. [7] A. A. Talib, "Formula Based Allocation of Public Funds: The Case of Higher Education Research Funding," Public Money & Management, vol. 21, no. 1, pp. 57-64, 2001/01/01 2001. [8] B. Prasetyo and Suharjito, "Optimizing Government Funding Allocation with Ensemble Machine Learning Models," in 2024 10th International Conference on Computing, Engineering and Design (ICCED), 2024, pp. 1-5. [9] C. Reddick, "State resource allocation and budget formats: towards a hybrid model," Journal of Public Budgeting, Accounting & Financial Management, vol. 19, pp. 221-244, 03/01 2007. [10] I. BenDavid-Hadar, "Funding education: developing a method of allocation for improvement," International Journal of Educational Management, vol. 32, no. 1, pp. 2-26, 2018/01/01/ 2018. [11] Y. Wang, N. Liu, Z. Pan, and X. You, "AI-Based Resource Allocation in E2E Network Slicing with Both Public and Non-Public Slices," Applied Sciences, vol. 13, no. 22, p. 12505. [12] H. Jang, "A decision support framework for robust R&D budget allocation using machine learning and optimization," Decision Support Systems, vol. 121, pp. 1-12, 2019/06/01/ 2019. [13] C. Challoumis, "BUILDING A SUSTAINABLE ECONOMY - HOW AI CAN OPTIMIZE RESOURCE ALLOCATION," 10/17 2024. [14] S. Chen, Y. Liu, W. Han, W. Zhang, and T. Liu, "A Survey on LLM-based Multi-Agent System: Recent Advances and New Frontiers in Application," arXiv e-prints, arXiv:2412.17481, 2024. [15] J. Ma, "Research on the role of LLM in multi-agent systems: A survey," Appl. Comput. Eng, vol. 71, pp. 180-186, 2024. [16] Z. Wang, Y. Yu, W. Zheng, W. Ma, and M. Zhang, "MACRec: a Multi-Agent Collaboration Framework for Recommendation," arXiv e-prints, arXiv:2402.15235, 2024. [17] M. Valentini, "Cooperative and Competitive LLM-Based Multi-Agent Systems for Recommendation," presented at the Advances in Information Retrieval: 47th European Conference on Information Retrieval, ECIR 2025, Lucca, Italy, April 6–10, 2025, Proceedings, Part V, Lucca, Italy, 2025. [18] K.-T. Tran, D. Dao, M.-D. Nguyen, Q.-V. Pham, B. O'Sullivan, and H. D. J. a. e.-p. Nguyen, "Multi-Agent Collaboration Mechanisms: A Survey of LLMs," p. arXiv:2501.06322Accessed on: January 01, 2025. [19] S. An, Z. Ma, Z. Lin, N. Zheng, and J.-G. J. a. e.-p. Lou, "Make Your LLM Fully Utilize the Context," p. arXiv:2404.16811Accessed on: April 01, 2024. [20] J. Gong, J. Wang, G. Wang, J. Ma, and X. Tam, "An LLMs-based Multi-Agent Collaborative Framework for Intelligent Public Fund Allocation," presented at the Proceedings of the 2025 International Conference on Generative Artificial Intelligence for Business, 2025. [21] S. Cai et al., "Agentic Feedback Loop Modeling Improves Recommendation and User Simulation," p. arXiv:2410.20027Accessed on: October 01, 2024. [22] C. Gao et al., "CIRS: Bursting Filter Bubbles by Counterfactual Interactive Recommender System," vol. 42, no. 1 %J ACM Trans. Inf. Syst., p. Article 14, 2023. [23] M. A. Hearst, S. T. Dumais, E. Osuna, J. Platt, and B. Scholkopf, "Support vector machines," IEEE Intelligent Systems and their Applications, vol. 13, no. 4, pp. 18-28, 1998. [24] Y. Kim, "Convolutional Neural Networks for Sentence Classification," p. arXiv:1408.5882Accessed on: August 01, 2014. [25] J. Devlin, M.-W. Chang, K. Lee, and K. J. a. e.-p. Toutanova, "BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding," p. arXiv:1810.04805Accessed on: October 01, 2018. [26] A. Grattafiori et al., "The Llama 3 Herd of Models," p. arXiv:2407.21783Accessed on: July 01, 2024. [27] DeepSeek-AI et al., "DeepSeek-V3 Technical Report," p. arXiv:2412.19437Accessed on: December 01, 2024.