Towards Autonomous Analysis in Finance: A Modular and Extensible Architecture for LLM-Based AI Agents

Hakan Kaya

doi:10.21541/apjess.1812322

Towards Autonomous Analysis in Finance: A Modular and Extensible Architecture for LLM-Based AI Agents

Abstract

The complexity and dynamics of financial markets make it difficult for investors and researchers to make decisions. In this regard, this research proposes an AI-based Financial Data Analysis and Reporting Assistant that incorporates technical analysis, fundamental analysis, and news-based sentiment analysis for stock and exchange-traded fund (ETF) analysis. Built with real-time information from Google Gemini 2.0 Flash, it uses a three-node structure based on LangGraph (Chatbot Node, Tools Node, and Human Node) and Yahoo Finance API to create user-directed reports with a platform that supports conversation mode. Core components of this system include caching of data, technical analysis elements (RSI, MACD, Bollinger Bands), key financial ratios, news analysis with BeautifulSoup for news-associated information, and data representation with Plotly graphs. The performance of this system for AAPL and TUPRS.IS stocks show its ability to correctly operate in global and local financial markets with proper upholding of ethical principles by not giving investment recommendations. The findings highlight the system's ability to process multilingual data, mitigate hallucinations through context awareness, and provide holistic financial decision support. Limitations include dependence on third-party APIs and potential data delays. The work contributes to the field of financial AI by filling gaps in integrated and conversational systems and provides a modular framework for future predictive analytics and multi-asset portfolio development.

Keywords

References

M. F. Dixon, I. Halperin, and P. Bilokon, Machine Learning in Finance, vol. 1170, New York, NY, USA: Springer International Publishing, 2020.
Y. Li, S. Wang, H. Ding, and H. Chen, “Large language models in finance: A survey,” in Proc. 4th ACM Int. Conf. AI Finance, 2023, pp. 374–382, doi: 10.1145/3604237.3626869.
K. Du, F. Xing, R. Mao, and E. Cambria, “Financial sentiment analysis: Techniques and applications,” ACM Comput. Surveys, vol. 56, no. 9, pp. 1–42, 2024, doi: 10.1145/3649451.
M. A. A. Ballesteros and E. A. M. Miranda, “Stock market forecasting using a neural network through fundamental indicators, technical indicators and market sentiment analysis,” Comput. Econ., vol. 66, no. 2, pp. 1715–1745, 2025, doi: 10.1007/s10614-024-10711-4.
R. Gómez-Martínez, M. L. Medrano-García, D. López-López, and J. Torres-Pruñonosa, “How sentiment indicators improve algorithmic trading performance,” SAGE Open, vol. 15, no. 3, 2025, doi: 10.1177/21582440251369559.
L. Lu, “Technical indicator networks (TINs): An interpretable neural architecture modernizing classical technical analysis for adaptive algorithmic trading,” arXiv preprint arXiv:2507.20202, 2025, doi: 10.48550/arXiv.2507.20202.
Y. Kim, S. Yoo, and S. Park, “A rule-based stock trading recommendation system using sentiment analysis and technical indicators,” Electronics, vol. 14, p. 773, 2025, doi: 10.3390/electronics14040773.
S. Joshi, “A comprehensive review of Gen AI agents: Applications and frameworks in finance, investments and risk domains,” Int. J. Innov. Sci. Res. Technol., pp. 1339–1355, 2025, doi: 10.38124/ijisrt/25may964.

X. Han, N. Wang, S. Che, H. Yang, K. Zhang, and S. X. Xu, “Enhancing investment analysis: Optimizing AI-agent collaboration in financial research,” in Proc. 5th ACM Int. Conf. AI Finance, 2024, pp. 538–546, doi: 10.1145/3677052.3698645.
G. M. Vital, D. Fernandes, M. Fernandes, and F. Soares, “A vision on sentiment analysis and other AI applications on investments portfolio optimization,” in Proc. IEEE 49th Annu. Comput., Softw., Appl. Conf. (COMPSAC), 2025, pp. 1899–1904, doi: 10.1109/COMPSAC65507.2025.00261.
A. G. Olanrewaju, A. O. Dada, E. Alade, F. Jingo, and R. N. Akalia, “Financial forecasting and behavioral analysis: The role of machine learning in predicting stock market trends and investor decisions,” J. Front. Multidiscip. Res., vol. 5, no. 1, pp. 325–343, 2024, doi: 10.54660/.IJFMR.2024.5.1.325-343.
M. S. Muzaffar et al., “Existing techniques for fundamental, technical and sentimental analysis for stock investment,” in Proc. Int. Conf. Elect. Electron. Comput. Technol. (ICEECT), vol. 1, 2024, pp. 1–7, doi: 10.1109/ICEECT61758.2024.10739294.
J. Braun, J. Hausler, and W. Schäfers, “Artificial intelligence, news sentiment, and property market liquidity,” J. Prop. Invest. Finance, vol. 38, no. 4, pp. 309–325, 2020, doi: 10.1108/JPIF-08-2019-0100.
M. S. Amin et al., “Harmonizing macro-financial factors and Twitter sentiment analysis in forecasting stock market trends,” J. Comput. Sci. Technol. Stud., vol. 6, no. 1, pp. 58–67, 2024, doi: 10.32996/jcsts.2024.6.1.7.
D. P. de Jesus, E. H. O. de Medeiros, L. L. Godeiro, and A. L. Proque, “Forecasting Brazilian stock market using sentiment indices from textual data, Chat-GPT-based and technical indicators,” Comput. Econ., pp. 1–46, 2025, doi: 10.1007/s10614-024-10835-7.
L. Mazzilli, “Forecasting global financial crises through AI-enhanced sentiment and economic signals,” SSRN Electron. J., 2025, doi: 10.2139/ssrn.5376944.
H. Yang et al., “Finrobot: An open-source AI agent platform for financial applications using large language models,” arXiv preprint arXiv:2405.14767, 2024, doi: 10.48550/arXiv.2405.14767.
Y. Nie et al., “A survey of large language models for financial applications: Progress, prospects and challenges,” arXiv preprint arXiv:2406.11903, 2024, doi: 10.48550/arXiv.2406.11903.
E. Kasneci et al., “ChatGPT for good? On opportunities and challenges of large language models for education,” Learn. Individ. Differ., vol. 103, p. 102274, 2023, doi: 10.1016/j.lindif.2023.102274.
A. T. Khan, S. Li, and X. Cao, “Bridging finance and AI: A comprehensive survey of large language models in financial systems,” Digit. Finance, pp. 1–23, 2025, doi: 10.1007/s42521-025-00146-3.
P. M. S. Choi, S. H. Huang, and Q. Wang, “Large language models in finance: An overview,” in Finance and Large Language Models, pp. 1–26, 2025, doi: 10.1007/978-981-96-5833-6_1.
D. Krause, “Large language models and generative AI in finance: An analysis of ChatGPT, Bard, and Bing AI,” SSRN Electron. J., Jul. 2023, doi: 10.2139/ssrn.4511540.
V. Mavroudis, “LangChain,” Preprints, Nov. 2024, doi: 10.20944/preprints202411.0566.v1.
J. Huang et al., “Open-finllms: Open multimodal large language models for financial applications,” arXiv preprint arXiv:2408.11878, 2024, doi: 10.48550/arXiv.2408.11878.
A. Biswas and W. Talukdar, Building Agentic AI Systems: Create Intelligent, Autonomous AI Agents that can Reason, Plan, and Adapt, Birmingham, U.K.: Packt Publishing Ltd., 2025.
J. Chen et al., “When large language models meet personalization: Perspectives of challenges and opportunities,” World Wide Web, vol. 27, no. 4, p. 42, 2024, doi: 10.1007/s11280-024-01276-1.
J. Lee, N. Stevens, and S. C. Han, “Large language models in finance (finllms),” Neural Comput. Appl., pp. 1–15, 2025, doi: 10.1007/s00521-024-10495-6.
Z. Wang, Z. Hu, F. Li, S. B. Ho, and E. Cambria, “Learning-based stock trending prediction by incorporating technical indicators and social media sentiment,” Cogn. Comput., vol. 15, no. 3, pp. 1092–1102, 2023, doi: 10.1007/s12559-023-10125-8.

Details

Primary Language

English

Subjects

Software Engineering (Other)

Journal Section

Research Article

Authors

Hakan Kaya ^*
0000-0002-0812-4839
Türkiye

Publication Date

May 31, 2026

Submission Date

October 28, 2025

Acceptance Date

January 14, 2026

Published in Issue

Year 2026 Volume: 14 Number: 2

DOI

https://doi.org/10.21541/apjess.1812322

IZ

https://izlik.org/JA77MM52WA

Cite

RIS / Bibtex

APA

Kaya, H. (2026). Towards Autonomous Analysis in Finance: A Modular and Extensible Architecture for LLM-Based AI Agents. Academic Platform Journal of Engineering and Smart Systems, 14(2), 76-84. https://doi.org/10.21541/apjess.1812322

AMA

1.Kaya H. Towards Autonomous Analysis in Finance: A Modular and Extensible Architecture for LLM-Based AI Agents. APJESS. 2026;14(2):76-84. doi:10.21541/apjess.1812322

Chicago

Kaya, Hakan. 2026. “Towards Autonomous Analysis in Finance: A Modular and Extensible Architecture for LLM-Based AI Agents”. Academic Platform Journal of Engineering and Smart Systems 14 (2): 76-84. https://doi.org/10.21541/apjess.1812322.

EndNote

Kaya H (May 1, 2026) Towards Autonomous Analysis in Finance: A Modular and Extensible Architecture for LLM-Based AI Agents. Academic Platform Journal of Engineering and Smart Systems 14 2 76–84.

IEEE

[1]H. Kaya, “Towards Autonomous Analysis in Finance: A Modular and Extensible Architecture for LLM-Based AI Agents”, APJESS, vol. 14, no. 2, pp. 76–84, May 2026, doi: 10.21541/apjess.1812322.

ISNAD

Kaya, Hakan. “Towards Autonomous Analysis in Finance: A Modular and Extensible Architecture for LLM-Based AI Agents”. Academic Platform Journal of Engineering and Smart Systems 14/2 (May 1, 2026): 76-84. https://doi.org/10.21541/apjess.1812322.

JAMA

1.Kaya H. Towards Autonomous Analysis in Finance: A Modular and Extensible Architecture for LLM-Based AI Agents. APJESS. 2026;14:76–84.

MLA

Kaya, Hakan. “Towards Autonomous Analysis in Finance: A Modular and Extensible Architecture for LLM-Based AI Agents”. Academic Platform Journal of Engineering and Smart Systems, vol. 14, no. 2, May 2026, pp. 76-84, doi:10.21541/apjess.1812322.

Vancouver

1.Hakan Kaya. Towards Autonomous Analysis in Finance: A Modular and Extensible Architecture for LLM-Based AI Agents. APJESS. 2026 May 1;14(2):76-84. doi:10.21541/apjess.1812322