LLM-Based multi-agent system for individual investment in energy and natural resources

• Autorzy: Zaleski Alexander , Chudziak Jaroslaw A.

Identyfikatory

DOI

10.24425/ijet.2025.153538

• Języki publikacji: EN

Abstrakty

EN

Recent advancements in large language models and multiagent large language model based systems show that these technologies can be applied to a large number of problems. They can automate complex tasks and perform advanced analyses that would take an expert a significant amount of time. This article describes a multiagent large language model (LLM) based platform for investment advisory in the energy natural resources sector. The system integrates multiple types of investment analyses e.g. technical analysis, fundamental analysis, sentiment analysis and stock price prediction. The approach of integrating multiple types of analyses in one system allows the investor to save significant amount of time on analyzing potential investments.

Słowa kluczowe

EN

Multiagent systems; Energy Minerals Market; Investment Advisory System; Autonomous LLM Agents; LangGraph

• Wydawca: Polish Academy of Sciences, Committee of Electronics and Telecommunication
• Czasopismo: International Journal of Electronics and Telecommunications
• Rocznik: 2025
• Tom: Vol. 71, No. 1
• Strony: 11--18
• Opis fizyczny: Bibliogr. 33 poz., tab., rys.

Twórcy

autor

Zaleski Alexander

• Warsaw University of Technology

autor

Chudziak Jaroslaw A.

• Warsaw University of Technology

• https://orcid.org/0000-0003-4534-8652

Bibliografia

• [1] L. Schernikau, Economics of the International Coal Trade. Springer, 2017.
• [2] D. W. Edwards, Energy Trading and Investing: Trading, Risk Management and Structuring Deals in the Energy Market. McGraw-Hill Education, 2009.
• [3] G. E. Peter Zweifel, Aaron Praktiknjo, Energy Economics. Springer, 2017.
• [4] S. Watkins, The Complete Guide To Global Oil Market Trading. AD-VFN Books, 2021.
• [5] M. Chrascina, M. VAN ˇEK, and K. Pekarˇcíková, “Intrinsic value of stocks of “big oil” companies,” GeoScience Engineering, vol. 70, pp. 67–77, 06 2024.
• [6] M. Ezeh, A. Ogbu, A. H. Ikevuje, and E. George, “Optimizing risk management in oil and gas trading: A comprehensive analysis,” International Journal of Applied Research in Social Sciences, vol. 6, pp. 1461–1480, 07 2024.
• [7] S. Obadi and M. Korcek, “The crude oil price and speculations: Inves-tigation using granger causality test,” International Journal of Energy Economics and Policy, vol. 8, pp. 275–282, 05 2018.
• [8] A. Sakkas and N. Tessaromatis, “Factor based commodity investing,” Journal of Banking & Finance, vol. 115, p. 105807, 2020. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S0378426620300741
• [9] TradingView, “Tradingview,” 2024, accessed: 2024-11-25. [Online]. Available: https://www.tradingview.com/
• [10] S. C. Bhattacharyya, Energy Economics. Springer London, 2011.
• [11] Y. Yang, Q. Peng, J. Wang, and W. Zhang, “Multi-llm-agent systems: Techniques and business perspectives,” 11 2024.
• [12] D. H. Hagos, R. Battle, and D. B. Rawat, “Recent advances in generative ai and large language models: Current status, challenges, and perspec-tives,” IEEE transactions on artificial intelligence, pp. 1–21, 2024.
• [13] M. Wawer, J. A. Chudziak, and E. Niewiadomska-Szynkiewicz, “Large language models and the elliott wave principle: A multi-agent deep learning approach to big data analysis in financial markets,” Applied Sciences, vol. 14, no. 24, 2024.
• [14] J. J. Murphy, Technical Analysis of the Financial Markets: A Compre-hensive Guide to Trading Methods and Applications. New York Institute of Finance, 1999.
• [15] R. S. Pindyck, “Volatility and commodity price dynamics,” The journal of futures markets, vol. 24, no. 11, pp. 1029–1047, 2004.
• [16] G. News, “Crude oil news search results,” 2024, accessed: 2024-11-09. [Online]. Available: https://www.google.com/search?q=crude+oil&tbm=nws
• [17] X. Huang, W. Liu, X. Chen, X. Wang, H. Wang, D. Lian, Y. Wang, R. Tang, and E. Chen, “Understanding the planning of llm agents: A survey,” 2024. [Online]. Available: https://arxiv.org/abs/2402.02716
• [18] S. Yao, J. Zhao, D. Yu, N. Du, I. Shafran, K. Narasimhan, and Y. Cao, “React: Synergizing reasoning and acting in language models,” 2023. [Online]. Available: https://arxiv.org/abs/2210.03629
• [19] M. Mäntylä, D. Graziotin, and M. Kuutila, “The evolution of sentiment analysis - a review of research topics, venues, and top cited papers,” Computer Science Review, vol. 27, 12 2016.
• [20] D. Araci, “Finbert: Financial sentiment analysis with pre-trained language models,” 2019. [Online]. Available: https://arxiv.org/abs/1908.10063
• [21] I. K. Nti, A. F. Adekoya, and B. A. Weyori, “A systematic review of fundamental and technical analysis of stock market predictions,” The Artificial intelligence review, vol. 53, no. 4, pp. 3007–3057, 2020.
• [22] T. Koller, M. Goedhart, and D. Wessels, Valuation: Measuring and Managing the Value of Companies. Wiley, 2020.
• [23] LangGraph, “Langgraph: Multi-agent systems concepts,” 2024, accessed: 2024-12-01. [Online]. Available: https://langchain-ai.github.io/langgraph/concepts/multi_agent/
• [24] K. L. Szydlowski and J. A. Chudziak, “Transformer-style neural network in stock price forecasting,” in Proceedings of the 21th International Conference on Modeling Decisions for Artificial Intelligence (MDAI 2024), Tokyo, Japan, 2024.
• [25] F. Bańka and J. A. Chudziak, “Applying informer for option pricing: A transformer-based approach,” in Proceedings of the 17th International Conference on Agents and Artificial Intelligence (ICAART 2025). SciTePress, 2025, pp. 1270–1277.
• [26] H. Face, “Transformers agents: Tools and capabilities,” 2024, accessed: 2024-11-30. [Online]. Available: https://huggingface.co/docs/transformers/agents#tools
• [27] K. L. Szydlowski and J. A. Chudziak, “Toward predictive stock trading with hidformer integrated into reinforcement learning strategy,” in Proceedings of the 36th International Conference on Tools for Artificial Intelligence (ICTAI 2024), Herndon, VA, USA, 2024.
• [28] X. Li, S. Wang, S. Zeng, Y. Wu, and Y. Yang, “A survey on llm-based multi-agent systems: workflow, infrastructure, and challenges,” Vicinagearth, vol. 1, no. 1, 2024.
• [29] J. A. Chudziak and M. Wawer, “Elliottagents: A natural language-driven multi-agent system for stock market analysis and prediction,” in Proceedings of the 38th Pacific Asia Conference on Language, Information and Computation, Tokyo, Japan, 2024.
• [30] V. Ekambaram, A. Jati, P. Dayama, S. Mukherjee, N. H. Nguyen, W. M. Gifford, C. Reddy, and J. Kalagnanam, “Tiny time mixers (ttms): Fast pre-trained models for enhanced zero/few-shot forecasting of multivariate time series,” 2024. [Online]. Available: https://arxiv.org/abs/2401.03955
• [31] LangChain, “Langgraph,” 2024, accessed: 2024-11-13. [Online]. Available: https://www.langchain.com/langgraph
• [32] J. E. Laird, The Soar Cognitive Architecture. The MIT Press, 2019.
• [33] OpenAI, “Chatgpt,” 2024, accessed: 2024-12-01. [Online]. Available: https://openai.com/chatgpt