FinAnalytics: A Survey of Coordinated and Self-Validating Multi-Agent Language-Model Systems for Financial Analysis

Author

Sahil S. Patil, Prabhleen Kaur , Anurag Sutar

Abstract

 Financial analysis draws on several kinds of source, including filings, earnings calls, news, and market data, but the tools that analyse them are separate, so analysts reconcile sentiment, event, fundamental, risk, and forecasting signals by hand. This survey reviews ten core studies (2019–2025) and 32 supporting works on financial language models, event extraction, sentiment-driven forecasting, risk assessment, multi-criteria company ranking, and multi-agent LLM systems. We propose a five-dimensional taxonomy and compare the core studies across eight analytical capabilities. Most of them address one or two tasks in isolation, and in our reading none uses confidence scoring to reconcile conflicting outputs across components. We identify six research gaps and describe how FinAnalytics, a metacognitive multi-agent platform with a Confidence & Safety Checker, answers each one through its architecture, data design, requirements, and evaluation plan. The paper ends with applications, open challenges, best practices, and a roadmap.

Keywords

Financial Intelligence, Multi-Agent Systems, Metacognition, Sentiment Analysis, FinBERT, Stock Forecasting, Risk Assessment, Explainable AI, Literature Review

Full Text:

Download Paper PDF

References

[1] Z. Liu, D. Huang, K. Huang, Z. Li, and J. Zhao, “FinBERT: A Pre-trained Financial Language Representation Model for Financial Text Mining,” in Proc. IJCAI, 2020.

[2] Y. Xiao, E. Sun, D. Luo, and W. Wang, “TradingAgents: Multi-Agents LLM Financial Trading Framework,” MARW Workshop, AAAI, 2025.

[3] L. Ein-Dor et al., “Financial Event Extraction Using Wikipedia-Based Weak Supervision,” in Proc. ECONLP, ACL, 2019, pp. 10–15.

[4] S. Gite, H. Khatavkar, K. Kotecha, S. Srivastava, P. Maheshwari, and N. Pandey, “Explainable Stock Prices Prediction from Financial News Articles Using Sentiment Analysis,” PeerJ Computer Science, vol. 7, 2021.

[5] T. Sidogi, R. Mbuvha, and T. Marwala, “Stock Price Prediction Using Sentiment Analysis,” in Proc. IEEE SMC, 2021, pp. 46–51.

[6] Y. Sun and J. Li, “Deep Learning for Intelligent Assessment of Financial Investment Risk Prediction,” Computational Intelligence and Neuroscience, 2022, Art. 3062566.

[7] K. F. Liew, W. S. Lam, and W. H. Lam, “Financial Network Analysis on the Performance of Companies Using Integrated Entropy–DEMATEL–TOPSIS Model,” Entropy, vol. 24, no. 8, p. 1056, 2022.

[8] A. Garlapati et al., “Stock Price Prediction Using Facebook Prophet and ARIMA Models,” in Proc. 6th Int. Conf. Convergence in Technology (I2CT), IEEE, 2021, pp. 1–7.

[9] M. Muthivhi and T. L. van Zyl, “Fusion of Sentiment and Asset Price Predictions for Portfolio Optimization,” in Proc. 25th Int. Conf. Information Fusion (FUSION), IEEE, 2022, pp. 1–8.

[10] K. Du, Y. Zhao, R. Mao, F. Xing, and E. Cambria, “Natural Language Processing in Finance: A Survey,” Information Fusion, vol. 115, 102755, 2025.

[11] J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, “BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding,” in Proc. NAACL-HLT, 2019.

[12] V. Sanh, L. Debut, J. Chaumond, and T. Wolf, “DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter,” arXiv:1910.01108, 2019.

[13] D. Araci, “FinBERT: Financial Sentiment Analysis with Pre-trained Language Models,” arXiv:1908.10063, 2019.

[14] P. Malo, A. Sinha, P. Korhonen, J. Wallenius, and P. Takala, “Good Debt or Bad Debt: Detecting Semantic Orientations in Economic Texts,” J. Assoc. Inf. Sci. Technol., vol. 65, no. 4, 2014.

[15] S. J. Taylor and B. Letham, “Forecasting at Scale,” The American Statistician, vol. 72, no. 1, pp. 37–45, 2018.

[16] S. Hochreiter and J. Schmidhuber, “Long Short-Term Memory,” Neural Computation, vol. 9, no. 8, pp. 1735–1780, 1997.

[17] M. T. Ribeiro, S. Singh, and C. Guestrin, “‘Why Should I Trust You?’: Explaining the Predictions of Any Classifier,” in Proc. ACM KDD, 2016.

[18] S. Wu et al., “BloombergGPT: A Large Language Model for Finance,” arXiv:2303.17564, 2023.

[19] H. Yang, X.-Y. Liu, and C. D. Wang, “FinGPT: Open-Source Financial Large Language Models,” arXiv:2306.06031, 2023.

[20] P. Lewis et al., “Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks,” in Proc. NeurIPS, 2020.

[21] N. Shinn et al., “Reflexion: Language Agents with Verbal Reinforcement Learning,” in Proc. NeurIPS, 2023.

[22] Q. Wu et al., “AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation,” arXiv:2308.08155, 2023.

[23] S. Hong et al., “MetaGPT: Meta Programming for a Multi-Agent Collaborative Framework,” in Proc. ICLR, 2024.

[24] G. E. P. Box, G. M. Jenkins, and G. C. Reinsel, Time Series Analysis: Forecasting and Control. Wiley.

[25] C.-L. Hwang and K. Yoon, Multiple Attribute Decision Making: Methods and Applications. Springer, 1981.

[26] W. F. Sharpe, “The Sharpe Ratio,” J. Portfolio Management, vol. 21, no. 1, pp. 49–58, 1994.

[27] A. Vaswani et al., “Attention Is All You Need,” in Proc. NIPS, 2017.

[28] L. Loukas et al., “EDGAR-CORPUS: Billions of Tokens Make the World Go Round,” in Proc. ECONLP, 2021.

[29] M. Maia et al., “WWW’18 Open Challenge: Financial Opinion Mining and Question Answering,” in Companion Proc. The Web Conf., 2018.

[30] J. Wei et al., “Chain-of-Thought Prompting Elicits Reasoning in Large Language Models,” in Proc. NeurIPS, 2022.

[31] C. Guo, G. Pleiss, Y. Sun, and K. Q. Weinberger, “On Calibration of Modern Neural Networks,” in Proc. ICML, 2017.

[32] J. H. Flavell, “Metacognition and Cognitive Monitoring: A New Area of Cognitive–Developmental Inquiry,” American Psychologist, vol. 34, no. 10, pp. 906–911, 1979.

[33] Y. Li, S. Wang, H. Ding, and H. Chen, “Large Language Models in Finance: A Survey,” in Proc. 4th ACM Int. Conf. AI in Finance (ICAIF), 2023.

[34] O. B. Sezer, M. U. Gudelek, and A. M. Ozbayoglu, “Financial Time Series Forecasting with Deep Learning: A Systematic Literature Review: 2005–2019,” Applied Soft Computing, vol. 90, 2020.

[35] A. K. Nassirtoussi, S. Aghabozorgi, T. Y. Wah, and D. C. L. Ngo, “Text Mining for Market Prediction: A Systematic Review,” Expert Systems with Applications, vol. 41, no. 16, pp. 7653–7670, 2014.

[36] Z. Xi et al., “The Rise and Potential of Large Language Model Based Agents: A Survey,” arXiv:2309.07864, 2023.

[37] L. Wang et al., “A Survey on Large Language Model based Autonomous Agents,” Frontiers of Computer Science, vol. 18, 2024 (arXiv:2308.11432).

[38] W. X. Zhao et al., “A Survey of Large Language Models,” arXiv:2303.18223, 2023.

[39] H. Markowitz, “Portfolio Selection,” The Journal of Finance, vol. 7, no. 1, pp. 77–91, 1952.

[40] S. Yao et al., “ReAct: Synergizing Reasoning and Acting in Language Models,” in Proc. ICLR, 2023.

[41] E. F. Fama, “Efficient Capital Markets: A Review of Theory and Empirical Work,” The Journal of Finance, vol. 25, no. 2, pp. 383–417, 1970.

[42] T. Loughran and B. McDonald, “When Is a Liability Not a Liability? Textual Analysis, Dictionaries, and 10-Ks,” The Journal of Finance, vol. 66, no. 1, pp. 35–65, 2011.

 

 

Share your valuable work from Social Media Buttons