Large Language Models in Trading: Models and Market Dynamics

Trading with LLMs: Models, Agents, and Risks

Author

Nam Nguyen
April 05, 2026 • Estimated Reading Time: 9 minutes

I just returned from a two-day conference in New York, FutureAlpha (formerly QuantStrats). This year, the theme focused largely on data, machine learning, and AI. While some speakers were very enthusiastic about the potential of AI to generate alpha, our panel was more conservative. The consensus among the panelists was to use ML and AI to enhance and improve risk management. Along this theme, in this edition, I discuss the use of generative AI in trading.

In this issue:

Latest Posts

  • Evaluating Option-Based Strategies and Dollar-Cost Averaging (10 min)

  • Machine Learning for Derivative Pricing and Crash Prediction (12 min)

  • Do Options Exhibit Momentum? (10 min)

  • Herding in Commodities and Cryptocurrencies (10 min)

  • Modern Pairs Trading: What Still Works and Why (10 min)

Integrating Structured and Unstructured Data with LLMs and RAG

Traditional quantitative methods often rely on structured data, such as time series. With the emergence of Large Language Models (LLMs), it is now possible to process unstructured data. A new line of research focuses on integrating unstructured data analysis into traditional frameworks.

Along this line, Reference [1] proposed the use of LLMs together with retrieval-augmented generation (RAG) to process both structured and unstructured data concurrently. Specifically, the authors developed a system that first applies LLMs to detect regime shifts using time-series techniques, then employs RAG to integrate external knowledge into the model’s decision-making process. By retrieving relevant information from a vector database and combining it with the model’s capabilities, RAG improves both the interpretability and effectiveness of trading strategies.

Findings

  • The paper studies methods for fine-tuning open-source Large Language Models to enhance quantitative trading strategies.

  • It integrates numerical data, such as prices and technical indicators, with textual data, including news and sentiment.

  • The approach uses Retrieval-Augmented Generation with a vector database to process and contextualize textual information.

  • The study focuses on fully fine-tuning smaller models to achieve cost efficiency and scalability.

  • It proposes a hybrid framework that combines LLM capabilities with traditional quantitative methods.

  • The framework incorporates real-time data pipelines and adaptive model tuning.

  • The results show improvements in predictive accuracy and risk-adjusted returns.

  • The integration of multimodal data helps address challenges in combining structured and unstructured information.

  • Fine-tuned smaller models improve regime detection and trading decision accuracy while maintaining efficiency.

  • Additional techniques enhance model performance and robustness, supporting practical applications in quantitative finance.

In short, incorporating RAG into the framework enhances the model’s ability to understand complex macroeconomic environments and adapt trading strategies as conditions evolve. Experimental results show significant gains in predictive accuracy and risk-adjusted returns, demonstrating the practical value of these fine-tuning methods in finance.

Reference

[1] Li, C., Chan, C.H.R., Huang, S.H., Choi, P.M.S. (2025). Integrating LLM-Based Time Series and Regime Detection with RAG for Adaptive Trading Strategies and Portfolio Management. In: Choi, P.M.S., Huang, S.H. (eds) Finance and Large Language Models. Blockchain Technologies. Springer, Singapore.

Can AI Trade? Modeling Investors with Large Language Models

The previous paper focuses on improving trading performance by integrating LLMs with quantitative models and data, while another line of research explores how LLMs behave as autonomous agents within market environments.

Reference [2] utilized LLMs to construct trading agents in the financial markets. Specifically, the author used LLMs to emulate various types of investors: value investors, momentum traders, market makers, retail traders, etc.

Findings

  • The paper develops a simulated stock market in which large language models act as heterogeneous trading agents.

  • The framework includes realistic market features such as an order book, market and limit orders, partial fills, dividends, and equilibrium clearing.

  • Agents operate with different strategies, information sets, and endowments, and communicate decisions using structured outputs while explaining reasoning in natural language.

  • The results show that LLMs can consistently follow instructions and implement strategies such as value investing, momentum trading, and market making.

  • LLM agents process market information and respond meaningfully to prices, dividends, and historical data.

  • The simulated market exhibits realistic dynamics, including price discovery, bubbles, underreaction, and liquidity provision.

  • The framework enables controlled analysis of agent behavior under different market conditions, similar to interpretability methods in machine learning.

  • It provides a cost-effective way to test financial theories that lack closed-form solutions.

  • The study highlights that LLM behavior is highly sensitive to prompts, which can lead to correlated actions across agents.

  • This correlation may amplify volatility and introduce systemic risks, emphasizing the need for careful testing before real-world deployment.

In short, the article concluded that trading strategies generated by large language models are effective, but could introduce new systemic risks to financial markets because these agents would act in a correlated manner.

Reference

Closing Thoughts

In this issue, the discussion highlights two complementary directions in applying LLMs to finance. On one hand, integrating LLMs with quantitative models and multimodal data can improve predictive accuracy and risk-adjusted returns. On the other hand, treating LLMs as autonomous trading agents reveals how their behavior can shape market dynamics, including liquidity, price discovery, and potential instability. Taken together, the results suggest that while LLMs offer meaningful opportunities in trading and risk management, their impact depends critically on implementation, prompting, and control of system-wide behavior.

Additional Reading

For further discussion on gen AI, please refer to previous issues:

Educational Video

Generative AI for Trading and Asset Management" with Dr. Hamlet Medina and Dr. Ernest Chan

In this discussion, Drs Medina and Chan introduce generative AI as a new framework for quantitative finance, emphasizing that its core capability lies in modeling high-dimensional data distributions rather than simply producing predictions. They explain that, unlike traditional machine learning, which focuses on conditional relationships, generative AI enables the integration of structured and unstructured data, including text, news, and alternative data sources, into trading workflows. This allows practitioners to extract signals more efficiently, perform forecasting, generate synthetic data, and enhance feature representation, lowering the barrier to entry for incorporating complex data into trading strategies.

At the same time, they highlight important limitations and practical considerations. While generative AI is useful for tasks such as summarizing research, generating code, and improving productivity, its outputs can be unreliable, particularly for precise numerical computations. A key conceptual shift is the move toward modeling joint data distributions, which enables better handling of uncertainty, anomaly detection, and reduced reliance on large labeled datasets. The discussion also emphasizes validation challenges, including the use of synthetic data and the need for robust evaluation frameworks, reinforcing that effective application in trading depends not only on model capability but also on careful implementation and risk control.

Around the Quantosphere

  • Goldman Sachs: Hedge Fund Performance Slumps, Worst in 4 Years (idnfinancials)

  • He Turned Down Ken Griffin to Run His Own Fund. That Was $20 Billion Ago. (wsj)

  • The Dawn of Hedge Agents: How Agentic AI Is Transforming Hedge Fund Operations (sify)

  • Multistrategy Hedge Funds’ 2025 Hiring (and Firing) Laid Bare in ADV Filings (efinancialcareers)

  • As stocks and bonds fall, and oil hits $100, a futures trade that boomed in 2022 may again be a winner (cnbc)

  • Distressed-debt funds target private credit downturn as ‘greatest opportunity’ since 2008 (ft)

  • Podcast: AI Is Being Built to Replace You, Not Help You (bloomberg)

Disclaimer

This newsletter is not investment advice. It is provided solely for entertainment and educational purposes. Always consult a financial professional before making any investment decisions.

We are not responsible for any outcomes arising from the use of the content and codes provided in the outbound links. By continuing to read this newsletter, you acknowledge and agree to this disclaimer.