arXiv · arXiv q-fin · 2025
Large language models show promise for financial decision-making, yet deploying them as autonomous trading agents raises fundamental challenges: how to adapt instructions when rewards arrive late and obscured by market noise, how to synthesize heterogeneous information streams into coherent decisions, and how to bridge the gap between model outputs and executable market actions. We present ATLAS (Adaptive Trading wit…
Charidimos Papadakis, Angeliki Dimitriou, Giorgos Filandrianos, Maria Lymperaiou, Konstantinos Thomas
arXiv · arXiv · 2026
This paper develops an autonomous framework for systematic factor investing via agentic AI. Rather than relying on sequential manual prompts, our approach operationalizes the model as a self-directed engine that endogenously formulates interpretable trading signals. To mitigate data snooping biases, this closed-loop system imposes strict empirical discipline through out-of-sample validation and economic rationale req…
Allen Yikuan Huang, Zheqi Fan
arXiv · arXiv · 2025
We develop a transparent and fully auditable LLM-based pipeline for macro-financial stress testing, combining structured prompting with optional retrieval of country fundamentals and news. The system generates machine-readable macroeconomic scenarios for the G7, which cover GDP growth, inflation, and policy rates, and are translated into portfolio losses through a factor-based mapping that enables Value-at-Risk and E…
Masoud Soleimani
arXiv · arXiv · 2025
The proliferation of Large Language Models (LLMs) is challenged by hallucinations, critical failure modes where models generate non-factual, nonsensical or unfaithful text. This paper introduces Semantic Divergence Metrics (SDM), a novel lightweight framework for detecting Faithfulness Hallucinations -- events of severe deviations of LLMs responses from input contexts. We focus on a specific implementation of these L…
Igor Halperin
arXiv · arXiv · 2024
We argue that the Declarative Self-improving Python (DSPy) optimizers are a way to align the large language model (LLM) prompts and their evaluations to the human annotations. We present a comparative analysis of five teleprompter algorithms, namely, Cooperative Prompt Optimization (COPRO), Multi-Stage Instruction Prompt Optimization (MIPRO), BootstrapFewShot, BootstrapFewShot with Optuna, and K-Nearest Neighbor Few …
Bhaskarjit Sarmah, Kriti Dutta, Anna Grigoryan, Sachin Tiwari, Stefano Pasquali
arXiv · arXiv q-fin · 2011
Asset liquidity in modern financial markets is a key but elusive concept. A market is often said to be liquid when the prevailing structure of transactions provides a prompt and secure link between the demand and supply of assets, thus delivering low costs of transaction. Providing a rigorous and empirically relevant definition of market liquidity has, however, provided to be a difficult task. This paper provides a c…
Alexandros Gabrielsen, Massimiliano Marzo, Paolo Zagaglia
arXiv · arXiv q-fin · 2025
This paper presents a realistic simulated stock market where large language models (LLMs) act as heterogeneous competing trading agents. The open-source framework incorporates a persistent order book with market and limit orders, partial fills, dividends, and equilibrium clearing alongside agents with varied strategies, information sets, and endowments. Agents submit standardized decisions using structured outputs an…
Alejandro Lopez-Lira
arXiv · arXiv q-fin · 2026
Recent works have increasingly applied Large Language Models (LLMs) as agents in financial stock market simulations to test if micro-level behaviors aggregate into macro-level phenomena. However, a crucial question arises: Do LLM agents' behaviors align with real market participants? This alignment is key to the validity of simulation results. To explore this, we select a financial stock market scenario to test behav…
Zeping Li, Guancheng Wan, Keyang Chen, Yu Chen, Yiwen Zhao
arXiv · arXiv q-fin · 2026
Evaluating whether large language model (LLM) agents can profit in capital markets is increasingly framed as end-to-end trading: place an agent in a historical market, let it trade, and measure portfolio returns. This setup is vulnerable to two evaluation failures. First, long backtests often overlap with the knowledge cutoffs of frontier LLMs, allowing memorized tickers, dates, prices, and market narratives to subst…
Taojie Zhu, Wentao Zhao, Rui Sun, Beidi Luan, Jiacheng Lu
arXiv · arXiv q-fin · 2026
We study how AI agents form expectations and trade in experimental asset markets. Using a simulated open-call auction populated by autonomous Large Language Model (LLM) agents, we document three main findings. First, AI agents exhibit classic behavioral patterns: a pronounced disposition effect and recency-weighted extrapolative beliefs. Second, these individual-level patterns aggregate into equilibrium dynamics that…
Shumiao Ouyang, Pengfei Sui
arXiv · arXiv q-fin · 2025
Large language models (LLMs) are increasingly deployed in agentic frameworks, in which prompts trigger complex tool-based analysis in pursuit of a goal. While these frameworks have shown promise across multiple domains including in finance, they typically lack a principled model-building step, relying instead on sentiment- or trend-based analysis. We address this gap by developing an agentic system that uses LLMs to …
Dimitrios Emmanoulopoulos, Ollie Olby, Justin Lyon, Namid R. Stillman
arXiv · arXiv q-fin · 2025
This paper investigates how Large Language Models (LLMs) from leading providers (OpenAI, Google, Anthropic, DeepSeek, and xAI) can be applied to quantitative sector-based portfolio construction. We use LLMs to identify investable universes of stocks within S&P 500 sector indices and evaluate how their selections perform when combined with classical portfolio optimization methods. Each model was prompted to select and…
Alina Voronina, Oleksandr Romanko, Ruiwen Cao, Roy H. Kwon, Rafael Mendoza-Arriaga
arXiv · arXiv · 2026
We study how frontier large language models (LLMs) behave as financial forecasters during boom-bust market cycles when made progressively aware of Soros's theory of reflexivity. Standard AI-assisted forecasting treats the market as an exogenous system. Reflexivity theory holds otherwise: prices shape fundamentals, and every forecaster is a participative agent in the loop it analyzes. We evaluate three frontier models…
Eugene Park
arXiv · arXiv · 2025
This paper presents a Multi Agent Bitcoin Trading system that utilizes Large Language Models (LLMs) for alpha generation and portfolio management in the cryptocurrencies market. Unlike equities, cryptocurrencies exhibit extreme volatility and are heavily influenced by rapidly shifting market sentiments and regulatory announcements, making them difficult to model using static regression models or neural networks train…
Aadi Singhi
arXiv · arXiv · 2024
This work presents a generative pre-trained transformer (GPT) designed for modeling financial time series. The GPT functions as an order generation engine within a discrete event simulator, enabling realistic replication of limit order book dynamics. Our model leverages recent advancements in large language models to produce long sequences of order messages in a steaming manner. Our results demonstrate that the model…
Aaron Wheeler, Jeffrey D. Varner
arXiv · arXiv · 2024
Performance attribution analysis, defined as the process of explaining the drivers of the excess performance of an investment portfolio against a benchmark, stands as a significant feature of portfolio management and plays a crucial role in the investment decision-making process, particularly within the fund management industry. Rooted in a solid financial and mathematical framework, the importance and methodologies …
Bruno de Melo, Jamiel Sheikh
arXiv · arXiv · 2020
With the good development in the financial industry, the market starts to catch people's eyes, not only by the diversified investing choices ranging from bonds and stocks to futures and options but also by the general "high-risk, high-reward" mindset prompting people to put money in the financial market. People are interested in reducing risk at a given level of return since there is no way of having both high return…
Qingyin Ge, Yunuo Ma, Yuezhi Liao, Rongyu Li, Tianle Zhu