arXiv · arXiv q-fin · 2026
Multi-agent LLM decision systems for portfolio management still lack a principled way to assign credit across specialist agents, remain vulnerable to cold-start dominance under regime shifts, and offer limited transparency into how final allocations are formed. We propose Market Regime Council (MRC), a cooperative multi-agent decision system that computes exact Shapley credits across all single, pairwise, and Grand-c…
Yunhua Pei, Zerui Ge, Jin Zheng, John Cartlidge
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
LLM agents are increasingly cast as autonomous portfolio managers, yet the dominant evaluation idiom, a leaderboard of returns over a fixed window, certifies neither the soundness of an agent's process nor the durability of its edge: one period's return is dominated by the market path, and apparent alpha can dissolve once look-ahead bias and trading costs are controlled. We introduce CLQT, a closed-loop benchmark tha…
Bo Qu, Mingguang Chen
arXiv · arXiv q-fin · 2025
This paper explores how Large Language Models (LLMs) behave in a classic experimental finance paradigm widely known for eliciting bubbles and crashes in human participants. We adapt an established trading design, where traders buy and sell a risky asset with a known fundamental value, and introduce several LLM-based agents, both in single-model markets (all traders are instances of the same LLM) and in mixed-model "b…
Thomas Henning, Siddhartha M. Ojha, Ross Spoon, Jiatong Han, Colin F. Camerer
arXiv · arXiv q-fin · 2025
Developing professional, structured reasoning on par with human financial analysts and traders remains a central challenge in AI for finance, where markets demand interpretability and trust. Traditional time-series models lack explainability, while LLMs face challenges in turning natural-language analysis into disciplined, executable trades. Although reasoning LLMs have advanced in step-by-step planning and verificat…
Yijia Xiao, Edward Sun, Tong Chen, Fang Wu, Di Luo
arXiv · arXiv q-fin · 2024
Significant progress has been made in automated problem-solving using societies of agents powered by large language models (LLMs). In finance, efforts have largely focused on single-agent systems handling specific tasks or multi-agent frameworks independently gathering data. However, the multi-agent systems' potential to replicate real-world trading firms' collaborative dynamics remains underexplored. TradingAgents p…
Yijia Xiao, Edward Sun, Di Luo, Wei Wang
arXiv · arXiv · 2026
Large language models (LLMs) have shown strong performance across diverse financial tasks, yet portfolio management (PM) remains poorly benchmarked. Existing benchmarks exhibit two gaps: they are often equity-only and ignore cross-asset correlations; they fail to evaluate the complete PM decision pipeline. We introduce PortBench, a benchmark spanning six heterogeneous asset classes from 2015 to 2025. PortBench compri…
Yuxuan Zhao, Sijia Chen, Ningxin Su
arXiv · arXiv · 2025
Cryptocurrency portfolio management requires the fusion of heterogeneous multi-modal signals, including structured price and on-chain time series, unstructured news text, and technical indicators, under high-volatility and real-time constraints. While deep learning approaches show predictive capability, their opacity limits practical adoption, and single large language model (LLM) agents struggle to process the bread…
Yichen Luo, Yebo Feng, Jiahua Xu, Paolo Tasca, Yang Liu
arXiv · arXiv · 2025
Financial bond yield forecasting is challenging due to data scarcity, nonlinear macroeconomic dependencies, and evolving market conditions. In this paper, we propose a novel framework that leverages Causal Generative Adversarial Networks (CausalGANs) and Soft Actor-Critic (SAC) reinforcement learning (RL) to generate high-fidelity synthetic bond yield data for four major bond categories (AAA, BAA, US10Y, Junk). By in…
Jaskaran Singh Walia, Aarush Sinha, Naman Saraswat, Srinitish Srinivasan, Srihari Unnikrishnan
arXiv · arXiv · 2026
We attempt to mitigate the persistent tradeoff between risk and return in medium- to long-term portfolio management. This paper proposes a novel LLM-guided no-regret portfolio allocation framework that integrates online learning dynamics, market sentiment indicators, and large language model (LLM)-based hedging to construct high-Sharpe ratio portfolios tailored for risk-averse investors and institutional fund manager…
Muhammad Abro, Hassan Jaleel
arXiv · arXiv · 2025
This paper mathematically models a constant-function automated market maker (CFAMM) position as a portfolio of exotic options, known as perpetual American continuous-installment (CI) options. This model replicates an AMM position's delta at each point in time over an infinite time horizon, thus taking into account the perpetual nature and optionality to withdraw of liquidity provision. This framework yields two key t…
Srisht Fateh Singh, Reina Ke Xin Li, Samuel Gaskin, Yuntao Wu, Jeffrey Klinck
arXiv · arXiv · 2025
Large Language Models (LLMs) have recently been leveraged for asset pricing tasks and stock trading applications, enabling AI agents to generate investment decisions from unstructured financial data. However, most evaluations of LLM timing-based investing strategies are conducted on narrow timeframes and limited stock universes, overstating effectiveness due to survivorship and data-snooping biases. We critically ass…
Weixian Waylon Li, Hyeonjun Kim, Mihai Cucuringu, Tiejun Ma
arXiv · arXiv · 2026
In financial markets, a sequential policy that reacts systematically to price movements may become predictable to other market participants. This paper studies whether large language model (LLM) agents exhibit such directional structure through RetailAgent, an experimental framework in which an LLM observes anonymized intraday equity price histories and permitted state, then repeatedly chooses long (hold the stock) o…
Yupeng Zhang, Liuyuan Jiang, Hongyi Huang, Bingheng Li, Lisha Chen
arXiv · arXiv · 2026
Large language models (LLMs) are increasingly used in investment decision-making, yet prior work shows that they exhibit systematic, model-specific investment preferences. We study whether a model's overall investment stance can be calibrated to a specified direction and strength. We introduce an investment-bias dial, an inference-time intervention on a single neuron that continuously adjusts a model-level decision p…
Sahong Park, Suhwan Park, Hoyoung Lee, Gakyung Kwon, Wonbin Ahn
arXiv · arXiv · 2026
Forecasting benchmarks for retrieval-augmented LLMs routinely confound model capability with information leakage: features labeled with a target's timestamp are often not observable at the system's decision time. We study leakage-controlled equity factor ranking with a retrieval-augmented 7B open-source LLM forecaster. At each month-end from 2023-04 to 2026-03, the forecaster observes only decision-time information: …
Mao Guan, Qian Chen
arXiv · arXiv · 2026
Business sentiment is a closely watched economic signal, but measuring it is slow and costly: surveys reach only a few hundred firms, arrive periodically, and take time to compile. We show that large language models hold the potential to address these shortcomings. We prompt an LLM to role-play as the CFO of a specific company at a specific date and focus on the economic-optimism question on the Duke-Federal Reserve …
John R. Graham, Campbell R. Harvey, Manish Jha