The advancement of large language models (LLMs) has accelerated the development of autonomous financial trading systems. While mainstream approaches deploy multi-agent systems mimicking analyst and manager roles, they often rely on abstract instructions that overlook the intricacies of real-world workflows, which can lead to degraded inference performance and less transparent decision-making. Therefore, we propose a multi-agent LLM trading framework that explicitly decomposes investment analysis into fine-grained tasks, rather than providing coarse-grained instructions. We evaluate the proposed framework using Japanese stock data, including prices, financial statements, news, and macro information, under a leakage-controlled backtesting setting. Experimental results show that fine-grained task decomposition significantly improves risk-adjusted returns compared to conventional coarse-grained designs. Crucially, further analysis of intermediate agent outputs suggests that alignment between analytical outputs and downstream decision preferences is a critical driver of system performance. Moreover, we conduct standard portfolio optimization, exploiting low correlation with the stock index and the variance of each system's output. This approach achieves superior performance. These findings contribute to the design of agent structure and task configuration when applying LLM agents to trading systems in practical settings.
A Unified Multi-Modal Framework for Intelligent Financial Systems: Integrating Reinforcement Learning, High-Frequency Trading, and Game-Theoretic Approaches with Cross-Modal Sentiment Analysis
Henan University, International Eurasia College(河南大学,国际欧亚学院);City University of Hong Kong, College of Business(香港城市大学,商学院);Northeastern University, School of Electronic and Information Engineering(东北大学,电子与信息工程学院)
When AI Meets Finance (StockAgent): Large Language Model-based Stock Trading in Simulated Real-world Environments
University of Liverpool(利物浦大学);Peking University(北京大学);Shanghai University of Finance(上海金融学院);Rutgers University(罗格斯大学);University of Michigan(密歇根大学);Northwestern University(西北大学);New York University(纽约大学);Xi’an Jiaotong-Liverpool University(西安交通大学利物浦大学);New Jersey Institute of Technology(新泽西理工学院)
QuantAgent: Seeking Holy Grail in Trading by Self-Improving Large Language Model
The Hong Kong University of Science and Technology(香港科技大学);IDEA Research(IDEA研究院);The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州))
Enhancing Profitability and Investor Confidence through Interpretable AI Models for Investment Decisions
School of Electrical Engineering and Computer Science, National University of Sciences and Technology (NUST)(国家科技大学电气工程与计算机科学学院);Department of Computer Science, Bahria University(巴里亚大学计算机科学系);College of Computer and Information Sciences (CCIS), Prince Sultan University(苏丹王子大学计算机与信息科学学院)