Toward expert investment teams: a multi-agent LLM system with fine-grained trading tasks

Journal article

The advancement of large language models (LLMs) has accelerated the development of autonomous financial trading systems. While mainstream approaches deploy multi-agent systems with hierarchical decision architectures, they often rely on coarse-grained instructions that underspecify the analytical procedures, leading to degraded inference quality and reduced transparency. We propose a structured decision architecture that explicitly decomposes investment analysis into fine-grained, domain-informed tasks assigned to specialized inference modules, rather than providing abstract role-level 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, validated through bootstrap confidence intervals, multiple-testing corrections, and subperiod stability analysis, demonstrate 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 semantic alignment between analytical outputs and downstream decision layers is a critical driver of system performance, consistent with a structured regularization interpretation. Moreover, we conduct standard portfolio optimization, exploiting low correlation with the stock index and the variance of each system’s output, achieving superior risk-adjusted performance. These findings contribute to the design of structured inference architectures and task decomposition strategies for LLM-based financial decision systems.

Authors: Miyazaki, K; Kawahara, T; Roberts, S; Zohren, S

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: With Intelligence
• Journal: Journal of Financial Data Science
• Volume: 8
• Issue: 3
• Pages: 168 - 202
• Publication date: 2026-06-16
• DOI: 10.3905/jfds.2026.008
• EISSN: 2640-3951
• ISSN: 2640-3943
• Language: English
• Keywords: inference; portfolio; task (project management); investment decisions; stock (firearms); decomposition; technical analysis; decision support system