# Toward Expert Investment Teams:A Multi-Agent LLM System with Fine-Grained Trading Tasks

arXiv: https://arxiv.org/abs/2602.23330 · HTML: https://mlsanity.com/paper/2602.23330/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in Financial trading and forecasting agents, one of 16 directions in LLM agents and tool use.
- Builds on 26 of its 74 references that are in the map.
- First posted on arXiv 26 Feb 2026.

## Placed in

- LLM agents and tool use / [Financial trading and forecasting agents](https://mlsanity.com/agents/financial-trading-and-forecasting-agents/)

## Builds on (most cited first, 26 of 26)

- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society](https://mlsanity.com/paper/2303.17760/) (2023)
- [Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models](https://mlsanity.com/paper/2305.04091/) (2023)
- [The Impact of AI on Developer Productivity: Evidence from GitHub Copilot](https://mlsanity.com/paper/2302.06590/) (2023)
- [TradingAgents: Multi-Agents LLM Financial Trading Framework](https://mlsanity.com/paper/2412.20138/) (2024)
- [Agent S: An Open Agentic Framework that Uses Computers Like a Human](https://mlsanity.com/paper/2410.08164/) (2024)
- [FinMem: A Performance-Enhanced LLM Trading Agent with Layered Memory and Character Design](https://mlsanity.com/paper/2311.13743/) (2023)
- [An Empirical Study of the Non-determinism of ChatGPT in Code Generation](https://mlsanity.com/paper/2308.02828/) (2023)
- [A Multimodal Foundation Agent for Financial Trading: Tool-Augmented, Diversified, and Generalist](https://mlsanity.com/paper/2402.18485/) (2024)
- [Language Models Learn to Mislead Humans via RLHF](https://mlsanity.com/paper/2409.12822/) (2024)
- [Non-Determinism of "Deterministic" LLM Settings](https://mlsanity.com/paper/2408.04667/) (2024)
- [Alpha-GPT: Human-AI Interactive Alpha Mining for Quantitative Investment](https://mlsanity.com/paper/2308.00016/) (2023)
- [Aligning Language Models to Explicitly Handle Ambiguity](https://mlsanity.com/paper/2404.11972/) (2024)
- [GUARDIAN: Safeguarding LLM Multi-Agent Collaborations with Temporal Graph Modeling](https://mlsanity.com/paper/2505.19234/) (2025)
- [HedgeAgents: A Balanced-aware Multi-agent Financial Trading System](https://mlsanity.com/paper/2502.13165/) (2025)
- [Your AI, Not Your View: The Bias of LLMs in Investment Analysis](https://mlsanity.com/paper/2507.20957/) (2025)
- [AlphaAgents: Large Language Model based Multi-Agents for Equity Portfolio Constructions](https://mlsanity.com/paper/2508.11152/) (2025)
- [Decision-informed Neural Networks with Large Language Model Integration for Portfolio Optimization](https://mlsanity.com/paper/2502.00828/) (2025)
- [Blueprint First, Model Second: A Framework for Deterministic LLM Workflow](https://mlsanity.com/paper/2508.02721/) (2025)
- [TradingGroup: A Multi-Agent Trading System with Self-Reflection and Data-Synthesis](https://mlsanity.com/paper/2508.17565/) (2025)
- [When Wording Steers the Evaluation: Framing Bias in LLM judges](https://mlsanity.com/paper/2601.13537/) (2026)
- [Decomposed Opinion Summarization with Verified Aspect-Aware Modules](https://mlsanity.com/paper/2501.17191/) (2025)
- [LLM Company Policies and Policy Implications in Software Organizations](https://mlsanity.com/paper/2510.06718/) (2025)
- [Finding Optimal Trading History in Reinforcement Learning for Stock Market Trading](https://mlsanity.com/paper/2502.12537/) (2025)
- [QTMRL: An Agent for Quantitative Trading Decision-Making Based on Multi-Indicator Guided Reinforcement Learning](https://mlsanity.com/paper/2508.20467/) (2025)

## Built on by (most cited first, 7 of 7)

- [AQuA: Recursively Self-Improving Quantitative Trading Research Agents](https://mlsanity.com/paper/2608.12841/) (2026)
- [Signal or Noise in Multi-Agent LLM-based Stock Recommendations?](https://mlsanity.com/paper/2604.17327/) (2026)
- [FundaPod: A Multi-Persona Agent Pod Architecture with Knowledge Graph Memory for AI-Assisted Fundamental Investment Research](https://mlsanity.com/paper/2605.27864/) (2026)
- [Beyond Agent Architecture: Execution Assumptions and Reproducibility in LLM-Based Trading Systems](https://mlsanity.com/paper/2606.08285/) (2026)
- [Fund2Persona: A Framework for Building and Refining Financial Advisor Personas from Fund Disclosure Data](https://mlsanity.com/paper/2606.29793/) (2026)
- [Right-Sizing LLM-Agent Decomposition in VAT Determination: A Pilot Controlled Sweep](https://mlsanity.com/paper/2608.23395/) (2026)
- [Agentic Empirical Asset Pricing: Methodological Foundations](https://mlsanity.com/paper/2609.00731/) (2026)

## Abstract (arXiv)

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.