AlphaAgents: Large Language Model based Multi-Agents for Equity Portfolio Constructions

2025-08-14

AI Summary

Traditional stock screening and portfolio management suffer from poor adaptability and limited interpretability. Method: We propose a role-driven, multi-agent collaborative framework powered by large language models (LLMs), where specialized agents—guided by structured prompt engineering, dynamic inter-agent communication, and iterative feedback—jointly perform fundamental analysis, risk assessment, and portfolio optimization under multi-tiered risk preferences. Contribution/Results: The framework overcomes inherent limitations of monolithic LLMs in complex financial reasoning, enabling an end-to-end, interpretable investment research pipeline with adjustable strategies and verifiable outputs. Empirical evaluation demonstrates statistically significant outperformance over mainstream benchmarks—including Fama-French three-factor-based stock selection and Wind CSI All-A Index constituent screening—across diverse risk tolerance levels, confirming the method’s efficacy, robustness, and practical deployability.

Technology Category

• Multiagent Systems: Mechanism Design
• Machine Learning: Large Multimodal Models (LMMs)
• Search and Optimization: Metareasoning and Metaheuristics

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

The field of artificial intelligence (AI) agents is evolving rapidly, driven by the capabilities of Large Language Models (LLMs) to autonomously perform and refine tasks with human-like efficiency and adaptability. In this context, multi-agent collaboration has emerged as a promising approach, enabling multiple AI agents to work together to solve complex challenges. This study investigates the application of role-based multi-agent systems to support stock selection in equity research and portfolio management. We present a comprehensive analysis performed by a team of specialized agents and evaluate their stock-picking performance against established benchmarks under varying levels of risk tolerance. Furthermore, we examine the advantages and limitations of employing multi-agent frameworks in equity analysis, offering critical insights into their practical efficacy and implementation challenges.

Problem

• Applying multi-agent systems for stock selection in equity research
• Evaluating agent performance against benchmarks with different risk levels
• Analyzing advantages and limitations of multi-agent frameworks in equity analysis

Innovation

• LLM-based multi-agent collaboration for stock selection
• Role-based agents for equity portfolio management
• Performance evaluation against risk-adjusted benchmarks