Orchestration Framework for Financial Agents: From Algorithmic Trading to Agentic Trading
Jifeng Li*, Arnav Grover*, Abraham Alpuerto, and 2 more authors
In NeurIPS 2025 Workshop on Generative AI in Finance, Dec 2025
Accepted for Poster Presentation
We propose an end-to-end orchestration framework that democratizes financial intelligence by mapping traditional algorithmic trading components (Data, Alpha, Risk, Portfolio) to specialized AI agents. By utilizing the Model Context Protocol (MCP) for orchestration and Agent-to-Agent (A2A) protocols for peer communication, we achieve a modular system where LLMs handle reasoning while preventing data leakage. In backtesting on hourly stock data (04/2024–12/2024), our framework achieved a Sharpe ratio of 2.63 compared to the S&P 500’s 1.86.