Orchestration Framework for Financial Agents: From Algorithmic Trading to Agentic Trading

TL;DR

This paper introduces an orchestration framework that transforms traditional algorithmic trading components into autonomous agents, making advanced financial trading systems more accessible to the general public.

Contribution

It proposes a comprehensive agent-based framework for financial trading, mapping each trading system component to autonomous agents, and demonstrates its effectiveness with real trading examples.

Findings

Achieved 20.42% return in stock trading with high Sharpe ratio

Generated 8.39% return in Bitcoin trading with manageable drawdown

Code implementation is publicly available on GitHub

Abstract

The financial market is a mission-critical playground for AI agents due to its temporal dynamics and low signal-to-noise ratio. Building an effective algorithmic trading system may require a professional team to develop and test over the years. In this paper, we propose an orchestration framework for financial agents, which aims to democratize financial intelligence to the general public. We map each component of the traditional algorithmic trading system to agents, including planner, orchestrator, alpha agents, risk agents, portfolio agents, backtest agents, execution agents, audit agents, and memory agent. We present two in-house trading examples. For the stock trading task (hourly data from 04/2024 to 12/2024), our approach achieved a return of $20.42\%$, a Sharpe ratio of 2.63, and a maximum drawdown of $-3.59\%$, while the S&P 500 index yielded a return of $15.97\%$. For the BTC trading task (minute data from 27/07/2025 to 13/08/2025), our approach achieved a return of $8.39\%$, a Sharpe ratio of $0.38$, and a maximum drawdown of $-2.80\%$, whereas the BTC price increased by $3.80\%$. Our code is available on \href{https://github.com/Open-Finance-Lab/AgenticTrading}{GitHub}.