StockAgent
Overview
Multi-agent LLM system that simulates investor trading behavior in a realistic stock-market environment to study how external factors affect decisions and outcomes.
StockAgent is an open-source, LLM-driven multi-agent framework for simulating stock trading behavior in a market environment that aims to resemble real-world conditions. The system models investor-like agents reacting to information such as macroeconomics, policy changes, company fundamentals, and global events, enabling analysis of trading behaviors and profitability effects under different external-factor scenarios. The authors also position StockAgent as addressing test-set leakage concerns in agent-based trading simulations by reducing reliance on prior memorized knowledge of the evaluation data. It’s primarily a research and experimentation framework (not a live-broker trading bot) for evaluating LLMs and studying emergent trading patterns in controlled simulations.
Autonomy level
55%
Comparisons
Custom Comparisons
Some of the use cases of StockAgent:
- Running agent-based stock trading simulations to test how news/events/fundamentals influence investor behavior.
- Benchmarking different LLMs in a trading decision-making loop under consistent simulation rules.
- Studying behavioral patterns (e.g., reaction to shocks) and profitability impacts across scenarios.
- Building academic or internal prototypes for market-simulation experiments without touching real capital.
Loading Community Opinions...