EvolveTrade: Experience-Driven Policy Refinement for Self-Evolving LLM Trading Agents
EvolveTrade lets LLM trading agents self-refine their tool-use policy from realized portfolio feedback, improving Sharpe ratios.
EvolveTrade treats a tool-using trading agent's system prompt as a text-parameterized policy that a Policy Agent revises after each update interval using accumulated decision traces and realized portfolio feedback, keeping the backbone LLM fixed. Experiments across multiple market regimes and two LLM backbones show improved Sharpe Ratio and Cumulative Return over fixed-policy baselines in most settings. Behavioral analyses show evolved policies increase code-mediated analysis and activate regime-relevant computations, with case-level attributions linking policy changes to returns.
- System prompt treated as a text-parameterized policy revised by a Policy Agent
- Backbone LLM stays fixed while the policy evolves each update interval
- Improves Sharpe Ratio and Cumulative Return in most evaluated settings
- Evolved policies increase code-mediated analysis and regime-relevant computations
- Case-level attributions trace policy changes to realized returns
From the original article
1 min read at huggingface.co
Large language model (LLM) trading agents can combine market data, news, and executable analysis, but their behavior is often controlled by static hand-written tool-use policies that are fixed before deployment. This limits their ability to adapt how they gather evidence, invoke tools, verify signals, and manage risk under changing market regimes.
By Sehee Kim, Yumin Choi, Minki Kang · huggingface.co
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.