Researchers propose EvolveTrade, a self-evolving framework that adapts LLM trading agents’ tool-use policies over time

LLM trading agents typically rely on static, hand-written tool-use policies that are fixed before deployment, limiting their ability to adapt how they gather evidence, invoke tools, verify signals, and manage risk under changing market regimes.

Researchers introduce EvolveTrade, a self-evolving framework that treats the system prompt of a tool-using trading agent as a text-parameterized policy.

After each update interval, a Policy Agent revises this policy using accumulated decision traces and realized portfolio feedback, while keeping the backbone LLM fixed.

The updated policy is then used for the next batch of trading decisions, enabling the agent to refine its information-acquisition and portfolio-construction procedures over time.

Experiments across multiple market regimes and two LLM backbones show that EvolveTrade often improves Sharpe Ratio and Cumulative Return over fixed-policy LLM baselines, achieving the improved metrics in most evaluated settings.

Behavioral analyses indicate that self-evolved policies increase code-mediated analysis and activate regime-relevant computations, and case-level policy-to-return attributions trace how policy-induced allocation changes contribute to realized return differences.