EvolveTrade: Experience-Driven Policy Refinement for Self-Evolving LLM Trading Agents

A new paper titled "EvolveTrade: Experience-Driven Policy Refinement for Self-Evolving LLM Trading Agents" addresses the limitation that large language model trading agents rely on static hand-written tool-use policies fixed before deployment, which restricts their ability to adapt how they gather evidence, invoke tools, and verify signals. The work proposes experience-driven policy refinement to let LLM trading agents evolve their tool-use behavior after deployment.

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 signal