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

**Published:** September 17, 2026
**Author:** Sehee Kim, Yumin Choi, Minki Kang, Sung Ju Hwang
**Source:** arXiv — cs.AI
**Language:** en-US
**HTML:** https://aiqazaqstan.com/en/articles/evolvetrade-experience-driven-policy-refinement-for-self-evolving-llm-tr

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…

> From the original source: **arXiv — cs.AI**
> [Read full article at arXiv — cs.AI](https://arxiv.org/abs/2609.17632)

**Tags:** #arXiv

---

*AI Qazaqstan — non-commercial informational portal about AI in Kazakhstan. Machine translations and summaries are AI-generated.*