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

arXiv: https://arxiv.org/abs/2609.17632 · HTML: https://mlsanity.com/paper/2609.17632/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Financial trading and forecasting agents, one of 16 directions in LLM agents and tool use.
- Builds on 18 of its 38 references that are in the map.
- First posted on arXiv 15 Sep 2026.

## Placed in

- LLM agents and tool use / [Financial trading and forecasting agents](https://mlsanity.com/agents/financial-trading-and-forecasting-agents/)
- Synthetic data and self-improvement for LLMs / [Self-evolving LLM agents](https://mlsanity.com/synth/self-evolving-llm-agents/)

## Builds on (most cited first, 18 of 18)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Automatic Prompt Optimization with "Gradient Descent" and Beam Search](https://mlsanity.com/paper/2305.03495/) (2023)
- [TradingAgents: Multi-Agents LLM Financial Trading Framework](https://mlsanity.com/paper/2412.20138/) (2024)
- [FinMem: A Performance-Enhanced LLM Trading Agent with Layered Memory and Character Design](https://mlsanity.com/paper/2311.13743/) (2023)
- [A Multimodal Foundation Agent for Financial Trading: Tool-Augmented, Diversified, and Generalist](https://mlsanity.com/paper/2402.18485/) (2024)
- [FinAgentBench: A Benchmark Dataset for Agentic Retrieval in Financial Question Answering](https://mlsanity.com/paper/2508.14052/) (2025)
- [AI-Trader: Benchmarking Autonomous Agents in Real-Time Financial Markets](https://mlsanity.com/paper/2512.10971/) (2025)
- [FLAG-Trader: Fusion LLM-Agent with Gradient-based Reinforcement Learning for Financial Trading](https://mlsanity.com/paper/2502.11433/) (2025)
- [System Prompt Optimization with Meta-Learning](https://mlsanity.com/paper/2505.09666/) (2025)
- [Look-Ahead-Bench: a Standardized Benchmark of Look-ahead Bias in Point-in-Time LLMs for Finance](https://mlsanity.com/paper/2601.13770/) (2026)
- [TradExpert: Revolutionizing Trading with Mixture of Expert LLMs](https://mlsanity.com/paper/2411.00782/) (2024)
- [ATLAS: Adaptive Trading with LLM AgentS Through Dynamic Prompt Optimization and Multi-Agent Coordination](https://mlsanity.com/paper/2510.15949/) (2025)
- [AlphaQuanter: An End-to-End Tool-Augmented Agentic Reinforcement Learning Framework for Stock Trading](https://mlsanity.com/paper/2510.14264/) (2025)
- [Can Blindfolded LLMs Still Trade? An Anonymization-First Framework for Portfolio Optimization](https://mlsanity.com/paper/2603.17692/) (2026)
- [SHARP: A Self-Evolving Human-Auditable Rubric Policy for Financial Trading Agents](https://mlsanity.com/paper/2605.06822/) (2026)
- [TrustTrade: Human-Inspired Selective Consensus Reduces Decision Uncertainty in LLM Trading Agents](https://mlsanity.com/paper/2603.22567/) (2026)
- [FinSphere, a Real-Time Stock Analysis Agent Powered by Instruction-Tuned LLMs and Domain Tools](https://mlsanity.com/paper/2501.12399/) (2025)

## Built on by (most cited first, 1 of 1)

- [From Existing Methods to New Research Ideas: Two Perspectives on Recursive Self-Improvement](https://mlsanity.com/paper/2610.14625/) (2026)

## Abstract (arXiv)

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. We 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 procedure 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 SR and CR in most evaluated settings. Behavioral analyses further show that self-evolved policies increase code-mediated analysis and activate regime-relevant computations; case-level policy-to-return attributions trace how policy-induced allocation changes contribute to realized return differences. These results suggest that adapting the reusable procedure governing tool use is a key direction for building more robust LLM trading agents.