EvolveTrade:用进化式系统提示词优化交易智能体

DAIR.AI · @dair_ai · X·2026-09-23 00:27·27分钟前
AI 导读

论文 EvolveTrade 将交易智能体的系统提示词视为策略,每轮交易后由独立的 Policy Agent 读取决策轨迹与实际收益并重写提示词,主干模型保持冻结。在多种市场环境和两个主干模型上,进化后的智能体在多数设置下于 Sharpe ratio 和累计收益上超越固定提示词基线。重写后的提示词还促使智能体更多使用代码分析,并计算契合当前市场环境的信号。

DAIR.AI@dair_ai
39AI 编辑部评分,满分 100

EvolveTrade:用进化式系统提示词优化交易智能体

2026-09-23 00:27· 27分钟前
AI 导读

论文 EvolveTrade 将交易智能体的系统提示词视为策略,每轮交易后由独立的 Policy Agent 读取决策轨迹与实际收益并重写提示词,主干模型保持冻结。在多种市场环境和两个主干模型上,进化后的智能体在多数设置下于 Sharpe ratio 和累计收益上超越固定提示词基线。重写后的提示词还促使智能体更多使用代码分析,并计算契合当前市场环境的信号。

Cool paper showing how effective tuning a system prompt for an agent can be.

Recommended paper if you tune agent harnesses.

This paper presents EvolveTrade, which treats a trading agent's system prompt as its policy.

After each trading interval, a separate Policy Agent reads the decision traces and the realized returns and rewrites the prompt. The backbone model stays frozen.

Across several market regimes and two backbone models, the evolved agent beats fixed-prompt baselines on Sharpe ratio and cumulative return in most settings.

The rewritten prompts also led the agent to run more code-based analysis and to compute signals that fit the current market regime.

Paper: https://academy.dair.ai/papers/evolvetrade-experience-driven-policy-refinement-for-self-evolving-llm-trading-ag-2609.17632

来源:DAIR.AI· x.com