发表机构
The Hong Kong University of Science and Technology (Guangzhou); HSBC Business School, Peking University; IDEA Research, International Digital Economy Academy（香港科技大学（广州）; 北京大学汇丰商学院; 国际数字经济学创新研究院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该综述梳理智能体量化交易的工作流阶段、系统特性与评估基准，指出当前系统多集中于信号发现，多智能体系统依赖聚合，且模型能力未必转化为实盘交易性能，并展望了未来研究方向。
AI 中文摘要
量化交易正从孤立的预测模型向结合推理、工具使用、记忆与反馈的智能体工作流转变。本综述从因子挖掘、信号发现、组合构建、订单执行与风险管理五个阶段对智能体量化交易展开研究，同时从架构、协调与适应维度分析智能体量化交易系统，并对比策略构建、离线交易、实盘市场评估及可靠性评估的基准。研究发现，当前系统仍集中于信号发现阶段，与组合构建、执行及风险控制的完整整合尚不常见；多智能体系统尽管工作流结构日益多样，仍高度依赖聚合；基准证据进一步表明，强模型或预测能力在实盘市场条件与可靠性控制下无法可靠转化为交易性能。最后，本文展望了更完整交易工作流、更强协调及与评估能力匹配的未来方向。
英文摘要
Quantitative trading is moving from isolated predictive models toward agentic workflows that combine reasoning, tool use, memory, and feedback. This survey reviews agentic quantitative trading across five stages: factor mining, signal discovery, portfolio construction, order execution, and risk management. We further examine agentic quant trading systems through architecture, coordination, and adaptation, while comparing benchmarks across strategy construction, offline trading, live market evaluation, and reliability assessment. Our review finds that current systems remain concentrated on signal discovery, while complete integration with portfolio construction, execution, and risk control is still uncommon. Multi-agent systems also rely heavily on aggregation despite increasingly diverse workflow structures. Benchmark evidence further shows that strong model or forecasting capability does not reliably translate into trading performance under live market conditions and reliability controls. We conclude with future directions for more complete trading workflows, stronger coordination, and evaluation matched to the capability being assessed.
Comments9 pages, 2 figures, 2 tables
