发表机构
Tongji University; Shanghai Non-convex Intelligent Technology（同济大学; 上海非凸智能科技）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出AlphaDiverse框架，通过多智能体系统、多样化路径收集和后训练，在Alpha因子挖掘中实现竞争性预测与广泛探索的平衡。
AI 中文摘要
基于大语言模型（LLM）的多智能体系统可以自动化Alpha因子挖掘，但它们对外部API的依赖限制了成本、可用性和保密性的控制。长时间的研究循环也倾向于重复少数成功的经济机制，导致研究路径崩溃。为解决这些局限性，我们提出了AlphaDiverse，一个整合了多智能体Alpha研究系统、多样化研究路径收集和本地智能体后训练的框架。我们让研究系统生成互补的计划组合，并在循环中变化研究环境以收集多样化的研究路径。利用这些多样化的轨迹，我们通过监督微调对本地Planner和Realizer智能体进行热启动。然后，我们提出了一种联合GRPO方法，利用预测质量和贡献多样性来优化这两个智能体。研究反馈被限制在内部周期数据内，而冻结的最终模型在后续的外部周期数据上进行评估，从而避免测试集调优。在四个中国股票池上的实验表明，AlphaDiverse能够将竞争性预测与更广泛的探索相结合。
英文摘要
Large language model (LLM)-based multi-agent systems can automate alpha factor mining, but their reliance on external APIs limits control over cost, availability, and confidentiality. Long research loops also tend to revisit a few successful economic mechanisms that lead to research path collapse. To address these limitations, we propose AlphaDiverse, a framework that integrates a multi-agent alpha research system, diverse research path collection, and post-training for local agents. We let the research system generate complementary plan portfolios and vary research environments across loops to collect diverse research paths. Using these diverse traces, we warm-start local Planner and Realizer agents with supervised fine-tuning. Then, we propose a joint GRPO method to optimize both of them using predictive quality and diversity of contributions. Research feedback is confined to inner period data, while a frozen final model is evaluated on a later outer period data, thereby avoiding test-set tuning. Experiments across four Chinese stock universes show that AlphaDiverse can combine competitive prediction with broader exploration.
Comments33 pages, 7 figures, 26 Tables. Preprint under review
