发表机构
The Chinese University of Hong Kong; University of Maryland（香港中文大学; 马里兰大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
AgonAlpha是首个结合经验证构件搜索、对抗审核器与并行预算分配的阿尔法挖掘系统，在WorldQuant BRAIN部署后产出SPECTACULAR级阿尔法，为交易因子自主研究提供了完整证据轨迹。
AI 中文摘要
语言模型可提出诸多看似合理的交易因子，但自主研究系统还需分配评估预算、验证自身证据并保留每个候选因子的生成过程。我们提出AgonAlpha，一种在冻结的研究构件（包括假设、可执行表达式、平台证据、原理及审核状态）而非仅公式上进行搜索的架构。据我们所知，AgonAlpha是首个将经验证的构件搜索、具备重新执行与否决权限的新鲜上下文对抗审核器、感知待处理任务的并行预算分配，以及完整公开证据轨迹相结合的阿尔法挖掘系统。在WorldQuant BRAIN上的独立部署，在5位用户、6种模型后端上产出了SPECTACULAR级阿尔法， Fitness达9.50，Sharpe达3.48，同时为每次提交保留了从提示到表达式的溯源信息。
英文摘要
Language models can propose many plausible trading factors, but an autonomous research system must also allocate its evaluation budget, verify its own evidence, and preserve how each candidate was produced. We present AgonAlpha, an architecture that searches over frozen research artifacts---hypotheses, executable expressions, platform evidence, rationales, and review status---rather than formulas alone. To our knowledge, AgonAlpha is the first alpha-mining system to combine verified artifact search, a fresh-context adversarial reviewer with re-execution and veto authority, and pending-aware parallel budget allocation, together with a complete public evidence trail. Independent deployments on WorldQuant BRAIN produced SPECTACULAR-grade alphas across five users and six model backends, with Fitness reaching 9.50 and Sharpe reaching 3.48, while retaining prompt-to-expression provenance for every submission.
