用可验证的智能体搜索自动发现高收益交易因子。
AgonAlpha: Autonomous Alpha Discovery via Prompt Economy and Scalable Agentic Search
- 在冻结的研究成果中搜索，包括假设、表达式和证据链
- 实测表现：夏普比率3.48，适应度达9.50，多用户验证成功
- 支持透明溯源，适合量化交易研究与自动化策略开发
语言模型能提出大量可能的交易因子，但自主研究系统还需合理分配评估预算、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，其架构在冻结的研究成果（如假设、可执行表达式、平台证据、推理过程及评审状态）中进行搜索，而非仅限于公式本身。据我们所知，AgonAlpha是首个结合已验证成果搜索、具备重执行与否决权的新型上下文对抗性评审器、支持待处理任务感知的并行预算分配，以及完整公开证据链的因子挖掘系统。在WorldQuant BRAIN上的独立部署中，该系统为五位用户和六种模型后端生成了卓越级交易因子，适应度达到9.50，夏普比率达3.48，且每项提交均保留从提示到表达式的完整可追溯性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。