ETF Agent adds a Workspace for long-term, cross-run research
The ETF Agent author describes a Research Workspace that organizes long-term goals and links prior Runs, Publications, evidence versions, permissions, and research progress without replacing the existing execution engine. Its P0 implementation has been merged into the private codebase, where controlled tests used synthetic sources and scripted model responses to consume exact historical Publication versions across independent Runs. The feature remains disabled by default, full type checking and formal acceptance are unfinished, and the public Open ETF Agent repository does not include this complete module.
The design offers a concrete architecture for preserving research identity and provenance across independent AI-agent Runs, but the synthetic engineering tests do not establish real-world financial-analysis quality.
基金研究 Agent 收到一份招募说明书 PDF，提取文字、找到费用条款，然后生成摘要。第一轮看似顺利；几周后，文件更新了，另一轮研究又想引用旧报告。
这时候，“能读 PDF”已经不够。我们还需要知道：读到的是哪个来源的哪个版本，哪些内容真的提取和读取过，今天还能否继续用它。
我在 ETF Agent 中把这组问题交给 研究资料资产模块。它负责研究文件的身份、版本、提取状态和生命周期；不替 PDF 阅读器解释页面，不替知识检索判断相关性，更不把“登记成功”当成投资结论可信。
图 1｜同一份研究文件可以被不同阶段消费，但每次读取仍须符合来源和 Run 的授权。封面为概念插画，不是运行截图。
#ETF Agent#ETF Agent Research Workspace#ResearchAsset#Open ETF Agent