一个会分步查资料的研究智能体

先看结果

输入：“今年[地区]的云存储数据驻留规则有哪些变化？一家 50 人的公司需要做什么？”

输出约 900 字，结尾如下：

Claims
| # | Claim | Supports | Contradicts | Confidence |
| 1 | Rule X took effect in March | [2][5] | - | high |
| 2 | Applies to companies over 25 staff | [2] | [4] says 50 | low: thresholds differ by source |
| 3 | Existing contracts have a 12-month transition | [3][5] | - | high |
Not resolved: the threshold in claim 2. Sources [2] and [4] are both official but dated differently; the newer one is [4].
Run: 6 searches, 9 reads, 41,200 tokens, 3 min 10 s.

报告会说明它知道什么、不知道什么，以及查明这些花费了多少成本。

架构

这是本站第一个真正带循环的项目：智能体会根据已读到的内容决定下一步搜索什么。