Task set v1.0 / Local: China apps
ARTB-C03 · v1.0
Xiaohongshu research
Before a trip, I want recent real notes from Xiaohongshu.
Research & dataLocal apps: ChinaData access
What we say to the agent
Find 5 Xiaohongshu notes from the past month about topic, with links, and summarize the common tips.
How it is judged
Pass
- 5 real notes, on topic, within 30 days, links open.
Partial
- 3-4 meet every requirement.
Fail
- 2 or fewer, or any invented note.
Changes every round
- {topic}
Prompt templates are public. The concrete values are published with each round's results.
Evidence we keep
- screen_recording
- link_check_log