Ant Group inclusionAI open-sources multi-model deep research system PanelWise
Original title:inclusionAI/PanelWise
AI summary
Ant Group's inclusionAI open-sourced PanelWise, a self-managed multi-model deep research system in which multiple research agents independently retrieve and write, then analyze and synthesize to produce final results. In a historical experiment with 100 tasks, the frontier combination scored 73.68, exceeding the then-record OpenRouter Fusion score of 68.3; the budget combination scored 66.42 at about $1.31 per question, roughly 19% of the externally estimated $7 per question.
Key Takeaways
- Ant Group's inclusionAI open-sourced PanelWise,a self-managed multi-model deep research system in…
- In a historical experiment with 100 tasks,the frontier combination scored 73.
- 68,exceeding the then-record OpenRouter Fusion score of 68.
- the budget combination scored 66.
- 42 at about $1.
Quick Facts
- Published
- Updated
- Source
- 蚂蚁 inclusionAI:GitHub 新仓库
- Category
- Tutorials & Tips
- AI score
- 57
其价值不在分数本身,而在公开了完整管线与实验中已知的协议差异,为复现和公平对比提供了可操作的起点。
Source & copyright
This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.
How to Cite
When citing this article, keep the title, date, and permalink, and credit Orange News as the source.
Orange News: Ant Group inclusionAI open-sources multi-model deep research system PanelWise. July 23, 2026. https://new.nat6.net/en/news/cmsb5luf205hrrohvg33txp9b/