Sentient Ecosystem(@SentientEco):More tool variety doesn’t tell you much about whether an agent will succeed. Across 13K+ OfficeQA runs, successful agents used slightly more varied tools than failing ones, but tool variety alone predicted success only slightly better than a coin flip. TLDR: Low tool variety may be a weak warning sign. It isn’t a diagnosis and our results show that switching tools is not a fix.

Sentient Ecosystem

@SentientEco

Empowering @SentientAGI builders, researchers, and the ecosystem in advancing open-source AGI 🤝

参加 July 2024

75 フォロー中 27.9K ファン

Sentient Ecosystem@SentientEco

2026.09.23 13:00

More tool variety doesn’t tell you much about whether an agent will succeed. Across 13K+ OfficeQA runs, successful agents used slightly more varied tools than failing ones, but tool variety alone predicted success only slightly better than a coin flip. TLDR: Low tool variety may be a weak warning sign. It isn’t a diagnosis and our results show that switching tools is not a fix.