Seataubench Progressively Adapting Tool Agent User Evaluation Into Low Resource Southeast Asian Languages 2026 06 27
Source
cohere.com
Author
Cohere editorial sitemap
Date
Why it matters
AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → benchmarks are mostly English. This one shows how tool-use success and language fidelity change as the user, tools and domain content move to Southeast Asian languages, so teams shipping multilingual agents can test it.
Terms in this piece · Glossary
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
