SEATauBench: Adapting Tool-Agent-User Evaluation Into Low-Resource Southeast Asian Languages
Provides a diagnostic benchmark and adaptation pipeline for evaluating multilingual agents in low-resource Southeast Asian languages, addressing a gap in sovereign AI development.
The paper introduces SEATauBench, the first agent-focused evaluation framework for Southeast Asian languages, adapting TauBench to five languages. It finds that English agent capabilities transfer reasonably well with only conversation language changes, but degrade sharply with full domain localization.
While AI development and evaluation for Southeast Asia (SEA) has grown rapidly, agent capabilities in regional languages are still poorly understood despite its importance to sovereign AI. To fill this gap, we introduce SEATauBench, the first agent-focused evaluation framework for SEA sovereign AI. SeaTau adapts TauBench to five languages -- Mandarin, Vietnamese, Thai, Indonesian, and Filipino -- and evaluates agents across progressively localized settings that vary the language of user-agent interaction, tool specifications, and task domains. Across three recent models, we find that English agent capabilities transfer reasonably well when only the conversation language changes, but quality and robustness degrade sharply as more task contexts are localized, with the largest losses in full domain adaptation. We also the limits of English-only agent assessment for measuring agent capabilities in SEA languages. More broadly, SeaTau provides a diagnostic benchmark and reusable adaptation pipeline for building reliable multilingual agents for linguistically diverse regions. Data and code can be accessed at github.com/SEACrowd/SEATauBench.