Publications
Research contributions in artificial intelligence, machine learning, and data mining
SEATauBench: Adapting Tool-Agent-User Evaluation Into Low-Resource Southeast Asian Languages
My Chiffon Nguyen, Aulia Adila, Saksorn Ruangtanusak, Kittiphat Leesombatwathana, Vissuta Gunawan Lim, Patomporn Payoungkhamdee, Samuel Cahyawijaya
arXiv preprint, 2026
Introduces SEATauBench, the first agent-focused evaluation framework for Southeast Asian sovereign AI, adapting the Tool-Agent-User benchmark (τ-bench) to five languages: Mandarin, Vietnamese, Thai, Indonesian, and Filipino. It evaluates agents across progressively localized settings that vary the language of user-agent interaction, tool specifications, and task domains, finding that English agent capabilities transfer well when only the conversation language changes but degrade sharply as more task context is localized. The benchmark offers a diagnostic suite and a reusable adaptation pipeline for building reliable multilingual agents.