{"ID":5438889,"CreatedAt":"2026-07-01T01:17:58.482524686Z","UpdatedAt":"2026-07-03T13:17:43.497842103Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.31648","arxiv_id":"2606.31648","title":"Think in English, Answer in Korean: Efficient Adaptation of Multilingual Tool-Using Agents","abstract":"We present LuckyStar 111B, a 111B-parameter hybrid reasoning model developed through a collaboration between Cohere and LG CNS for Korean-English enterprise agents under practical memory and serving constraints. The model trains from Cohere's fully post-trained Command A model rather than a new pretraining run, and uses preamble conditioning to switch between concise non-reasoning behavior and longer tool-oriented reasoning. We study four choices for scaling tool-using agents efficiently: multilingual supervised fine-tuning, reinforcement learning with verifiable rewards for multi-step tool-use tasks, language-consistency rewards for Korean user-facing responses, and 4-bit quantization for single-GPU serving. The adapted model improves mathematical reasoning, function calling, and agentic natural-language-to-SQL (NL2SQL) performance while preserving general Korean and English instruction-following quality. These results provide a practical recipe and failure-mode analysis for adapting post-trained multilingual models to verifiable agentic workflows under memory-constrained deployment.","short_abstract":"We present LuckyStar 111B, a 111B-parameter hybrid reasoning model developed through a collaboration between Cohere and LG CNS for Korean-English enterprise agents under practical memory and serving constraints. The model trains from Cohere's fully post-trained Command A model rather than a new pretraining run, and use...","url_abs":"https://arxiv.org/abs/2606.31648","url_pdf":"https://arxiv.org/pdf/2606.31648v1","authors":"[\"Utsav Garg\",\"Sungjin Hong\",\"Jason Jung\",\"Justin Lee\",\"Shaan Desai\",\"Joon Hee Kim\",\"Anirudh Shrinivason\",\"Edmond Wen\",\"Susie Park\"]","published":"2026-06-30T13:29:16Z","proceeding":"cs.AI","tasks":"[\"cs.AI\",\"cs.LG\"]","methods":"[\"Reinforcement Learning\"]","has_code":false}