CORTEXA
← Browse
arxivcs.AIcs.LG2026-06-30

Think in English, Answer in Korean: Efficient Adaptation of Multilingual Tool-Using Agents

Utsav Garg, Sungjin Hong, Jason Jung, Justin Lee, Shaan Desai, Joon Hee Kim, Anirudh Shrinivason, Edmond Wen, Susie Park

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.

View free PDFSource page

Related papers

arxivcs.AIcs.LGcs.MA2026-07-24

TRACE-ROUTER: Task-Consistent and Adaptive Online Routing for Agentic AI

Ritik Raj, Souvik Kundu, Sarbartha Banerjee, Dheemanth Joshi, Ishita Vohra, Tushar Krishna

Routing to select large language models (LLMs) with different cost-quality trade-offs has become a fundamental deployment feature of enterprise AI. Existing routers, primarily make independent routing decisions for each LLM call. However, agentic applications execute as long-hori…

View free PDFSource page
arxivcs.ROcs.AIcs.LG2026-07-24

One Hand Watches The Other: Dynamic Multi-Agent Cooperation for Sample-Efficient Bimanual Manipulation in Dynamic Environments

Jan Ole von Hartz, Abhinav Valada, Joschka Boedecker

Multi-stream robot manipulation policies achieve unparalleled sample efficiency and generalization by modeling actions relative to environmental reference frames. However, existing approaches typically assume these frames to be strictly exogenous. This causal assumption collapses…

View free PDFSource page
arxivcs.LGcs.AI2026-07-31

DreamQAS: Learning a Decision-Useful World Model for VQE-Efficient Quantum Architecture Search

Jiayang Niu, Yan Wang, Jie Li, Ke Deng, Azadeh Alavi, Muhammad Usman, et al.

Reinforcement-learning-based quantum architecture search (RL-QAS) repeatedly optimizes a variational quantum eigensolver (VQE) after extending a circuit, although circuit construction and action legality are deterministic and known. We introduce DreamQAS, a model-based RL framewo…

View free PDFSource page
arxivcs.LGcs.AI2026-07-24

Optimization of time-consuming experimental conditions using pseudo-experimental data guided by adaptive polynomial regression

Hirotaka Sugawara, Yujin Taguchi, Kei Minagawa, Yusuke Hiki, Takashi Morikura, Akira Funahashi

Bayesian optimization (BO) is an optimization method that sequentially proposes the next candidate explainable variables for optimizing target variables by balancing exploration and exploitation. BO is often used under a limited evaluation budget, such as hyperparameter tuning of…

View free PDFSource page