@inproceedings{cho-etal-2025-building,
    title = "Building Resource-Constrained Language Agents: A {K}orean Case Study on Chemical Toxicity Information",
    author = "Cho, Hojun  and
      Kim, Donghu  and
      Yang, Soyoung  and
      Lee, Chan  and
      Lee, Hunjoo  and
      Choo, Jaegul",
    editor = "Potdar, Saloni  and
      Rojas-Barahona, Lina  and
      Montella, Sebastien",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track",
    month = nov,
    year = "2025",
    address = "Suzhou (China)",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/name-variant-enfa-fane/2025.emnlp-industry.191/",
    doi = "10.18653/v1/2025.emnlp-industry.191",
    pages = "2852--2880",
    ISBN = "979-8-89176-333-3",
    abstract = "Language agents powered by large language models (LLMs) face significant deployment challenges in resource-constrained environments, particularly for specialized domains and less-common languages. This paper presents Tox-chat, a Korean chemical toxicity information agent devised within these limitations. We propose two key innovations: a context-efficient architecture that reduces token consumption through hierarchical section search, and a scenario-based dialogue generation methodology that effectively distills tool-using capabilities from larger models. Experimental evaluations demonstrate that our fine-tuned 8B parameter model substantially outperforms both untuned models and baseline approaches, in terms of DB faithfulness and preference. Our work offers valuable insights for researchers developing domain-specific language agents under practical constraints."
}