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.
@article{arxiv.2503.17753,
title = {Building Resource-Constrained Language Agents: A Korean Case Study on Chemical Toxicity Information},
author = {Hojun Cho and Donghu Kim and Soyoung Yang and Chan Lee and Hunjoo Lee and Jaegul Choo},
journal= {arXiv preprint arXiv:2503.17753},
year = {2025}
}