Building Resource-Constrained Language Agents: A Korean Case Study on Chemical Toxicity Information
Year: 2025
Type: preprint
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.
Source: arXiv (Cornell University)
Authors: Cho, Hojun, Kim, Donghu, Yang, Soyoung, Lee, Chan, Lee, Hunjoo, Choo, Jaegul
Language: English
Topic: Speech and dialogue systems
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W6979271340
Cites:
Cited by:
Related to: