Building Resource-Constrained Language Agents: A Korean Case Study on Chemical Toxicity Information
This work addresses the problem of building practical language agents for domain-specific applications in resource-limited settings, particularly for Korean chemical toxicity information, representing an incremental advancement.
The paper tackles the challenge of deploying language agents in resource-constrained environments for specialized domains and less-common languages, specifically developing Tox-chat, a Korean chemical toxicity information agent. The result shows that their fine-tuned 8B parameter model substantially outperforms untuned models and baselines in DB faithfulness and preference.
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.