mlsanityData to 14 Oct 2026

Building Resource-Constrained Language Agents: A Korean Case Study on Chemical Toxicity Information

arXiv 2503.17753 ↗First posted 22 Mar 2025cs.CL cs.AIcited by 1

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

Abstract (arXiv)

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.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 24 of its 48 references that are in the map. First posted on arXiv 22 Mar 2025.

Builds on

24 of 48 references.

Closest ancestors · 5

Same direction, newest first

  1. 2024Chain of Agents: Large Language Models Collaborating on Long-Context Tasks4 Jun
  2. 2023Agent Lumos: Unified and Modular Training for Open-Source Language Agents9 Nov
  3. 2023The Rise and Potential of Large Language Model Based Agents: A Survey14 Sep
  4. 2023A Survey on Large Language Model based Autonomous Agents22 Aug
  5. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society31 Mar

Other references · 19

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2023GPT-4 Technical Reportcited by 18,396
  3. 2024The Llama 3 Herd of Modelscited by 14,715
  4. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  5. 2024GPT-4o System Cardcited by 4,588
  6. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,947
  7. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
  8. 2023Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!cited by 1,154
  9. 2022Red Teaming Language Models with Language Modelscited by 1,026
  10. 2023Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizescited by 737
  11. 2023PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallelcited by 660
  12. 2023API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMscited by 591
7 more
  1. 2024Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexitycited by 451
  2. 2023Specializing Smaller Language Models towards Multi-Step Reasoningcited by 251
  3. 2024Two Tales of Persona in LLMs: A Survey of Role-Playing and Personalizationcited by 208
  4. 2023Chain-of-Knowledge: Grounding Large Language Models via Dynamic Knowledge Adapting over Heterogeneous Sourcescited by 122
  5. 2024A Note on Shumailov et al. (2024): `AI Models Collapse When Trained on Recursively Generated Data'cited by 115
  6. 2023Hierarchical Prompting Assists Large Language Model on Web Navigationcited by 36
  7. 2025ToolDial: Multi-turn Dialogue Generation Method for Tool-Augmented Language Modelscited by 34

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025From LLM Reasoning to Autonomous AI Agents: A Comprehensive Reviewcited by 149

Similar, not cited

Close in wording, no citation either way

  1. 2024Realistic Evaluation of Toxicity in Large Language Models
  2. 2025Toxicity Red-Teaming: Benchmarking LLM Safety in Singapore's Low-Resource Languages
  3. 2024From One to Many: Expanding the Scope of Toxicity Mitigation in Language Models
  4. 2024Toxic Subword Pruning for Dialogue Response Generation on Large Language Models
  5. 2026ToxiREX: A Dataset on Toxic REasoning in ConteXt
  6. 2026A Survey of Toxicity Detection and Mitigation Strategies for Multilingual Language Models
  7. 2023OpenAgents: An Open Platform for Language Agents in the Wild
  8. 2025ToxSearch: Evolving Prompts for Toxicity Search in Large Language Models