SLM-Based Agentic AI with P-C-G: Optimized for Korean Tool Use
On the map: LLM agents and tool use → Tool learning and function calling
Abstract (arXiv)
We propose a small-scale language model (SLM) based agent architecture, Planner-Caller-Generator (P-C-G), optimized for Korean tool use. P-C-G separates planning, calling, and generation by role: the Planner produces an initial batch plan with limited on-demand replanning; the Caller returns a normalized call object after joint schema-value validation; and the Generator integrates tool outputs to produce the final answer. We apply a Korean-first value policy to reduce execution failures caused by frequent Korean-to-English code switching in Korean settings. Evaluation assumes Korean queries and Korean tool/parameter specifications; it covers single-chain, multi-chain, missing-parameters, and missing-functions scenarios, and is conducted via an LLM-as-a-Judge protocol averaged over five runs under a unified I/O interface. Results show that P-C-G delivers competitive tool-use accuracy and end-to-end quality while reducing tokens and maintaining acceptable latency, indicating that role-specialized SLMs are a cost-effective alternative for Korean tool-use agents.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in Tool learning and function calling, one of 16 directions in LLM agents and tool use. Builds on 16 of its 17 references that are in the map. First posted on arXiv 19 Sep 2025.
Builds on
16 of 17 references.
Closest ancestors · 3
Same direction, newest first
- 2024FunctionChat-Bench: Comprehensive Evaluation of Language Models' Generative Capabilities in Korean Tool-use Dialogs21 Nov
- 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs31 Jul
- 2023Toolformer: Language Models Can Teach Themselves to Use Tools9 Feb
Other references · 13
- 2023GPT-4 Technical Reportcited by 18,396
- 2024The Llama 3 Herd of Modelscited by 14,715
- 2025Qwen3 Technical Reportcited by 8,820
- 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
- 2023A Survey on Large Language Model based Autonomous Agentscited by 2,242
- 2020Extracting Training Data from Large Language Modelscited by 2,189
- 2025Small Language Models are the Future of Agentic AIcited by 270
- 2023ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Modelscited by 184
- 2023An LLM Compiler for Parallel Function Callingcited by 179
- 2021KLUE: Korean Language Understanding Evaluationcited by 114
- 2024Small LLMs Are Weak Tool Learners: A Multi-LLM Agentcited by 93
- 2022KOBEST: Korean Balanced Evaluation of Significant Taskscited by 37
1 more
Built on by
Citing papers per year: 2026: 2.
2 papers.
Similar, not cited
Close in wording, no citation either way
- 2026Think in English, Answer in Korean: Efficient Adaptation of Multilingual Tool-Using Agents
- 2026ToolTree: Efficient LLM Agent Tool Planning via Dual-Feedback Monte Carlo Tree Search and Bidirectional Pruning
- 2026Beyond State Machines: Executing Network Procedures with Agentic Tool-Calling Sequences
- 2026The Evolution of Tool Use in LLM Agents: From Single-Tool Call to Multi-Tool Orchestration
- 2024Designing Algorithms Empowered by Language Models: An Analytical Framework, Case Studies, and Insights
- 2026PDEU-Bench: Benchmarking the Personalized Planning Lifecycle of Tool-Calling LLM Agents
- 2026Toward SLM-based agentic task-tool intent matching
- 2025From Language to Action: A Review of Large Language Models as Autonomous Agents and Tool Users