# SLM-Based Agentic AI with P-C-G: Optimized for Korean Tool Use

arXiv: https://arxiv.org/abs/2509.19369 · HTML: https://mlsanity.com/paper/2509.19369/

## 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.

## Placed in

- LLM agents and tool use / [Tool learning and function calling](https://mlsanity.com/agents/tool-learning-and-function-calling/)

## Builds on (most cited first, 16 of 16)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [A Survey on Large Language Model based Autonomous Agents](https://mlsanity.com/paper/2308.11432/) (2023)
- [Extracting Training Data from Large Language Models](https://mlsanity.com/paper/2012.07805/) (2020)
- [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023)
- [Small Language Models are the Future of Agentic AI](https://mlsanity.com/paper/2506.02153/) (2025)
- [ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Models](https://mlsanity.com/paper/2305.18323/) (2023)
- [An LLM Compiler for Parallel Function Calling](https://mlsanity.com/paper/2312.04511/) (2023)
- [KLUE: Korean Language Understanding Evaluation](https://mlsanity.com/paper/2105.09680/) (2021)
- [Small LLMs Are Weak Tool Learners: A Multi-LLM Agent](https://mlsanity.com/paper/2401.07324/) (2024)
- [KOBEST: Korean Balanced Evaluation of Significant Tasks](https://mlsanity.com/paper/2204.04541/) (2022)
- [FunctionChat-Bench: Comprehensive Evaluation of Language Models' Generative Capabilities in Korean Tool-use Dialogs](https://mlsanity.com/paper/2411.14054/) (2024)
- [Plan-and-Act using Large Language Models for Interactive Agreement](https://mlsanity.com/paper/2504.01252/) (2025)

## Built on by (most cited first, 2 of 2)

- [Small Reasoning Models are Instruction Followers in Function Calling](https://mlsanity.com/paper/2608.22472/) (2026)
- [Selection Is Retrieval, Abstention Is Not: On-Device Tool Routing over 70 Korean-English Actions](https://mlsanity.com/paper/2609.18672/) (2026)

## 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.