专为韩语工具使用优化的小模型智能体，提升准确率并减少成本。
SLM-Based Agentic AI with P-C-G: Optimized for Korean Tool Use
- 分角色设计规划-调用-生成流程，分工明确提升效率。
- 韩语优先策略降低中英代码切换导致的执行失败率。
- 适合需要低成本高可用韩语工具调用的场景。
我们提出一种基于小规模语言模型（SLM）的智能体架构Planner-Caller-Generator（P-C-G），专为韩语工具使用优化。该架构按角色分离规划、调用与生成：规划器生成初始任务计划并支持有限的动态重规划；调用器在联合模式-值验证后返回标准化调用对象；生成器整合工具输出生成最终答案。采用韩语优先的价值策略，缓解韩语环境中频繁出现的韩英代码切换所引发的执行失败问题。评估基于韩语查询与韩语工具/参数规范，涵盖单链、多链、参数缺失及函数缺失等场景，通过大模型作为裁判（LLM-as-a-Judge）协议，在统一输入输出接口下平均五次运行得出结果。实验表明，P-C-G在保持可接受延迟的同时，显著降低令牌消耗，且在工具使用准确率与端到端质量上表现优异，证明角色专业化的小模型是韩语工具调用智能体的经济高效替代方案。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。