发表机构
Islamic Azad University; University of Isfahan（伊斯兰阿扎德大学; 伊斯法罕大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出指令跟随式函数调用（IFFC）框架，将函数调用逻辑与主大语言模型解耦，交由专用小型模型处理，其性能优于原生和基于提示的函数调用基线，可高效部署于边缘计算场景。
AI 中文摘要
函数调用是智能体大语言模型（LLM）的核心能力，现有研究聚焦于通过微调、强化学习（RL）和多智能体框架提升LLM的函数调用准确率，尤其针对原生支持函数调用的LLM。本研究表明，LLM在指令跟随场景（即标准的用户-助手交互）下的函数调用准确率优于工具调用场景。我们提出了指令跟随式函数调用（Instruction-Followed Function Calling，IFFC）这一新型框架，它将函数调用逻辑与主LLM解耦，交由在指令跟随范式下运行的专用小型模型处理。我们的方法在原生函数调用（NFC）和基于提示的函数调用（PFC）基线中始终表现更优，在面向推理的LLM上提升尤为显著。此外，我们证明IFFC在激进量化下仍能保持稳健性能，可实现高效的设备端部署且不会出现明显的准确率下降。本研究为边缘计算场景下可靠、资源高效的函数调用建立了新范式。
英文摘要
Function calling represents the core capability of agentic large language models (LLMs). Existing research has focused on enhancing LLMs function-calling accuracy through fine-tuning, reinforcement learning (RL), and multi-agent frameworks, particularly for native function-calling LLMs. This work demonstrates that LLMs achieve superior accuracy in function calling in instruction-following contexts (i.e., standard user-assistant interactions) rather than a tool calling context. We introduce Instruction-Followed Function Calling (IFFC), a novel framework that decouples function-calling logic from the primary LLM and delegates it to a dedicated smaller model operating within the instruction-following paradigm. Our method consistently outperforms both native function calling (NFC) and prompt-based function calling (PFC) baselines, with particularly strong gains on reasoning-oriented LLMs. Furthermore, we demonstrate that IFFC maintains robust performance under aggressive quantization, enabling efficient on-device deployment without significant accuracy degradation. This work establishes a new paradigm for reliable, resource-efficient function calling in edge-computing scenarios.
