Routine：面向企业级LLM智能体系统的结构化规划框架
Routine: A Structural Planning Framework for LLM Agent System in Enterprise
AI总结：
本文提出企业级LLM智能体结构化规划框架Routine，通过清晰结构与指令提升多步骤工具调用稳定性，将GPT-4o和Qwen3-14B执行准确率分别提升至96.3%和95.5%。
摘要：
在企业环境中部署智能体系统往往受到若干挑战的阻碍：通用模型缺乏领域特定的流程知识，导致计划混乱、遗漏关键工具以及执行稳定性差。为解决这一问题，本文提出了Routine，这是一个多步骤智能体规划框架，其设计具有清晰的结构、明确的指令和无缝的参数传递，以引导智能体的执行模块以高稳定性执行多步骤工具调用任务。在真实企业场景中进行的评估表明，Routine显著提高了模型工具调用的执行准确率，将GPT-4o的性能从41.1%提升至96.3%，将Qwen3-14B的性能从32.6%提升至83.3%。我们进一步构建了一个Routine遵循训练数据集，并对Qwen3-14B进行微调，使其在场景特定评估上的准确率提升至88.2%，表明其对执行计划的遵循能力有所改善。此外，我们采用基于Routine的蒸馏方法创建了一个场景特定的多步骤工具调用数据集。在该蒸馏数据集上进行微调后，模型的准确率提升至95.5%，接近GPT-4o的性能。这些结果凸显了Routine在蒸馏领域特定工具使用模式以及增强模型对新场景适应性方面的有效性。我们的实验结果表明，Routine为构建稳定的智能体工作流提供了一种实用且易于采用的方法，加速了智能体系统在企业环境中的部署和应用，并推动了AI for Process这一技术愿景的发展。
英文摘要：
The deployment of agent systems in an enterprise environment is often hindered by several challenges: common models lack domain-specific process knowledge, leading to disorganized plans, missing key tools, and poor execution stability. To address this, this paper introduces Routine, a multi-step agent planning framework designed with a clear structure, explicit instructions, and seamless parameter passing to guide the agent's execution module in performing multi-step tool-calling tasks with high stability. In evaluations conducted within a real-world enterprise scenario, Routine significantly increases the execution accuracy in model tool calls, increasing the performance of GPT-4o from 41.1% to 96.3%, and Qwen3-14B from 32.6% to 83.3%. We further constructed a Routine-following training dataset and fine-tuned Qwen3-14B, resulting in an accuracy increase to 88.2% on scenario-specific evaluations, indicating improved adherence to execution plans. In addition, we employed Routine-based distillation to create a scenario-specific, multi-step tool-calling dataset. Fine-tuning on this distilled dataset raised the model's accuracy to 95.5%, approaching GPT-4o's performance. These results highlight Routine's effectiveness in distilling domain-specific tool-usage patterns and enhancing model adaptability to new scenarios. Our experimental results demonstrate that Routine provides a practical and accessible approach to building stable agent workflows, accelerating the deployment and adoption of agent systems in enterprise environments, and advancing the technical vision of AI for Process.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
