{"ID":2892730,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.14447","arxiv_id":"2507.14447","title":"Routine: A Structural Planning Framework for LLM Agent System in Enterprise","abstract":"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.","short_abstract":"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 framewor...","url_abs":"https://arxiv.org/abs/2507.14447","url_pdf":"https://arxiv.org/pdf/2507.14447v2","authors":"[\"Guancheng Zeng\",\"Xueyi Chen\",\"Jiawang Hu\",\"Shaohua Qi\",\"Yaxuan Mao\",\"Zhantao Wang\",\"Yifan Nie\",\"Shuang Li\",\"Qiuyang Feng\",\"Pengxu Qiu\",\"Yujia Wang\",\"Wenqiang Han\",\"Linyan Huang\",\"Gang Li\",\"Jingjing Mo\",\"Haowen Hu\"]","published":"2025-07-19T02:46:19Z","proceeding":"cs.AI","tasks":"[\"cs.AI\",\"cs.CL\"]","methods":"[\"Large Language Model\",\"Generative Adversarial Network\"]","has_code":false}