Routine: A Structural Planning Framework for LLM Agent System in Enterprise
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

TL;DR
Routine is a structured planning framework that significantly improves the stability and accuracy of multi-step tool-calling in enterprise LLM agent systems, facilitating practical deployment and domain adaptation.
Contribution
This paper introduces Routine, a novel multi-step agent planning framework with explicit instructions and parameter passing, enhancing stability and accuracy in enterprise LLM agent systems.
Findings
GPT-4o tool call accuracy increased from 41.1% to 96.3%.
Qwen3-14B accuracy improved from 32.6% to 83.3%.
Fine-tuning with Routine-based datasets further increased accuracy to 95.5%.
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsMulti-Agent Systems and Negotiation · Business Process Modeling and Analysis · Digital Rights Management and Security
