---
title: "Horae: A Domain-Agnostic Language for Automated Service Regulation"
authors:
  - "Yutao Sun"
  - "Mingshuai Chen"
  - "Tiancheng Zhao"
  - "Kangjia Zhao"
  - "He Li"
  - "Jintao Chen"
  - "Zhongyi Wang"
  - "Liqiang Lu"
  - "Xinkui Zhao"
  - "Shuiguang Deng"
  - "Jianwei Yin"
doi: "10.24963/ijcai.2025/1039"
url: "https://ijcai.org/proceedings/2025/1039"
pdf: "https://ijcai.org/proceedings/2025/1039.pdf"
venue: "Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence"
year: 2025
pages: "9349-9356"
track: "AI4Tech: AI Enabling Technologies"
keywords:
  - "Domain-specific AI4Tech: AI4Regulation"
  - "Advanced AI4Tech: Generative and LLMs-driven AI4Tech"
---

# Horae: A Domain-Agnostic Language for Automated Service Regulation

Yutao Sun, Mingshuai Chen, Tiancheng Zhao, Kangjia Zhao, He Li, Jintao Chen, Zhongyi Wang, Liqiang Lu, Xinkui Zhao, Shuiguang Deng, Jianwei Yin

*Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence*, pages 9349-9356. DOI: [10.24963/ijcai.2025/1039](https://doi.org/10.24963/ijcai.2025/1039)

## Abstract

Artificial intelligence is rapidly encroaching on the field of service regulation. However, existing AI-based regulation techniques are often tailored to specific application domains and thus are difficult to generalize in an automated manner. This paper presents Horae, a unified specification language for modeling (multimodal) regulation rules across a diverse set of domains. We showcase how Horae facilitates an intelligent service regulation pipeline by further exploiting a fine-tuned large language model named RuleGPT that automates the Horae modeling process, thereby yielding an end-to-end framework for fully automated intelligent service regulation. The feasibility and effectiveness of our framework are demonstrated over a benchmark of various real-world regulation domains. In particular, we show that our open-sourced, fine-tuned RuleGPT with 7B parameters suffices to outperform GPT-3.5 and perform on par with GPT-4o.