Task-oriented dialogue (TOD) systems have been widely used by mobile phone intelligent assistants to accomplish tasks such as calendar scheduling or hotel reservation. Current TOD systems usually focus on multi-turn text/speech interaction, then they would call back-end APIs designed for TODs to perform the task. However, this API-based architecture greatly limits the information-searching capability of intelligent assistants and may even lead to task failure if TOD-specific APIs are not available or the task is too complicated to be executed by the provided APIs. In this paper, we propose a new TOD architecture: GUI-based task-oriented dialogue system (GUI-TOD). A GUI-TOD system can directly perform GUI operations on real APPs and execute tasks without invoking TOD-specific backend APIs. Furthermore, we release META-GUI, a dataset for training a Multi-modal convErsaTional Agent on mobile GUI. We also propose a multi-model action prediction and response model, which show promising results on META-GUI. The dataset, codes and leaderboard are publicly available.
@article{arxiv.2205.11029,
title = {META-GUI: Towards Multi-modal Conversational Agents on Mobile GUI},
author = {Liangtai Sun and Xingyu Chen and Lu Chen and Tianle Dai and Zichen Zhu and Kai Yu},
journal= {arXiv preprint arXiv:2205.11029},
year = {2024}
}