META-GUI: Towards Multi-modal Conversational Agents on Mobile GUI
This addresses the problem of restricted information-searching and task failure in mobile intelligent assistants, offering a more flexible approach, though it appears incremental as it builds on existing TOD systems.
The paper tackles the limitation of API-based task-oriented dialogue systems by proposing a GUI-based architecture that directly interacts with mobile apps, and they release the META-GUI dataset and a model showing promising results.
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.