Year: 2024
Type: conference-paper
Abstract: Multimodal large language models (MLLMs) have shown remarkable potential as human-like autonomous language agents to interact with real-world environments, especially for graphical user interface (GUI) automation.However, those GUI agents require comprehensive cognition including exhaustive perception and reliable action response.We propose a Comprehensive Cognitive LLM Agent, CoCo-Agent, with two novel approaches, comprehensive environment perception (CEP) and conditional action prediction (CAP), to systematically improve the GUI automation performance.First, CEP facilitates the GUI perception through different aspects and granularity, including screenshots and complementary detailed layouts for the visual channel and historical actions for the textual channel.Second, CAP decomposes the action prediction into sub-problems: determining the action type and then identifying the action target conditioned on the action type.With our technical design, our agent achieves state-ofthe-art performance on AITW and META-GUI benchmarks, showing promising abilities in realistic scenarios.
Authors: Xinbei Ma, Zhuosheng Zhang, Hai Zhao
Institution: Shanghai Jiao Tong University
Language: English
Subfield: Software
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
Award: G7272630985
OpenAlex ID: W4402683864