CoCo-Agent: A Comprehensive Cognitive MLLM Agent for Smartphone GUI Automation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914818547515392 |
|---|---|
| author | Ma, Xinbei Zhang, Zhuosheng Zhao, Hai |
| author_facet | Ma, Xinbei Zhang, Zhuosheng Zhao, Hai |
| contents | 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 ability 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: action type prediction and action target conditioned on the action type. With our technical design, our agent achieves new state-of-the-art performance on AITW and META-GUI benchmarks, showing promising abilities in realistic scenarios. Code is available at https://github.com/xbmxb/CoCo-Agent. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_11941 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | CoCo-Agent: A Comprehensive Cognitive MLLM Agent for Smartphone GUI Automation Ma, Xinbei Zhang, Zhuosheng Zhao, Hai Computation and Language 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 ability 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: action type prediction and action target conditioned on the action type. With our technical design, our agent achieves new state-of-the-art performance on AITW and META-GUI benchmarks, showing promising abilities in realistic scenarios. Code is available at https://github.com/xbmxb/CoCo-Agent. |
| title | CoCo-Agent: A Comprehensive Cognitive MLLM Agent for Smartphone GUI Automation |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2402.11941 |