Mingfei Gao, Rui Tian, Haiming Gang, Bohan Zhai, Le Zhang, Yuanzheng Gong, Di Feng, Ege Özsoy, Kaixin Ma, Vishwesh Kirthivasan, Oğuzhan Fatih Kar, Roman Bachmann, Anders Boesen Lindbo Larsen, Afshin Dehghan
MintAct is a unified visual agent for digital environments, achieving state-of-the-art performance across various benchmarks. It unifies UI grounding, navigation, and visual tool use through a scalable environment and reinforcement learning infrastructure. MintAct models match per-domain specialists' performance at comparable model sizes.
MintAct's unified approach enables more efficient and effective interaction with digital environments, potentially improving user experience and automation. Its scalability and performance make it a significant step towards more generalizable and applicable AI models. This can have practical implications for various applications, including virtual assistance and automation.
Thank you to arXiv for use of its open access interoperability. arxiv.org. aibrief.ai is not affiliated with or endorsed by arXiv.