[2602.24142] CoME: Empowering Channel-of-Mobile-Experts with Informative Hybrid-Capabilities Reasoning

Computer Science > Computation and Language arXiv:2602.24142 (cs) [Submitted on 27 Feb 2026] Title:CoME: Empowering Channel-of-Mobile-Experts with Informative Hybrid-Capabilities Reasoning Authors:Yuxuan Liu, Weikai Xu, Kun Huang, Changyu Chen, Jiankun Zhao, Pengzhi Gao, Wei Liu, Jian Luan, Shuo Shang, Bo Du, Ji-Rong Wen, Rui Yan View a PDF of the paper titled CoME: Empowering Channel-of-Mobile-Experts with Informative Hybrid-Capabilities Reasoning, by Yuxuan Liu and 11 other authors View PDF HTML (experimental) Abstract:Mobile Agents can autonomously execute user instructions, which requires hybrid-capabilities reasoning, including screen summary, subtask planning, action decision and action function. However, existing agents struggle to achieve both decoupled enhancement and balanced integration of these capabilities. To address these challenges, we propose Channel-of-Mobile-Experts (CoME), a novel agent architecture consisting of four distinct experts, each aligned with a specific reasoning stage, CoME activates the corresponding expert to generate output tokens in each reasoning stage via output-oriented activation. To empower CoME with hybrid-capabilities reasoning, we introduce a progressive training strategy: Expert-FT enables decoupling and enhancement of different experts' capability; Router-FT aligns expert activation with the different reasoning stage; CoT-FT facilitates seamless collaboration and balanced optimization across multiple capabilities. To mitigate e...