The emerging convergence of next-generation wireless networks and agentic artificial intelligence (AI) is inspiring a new vision: embodied intelligent network entities utilize environmental sensing to refine their physical-layer (PHY) actions. Despite a growing body of preliminary work, prevailing small and task-specific AI models require extensive manual design of data pre-processing, network architecture, and fine-tuning, leaving them tightly coupled to particular PHY actions, system configurations, and deployment scenarios. To address this, we propose a paradigm shift with WiFo-M2, a foundation model that enables environment sensing to be easily integrated into PHY actions, delivering universal performance gains. To extract generalizable out-of-band (OOB) channel-aware features from environment sensing, we introduce ContraSoM, a contrastive pre-training strategy. Once pre-trained, WiFo-M2 infers future OOB channel-aware features from historical sensory data and strengthens feature robustness via modality-specific data augmentation. Experiments show that WiFo-M2 improves the performance of diverse PHY actions and demonstrates strong generalization to unseen scenarios.
@article{arxiv.2601.09179,
title = {WiFo-M$^2$: Empower Wireless Communications With Plug-and-Play Environment Sensing via Foundation Model},
author = {Haotian Zhang and Shijian Gao and Xiang Cheng},
journal= {arXiv preprint arXiv:2601.09179},
year = {2026}
}