Towards Edge General Intelligence: Knowledge Distillation for Mobile Agentic AI

2025-11-25

AI Summary

To address the challenge of efficiently deploying autonomous intelligent agents on resource-constrained devices in mobile edge computing, this paper proposes the Edge General Intelligence (EGI) framework. It introduces a novel wireless-communication-aware knowledge distillation paradigm, comprising channel-aware self-distillation, CSI feedback distillation, and robust modulation classification distillation. The method synergistically integrates state-space models—including Mamba and RWKV—with cross-architecture distillation mechanisms to jointly optimize model lightweighting and communication awareness. Experimental results demonstrate significant reductions in computational and communication overhead across vision, speech, and multimodal tasks. The EGI framework enhances inference efficiency, generalization capability, and scalability at the edge, thereby establishing a systematic technical pathway for deploying autonomous intelligent agents under stringent resource constraints.

Technology Category

• Machine Learning: Learning on the Edge & Model Compression
• Multiagent Systems: Agent Communication
• Cognitive Modeling & Cognitive Systems: Agent Architectures

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Agentic search

Abstract

Edge General Intelligence (EGI) represents a paradigm shift in mobile edge computing, where intelligent agents operate autonomously in dynamic, resource-constrained environments. However, the deployment of advanced agentic AI models on mobile and edge devices faces significant challenges due to limited computation, energy, and storage resources. To address these constraints, this survey investigates the integration of Knowledge Distillation (KD) into EGI, positioning KD as a key enabler for efficient, communication-aware, and scalable intelligence at the wireless edge. In particular, we emphasize KD techniques specifically designed for wireless communication and mobile networking, such as channel-aware self-distillation, cross-model Channel State Information (CSI) feedback distillation, and robust modulation/classification distillation. Furthermore, we review novel architectures natively suited for KD and edge deployment, such as Mamba, RWKV (Receptance, Weight, Key, Value) and Cross-Architecture distillation, which enhance generalization capabilities. Subsequently, we examine diverse applications in which KD-driven architectures enable EGI across vision, speech, and multimodal tasks. Finally, we highlight the key challenges and future directions for KD in EGI. This survey aims to provide a comprehensive reference for researchers exploring KD-driven frameworks for mobile agentic AI in the era of EGI.

Problem

• Deploying advanced AI agents on resource-limited mobile edge devices
• Enabling efficient intelligence through knowledge distillation for wireless edge
• Enhancing generalization with novel architectures for mobile agentic AI

Innovation

• Knowledge distillation enables efficient edge intelligence
• Channel-aware distillation optimizes wireless communication
• Novel architectures enhance generalization for edge deployment