Agentic AI Reasoning for Mobile Edge General Intelligence: Fundamentals, Approaches, and Directions
This work addresses the problem of enabling real-time, privacy-preserving AI reasoning at the network edge for applications in mobile and edge computing, though it appears incremental as it builds on existing methods like CoT and MoE.
The paper tackles the challenge of deploying LLM-based agentic AI reasoning in resource-constrained Mobile Edge General Intelligence (MEGI) environments by proposing a joint optimization framework that dynamically adjusts reasoning depth and expert activation. Experimental results show the framework effectively balances reasoning quality with resource efficiency, validating its practical viability.
The rapid advancement of large language models (LLMs) has enabled an emergence of agentic artificial intelligence (AI) with powerful reasoning and autonomous decision-making capabilities. This integration with edge computing has led to the development of Mobile Edge General Intelligence (MEGI), which brings real-time, privacy-preserving reasoning to the network edge. However, deploying LLM-based agentic AI reasoning in MEGI environments poses significant challenges due to the high computational demands of reasoning and the limited resources of edge devices. To address these challenges, we propose a joint optimization framework for efficient LLM reasoning deployment in MEGI. First, we review methods that enhance LLM reasoning capabilities, such as Chain-of-Thought (CoT) prompting, Supervised Fine-Tuning (SFT), and Mixture of Experts (MoE). Next, we present a distributed framework that addresses two correlated aspects: reasoning enhancement through adaptive CoT prompting and scalable deployment through distributed MoE architecture. The framework dynamically activates expert networks and adjusts reasoning depth based on task complexity and device capabilities. We further conduct experimental evaluations in mobile edge environments. Experimental results demonstrate the framework's effectiveness in balancing reasoning quality with resource efficiency, validating the practical viability of deploying sophisticated LLM reasoning capabilities in resource-constrained MEGI environments.