Agentic Wireless Communication for 6G: Intent-Aware and Continuously Evolving Physical-Layer Intelligence

TL;DR

The paper argues that 6G networks should transition from fixed, rule-based optimization to intent-aware, autonomous control driven by agentic AI and LLMs. It surveys key physical-layer tasks, identifies limitations of traditional, DL, and LLM approaches under dynamic, multi-objective conditions, and introduces AgenCom, an intent-aware agent that perceives multimodal inputs and outputs cohesive, cross-layer link configurations. The work details an architecture combining multimodal perception, an LLM-based domain-adaptive policy network, structured action generation, and tool-assisted learning, supported by a case study showing how different user intents yield distinct, consistent trade-offs among reliability, throughput, and energy. Collectively, the article outlines challenges and enabling technologies for domain-adaptive deployment and presents a practical pathway toward scalable, user-centric, autonomous 6G networks that continually evolve with environment and intent.

Abstract

As 6G wireless systems evolve, growing functional complexity and diverse service demands are driving a shift from rule-based control to intent-driven autonomous intelligence. User requirements are no longer captured by a single metric (e.g., throughput or reliability), but by multi-dimensional objectives such as latency sensitivity, energy preference, computational constraints, and service-level requirements. These objectives may also change over time due to environmental dynamics and user-network interactions. Therefore, accurate understanding of both the communication environment and user intent is critical for autonomous and sustainably evolving 6G communications. Large language models (LLMs), with strong contextual understanding and cross-modal reasoning, provide a promising foundation for intent-aware network agents. Compared with rule-driven or centrally optimized designs, LLM-based agents can integrate heterogeneous information and translate natural-language intents into executable control and configuration decisions. Focusing on a closed-loop pipeline of intent perception, autonomous decision making, and network execution, this paper investigates agentic AI for the 6G physical layer and its realization pathways. We review representative physical-layer tasks and their limitations in supporting intent awareness and autonomy, identify application scenarios where agentic AI is advantageous, and discuss key challenges and enabling technologies in multimodal perception, cross-layer decision making, and sustainable optimization. Finally, we present a case study of an intent-driven link decision agent, termed AgenCom, which adaptively constructs communication links under diverse user preferences and channel conditions.

Figures (3)

• Figure 1: Applications, mechanisms, and enabling techniques for agent.
• Figure 2: Proposed intent-aware communication agent.
• Figure 3: Case studies of proposed Agent. (a) Comparison of output strategies for different user needs; (b) User Interaction Case.