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.
LAMeTA: Intent-Aware Agentic Network Optimization via a Large AI Model-Empowered Two-Stage Approach
College of Computing and Data Science, Nanyang Technological University(南洋理工大学计算与数据科学学院);College of Computer Science and Technology, Jilin University(吉林大学计算机科学与技术学院);Pillar of Information Systems Technology and Design, Singapore University of Technology and Design(新加坡科技设计大学信息系统技术与设计学院);Department of Computer Science and Engineering, Kyung Hee University(韩国庆熙大学计算机科学与工程系)
$Z^2$-ACT: End-to-End Verifiable Agentic Intent Control for Open 6G RAN
School of Computer Science, Dublin City University(都柏林城市大学计算机科学学院);Munster Technological University(芒斯特理工大学);National and Kapodistrian University of Athens(雅典国立与卡波迪斯特里亚大学)
From Code-Centric to Intent-Centric Software Engineering: A Reflexive Thematic Analysis of Generative AI, Agentic Systems, and Engineering Accountability
Agentic TinyML for Intent-aware Handover in 6G Wireless Networks
Center for Ubiquitous Computing(无处不在计算中心);University of Oulu(奥卢大学);Department of Communication Systems(通信系统系);EURECOM;Department of Computer Science(计算机科学系);University of Helsinki(赫尔辛基大学);RISE Research Institutes of Sweden(瑞典研究机构);Department of Computer Science, Electrical and Space Engineering(计算机科学、电气与空间工程系);Luleå University of Technology(卢勒奥技术大学)
Beyond the 'Diff': Addressing Agentic Entropy in Agentic Software Development
Dipartimento Tecnologie Innovative, SUPSI(技术创新部,SUPSI);Dalle Molle Institute for Artificial Intelligence (IDSIA), SUPSI(达勒莫利人工智能研究所(IDSIA),SUPSI);Management in Networked and Digital Societies (MINDS) Department, Kozminski University(网络化与数字化社会管理(MINDS)系,科津斯基大学);Institute of Biomedical Ethics and History of Medicine, University of Zurich(生物医学伦理与医学史研究所,苏黎世大学);ETH Zurich(苏黎世联邦理工学院)
MAGMA: A Multi-Graph based Agentic Memory Architecture for AI Agents
Department of Computer Science, The University of Texas at Dallas(德克萨斯大学达拉斯分校计算机科学系);Department of Electrical and Computer Engineering, University of Florida(佛罗里达大学电气与计算机工程系)
Limits to Verification and Validation of Agentic Behavior
代理行为的验证和确认已被建议作为重要的研究重点,以减少与创建通用人工智能相关的风险(Russell et al 2015)。在本文中,我们质疑使用语言的确定性方面的努力,以管理这种风险的适当性。我们首先建立了一个非常一般的形式主义来描述代理行为和可接受的行为的标准。我们表明,确定一个代理是否符合任何特定的标准是不可计算的。我们讨论了与人工证明和自动化行为治理验证相关的负担程度。我们表明,为了确保行为标准本身的可判定性,必须进一步限制代理的能力。然后,我们证明,如果我们的关注涉及到在物理世界的结果,验证的尝试是徒劳的。最后,我们表明,分层架构旨在使这些挑战易于处理的错误等同于意图与行动或结果,从而无法提供任何保证。最后,我们讨论了为什么确定性语言应该从关于一般人工智能安全性的对话中根除。
CoGen3D: An Agentic Human-AI Co-Design Pipeline for 3D Asset Generation for Virtual Reality
Nanjing University of Information Science and Technology(南京信息工程大学);Japan Advanced Institute of Science and Technology(日本科学技术大学);The University of Sydney(悉尼大学);University of Copenhagen(哥本哈根大学);TU Dortmund University(多特蒙德技术大学);Research Center Trustworthy Data Science and Security(可信数据科学与安全研究中心)
University of Houston–Clear Lake(休斯顿大学清水湖分校);Infodat International Inc.(信息数据国际公司);Cardinal Health(红衣主教健康公司);Fontus Labs Inc.(方图斯实验室公司);Stockton University(斯托克顿大学)
A Quantum-Assisted Agentic Distributed Artificial Intelligence Framework for Deadline-Bounded Orchestration of Hybrid Renewable Microgrids
Philips University(菲利普斯大学);University of Cyprus(塞浦路斯大学);CYENS Centre of Excellence(CYENS卓越中心);Japan Advanced Institute of Science and Technology(日本先端科学技术大学院大学);Doshisha University(同志社大学)