Towards Resilient and Autonomous Networks: A BlueSky Vision on AI-Native 6G

Kelly Wan; Liangjie Hong; Liang Wu; Mayank Darbari

arxiv: 2605.21395 · v1 · pith:RFDIF233new · submitted 2026-05-20 · 💻 cs.AI · cs.LG

Towards Resilient and Autonomous Networks: A BlueSky Vision on AI-Native 6G

Liang Wu , Kelly Wan , Mayank Darbari , Liangjie Hong This is my paper

Pith reviewed 2026-05-21 04:12 UTC · model grok-4.3

classification 💻 cs.AI cs.LG

keywords AI-native 6Gfoundation modelsmulti-agent systemsnetwork resilienceautonomous networksAI for networksself-sustaining infrastructure

0 comments

The pith

6G networks will use one foundation model plus multi-agent systems to manage themselves autonomously.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper argues that cellular networks must move beyond faster speeds to become fundamentally more resilient and autonomous to support new uses like self-driving cars and immersive media. It contrasts 5G's collection of separate, single-purpose AI models with a 6G approach built around one large foundation model that handles many tasks at once. This model would be paired with teams of collaborating agents that diagnose problems, perform maintenance, and restore service with little human input. The result would turn network operations into a single, multi-modal optimization task instead of many isolated ones. Distilling the big model down to smaller versions would let the same intelligence run on edge devices throughout the network.

Core claim

Native AI in the 6G era will be anchored by a foundation model and orchestrated via collaborative multi-agent systems, framing network management as a unified, multi-modal, multi-task optimization problem. This leads to two concrete directions: building the 6G foundation model as a unified backbone whose knowledge can be distilled into compact models for edge use, and advancing multi-agent systems that autonomously diagnose, maintain, and recover networks with minimal human intervention.

What carries the argument

A 6G foundation model as unified backbone, with knowledge distilled into compact edge models and orchestration supplied by collaborative multi-agent systems.

If this is right

Network management is reframed as one unified multi-modal multi-task optimization problem instead of many separate ad-hoc tasks.
Task-specific knowledge is distilled from the foundation model into compact models suitable for diverse edge deployments.
Multi-agent systems autonomously diagnose, maintain, and recover networks with minimal human intervention.
6G evolves into an intelligent, self-sustaining communication infrastructure.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

Such systems could reduce the human workforce needed to operate large cellular networks over time.
The approach might connect to wider uses of foundation models for controlling other large physical systems beyond communications.
Real-world validation would require measuring recovery speed and stability after injected network faults under both current and proposed architectures.

Load-bearing premise

A single foundation model can serve as an effective unified backbone for diverse network tasks and distill successfully into compact edge models, while multi-agent systems can autonomously diagnose, maintain, and recover networks with minimal human intervention.

What would settle it

A controlled test in which current scattered task-specific models outperform the proposed foundation-model approach on combined network management tasks, or in which multi-agent systems require repeated human intervention to restore service after simulated outages.

read the original abstract

The proliferation of emerging applications, such as autonomous driving and immersive experiences, demands cellular networks that are not only faster, but fundamentally more resilient and autonomous. This paper presents a BlueSky vision on how Artificial Intelligence will be natively integrated into 6G, shifting the paradigm from \underline{Network for AI} to \underline{AI for Network}. We envision that, unlike 5G's reliance on scattered, ad-hoc models each trained for a single task, native AI in the 6G era will be anchored by a foundation model and and orchestrated via collaborative multi-agent systems, framing network management as a unified, multi-modal, multi-task optimization problem. Built on this vision, we outline two transformative directions. The first focuses on developing a 6G foundation model as a unified backbone, with task-specific knowledge distilled into compact models suited for diverse edge deployments. The second advances multi-agent systems designed to autonomously diagnose, maintain, and recover networks with minimal human intervention. These directions chart a roadmap for 6G to evolve into an intelligent, self-sustaining communication infrastructure.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Desk Editor's Note private letter to a colleague

This is a high-level vision paper sketching AI-native 6G via a foundation model plus multi-agent orchestration, but it contains no technical content or evidence.

read the letter

This paper is a forward-looking outline for making 6G networks more autonomous through native AI. It contrasts 5G's scattered task-specific models with a proposed unified foundation model that gets distilled for edge use, plus multi-agent systems to handle diagnosis, maintenance, and recovery with little human input. The core framing treats network management as one big multi-modal, multi-task problem. That is the main thing to take away: it is a roadmap, not a solved problem or new method. The authors do a reasonable job laying out two clear directions and tying them to real application needs like autonomous driving and immersive services. The writing keeps the ideas accessible and shows how recent AI trends could map onto wireless infrastructure. The soft spots are straightforward. The entire argument rests on unexamined assumptions about whether a single foundation model can handle the range of network tasks at scale or whether agent systems can deliver reliable autonomy in live deployments. No feasibility checks, no discussion of compute costs, latency, data needs, or failure modes appear. The paper offers no experiments, derivations, or even worked examples to ground the claims. This leaves the vision interesting on paper but hard to assess for practicality. The work is for readers who follow long-term 6G planning or who want prompts for future research agendas. It will not help someone looking for algorithms, datasets, or reproducible results they can use now. I would send it to peer review at a venue that accepts vision or position papers. Feedback could push the authors to add concrete next steps or risk analysis, which would make the ideas more useful.

Referee Report

0 major / 1 minor

Summary. The paper presents a BlueSky vision on the native integration of Artificial Intelligence into 6G networks, shifting the paradigm from Network for AI to AI for Network. It envisions that 6G will be anchored by a foundation model orchestrated via collaborative multi-agent systems, framing network management as a unified, multi-modal, multi-task optimization problem. Two transformative directions are outlined: the development of a 6G foundation model as a unified backbone with task-specific knowledge distilled into compact edge models, and the advancement of multi-agent systems for autonomous network diagnosis, maintenance, and recovery with minimal human intervention.

Significance. This vision, if realized, could transform cellular networks into intelligent, self-sustaining infrastructures better suited for emerging applications like autonomous driving and immersive experiences. The proposal to move beyond 5G's scattered ad-hoc models to a unified foundation model and multi-agent orchestration offers a coherent framework for future research in AI-native networking. The manuscript provides a clear roadmap that could stimulate targeted investigations in foundation models and autonomous systems for communications.

minor comments (1)

[Abstract] The sentence 'anchored by a foundation model and and orchestrated via collaborative multi-agent systems' contains a duplicated word 'and'.

Simulated Author's Rebuttal

0 responses · 0 unresolved

We thank the referee for their positive assessment of the manuscript and for recommending acceptance. We are encouraged by the recognition of the vision's potential to provide a coherent framework for AI-native 6G research.

Circularity Check

0 steps flagged

No significant circularity in this high-level vision paper

full rationale

The manuscript is explicitly a BlueSky vision paper that outlines aspirational research directions for AI-native 6G rather than presenting equations, algorithms, empirical results, or derivations. The central premise regarding a foundation model and multi-agent orchestration is framed as a conceptual roadmap for future work, with no fitted parameters, self-definitional steps, or load-bearing self-citations that reduce claims to their own inputs by construction. No technical derivations exist to analyze for circularity, rendering the paper self-contained as a forward-looking outline.

Axiom & Free-Parameter Ledger

0 free parameters · 2 axioms · 1 invented entities

The vision depends on untested assumptions about AI scalability in network environments and introduces conceptual constructs without independent validation or technical specifications.

axioms (2)

domain assumption A foundation model can serve as a unified backbone for multi-modal, multi-task network optimization in 6G.
Invoked as the core of the first transformative direction without evidence of feasibility or performance bounds.
domain assumption Collaborative multi-agent systems can autonomously diagnose, maintain, and recover networks with minimal human intervention.
Central premise of the second direction, presented without supporting mechanisms or prior validation.

invented entities (1)

6G foundation model no independent evidence
purpose: Unified backbone from which task-specific knowledge is distilled into compact models for edge deployments.
New conceptual entity introduced to anchor native AI in 6G, with no independent evidence or existence outside this vision.

pith-pipeline@v0.9.0 · 5728 in / 1466 out tokens · 77016 ms · 2026-05-21T04:12:06.814951+00:00 · methodology

discussion (0)

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

IndisputableMonolith/Foundation/RealityFromDistinction.lean reality_from_one_distinction unclear

?

unclear
Relation between the paper passage and the cited Recognition theorem.

native AI in the 6G era will be anchored by a foundation model and orchestrated via collaborative multi-agent systems, framing network management as a unified, multi-modal, multi-task optimization problem

What do these tags mean?

matches: The paper's claim is directly supported by a theorem in the formal canon.
supports: The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends: The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses: The paper appears to rely on the theorem as machinery.
contradicts: The paper's claim conflicts with a theorem or certificate in the canon.
unclear: Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Reference graph

Works this paper leans on

46 extracted references · 46 canonical work pages · 3 internal anchors

[1]

Bharat Agarwal, Mohammed Amine Togou, Marco Marco, and Gabriel-Miro Muntean. 2022. A comprehensive survey on radio resource management in 5G HetNets: Current solutions, future trends and open issues.IEEE Communications Surveys & Tutorials24, 4 (2022), 2495–2534

work page 2022
[2]

Hafiz Farooq Ahmad, Wajid Rafique, Raihan Ur Rasool, Abdulaziz Alhumam, Zahid Anwar, and Junaid Qadir. 2023. Leveraging 6G, extended reality, and IoT big data analytics for healthcare: A review.Computer Science Review48 (2023), 100558

work page 2023
[3]

Irfan Ahmed, Hedi Khammari, Adnan Shahid, Ahmed Musa, Kwang Soon Kim, Eli De Poorter, and Ingrid Moerman. 2018. A survey on hybrid beamforming tech- niques in 5G: Architecture and system model perspectives.IEEE Communications Surveys & Tutorials20, 4 (2018), 3060–3097

work page 2018
[4]

Abdul Fatir Ansari, Oleksandr Shchur, Jaris Küken, Andreas Auer, Boran Han, Pedro Mercado, Syama Sundar Rangapuram, Huibin Shen, Lorenzo Stella, Xiyuan Zhang, et al. 2025. Chronos-2: From univariate to universal forecasting.arXiv preprint arXiv:2510.15821(2025)

work page internal anchor Pith review Pith/arXiv arXiv 2025
[5]

Abdul Fatir Ansari, Lorenzo Stella, Caner Turkmen, Xiyuan Zhang, Pedro Mercado, Huibin Shen, Oleksandr Shchur, Syama Sundar Rangapuram, Sebas- tian Pineda Arango, Shubham Kapoor, et al. 2024. Chronos: Learning the language of time series.arXiv preprint arXiv:2403.07815(2024)

work page internal anchor Pith review Pith/arXiv arXiv 2024
[6]

Sihem Baccari, Mohamed Hadded, Hakim Ghazzai, Haifa Touati, and Mourad Elhadef. 2024. Anomaly detection in connected and autonomous vehicles: A survey, analysis, and research challenges.IEEE access12 (2024), 19250–19276

work page 2024
[7]

Osman Tugay Basaran, Hammad Zafar, Martin Kasparick, Falko Dressler, and Slawomir Stańczak. 2025. Next-Gen AI-on-RAN: AI-native, Interoperable, and GPU-Accelerated Testbed Towards 6G Open-RAN. InICC 2025-IEEE International Conference on Communications. IEEE, 5362–5367

work page 2025
[8]

Robin Chataut, Mary Nankya, and Robert Akl. 2024. 6G networks and the AI revolution—Exploring technologies, applications, and emerging challenges. Sensors24, 6 (2024), 1888

work page 2024
[9]

Daihang Chen, Yonghui Liu, Mingyi Zhou, Yanjie Zhao, Haoyu Wang, Shuai Wang, Xiao Chen, Tegawendé F Bissyandé, Jacques Klein, and Li Li. 2025. Llm for mobile: An initial roadmap.ACM Transactions on Software Engineering and Methodology34, 5 (2025), 1–29

work page 2025
[10]

Na Chen, Jingyu Zhou, Hui Guan, Nan Xu, Sheng Xue, Shuting Li, and Zhiqiong Liu. 2023. 5G charging mechanism based on dynamic step size.IEEE Access11 (2023), 15069–15081

work page 2023
[11]

Ben Cohen, Emaad Khwaja, Kan Wang, Charles Masson, Elise Ramé, Youssef Doubli, and Othmane Abou-Amal. 2024. Toto: Time series optimized transformer for observability.arXiv preprint arXiv:2407.07874(2024)

work page arXiv 2024
[12]

Austin Feng, Andreas Varvarigos, Ioannis Panitsas, Daniela Fernandez, Jinbiao Wei, Yuwei Guo, Jialin Chen, Ali Maatouk, Leandros Tassiulas, and Rex Ying

work page
[13]

TelecomTS: A Multi-Modal Observability Dataset for Time Series and Language Analysis.arXiv preprint arXiv:2510.06063(2025)

work page internal anchor Pith review Pith/arXiv arXiv 2025
[14]

Jianhua He, Kun Yang, and Hsiao-Hwa Chen. 2020. 6G cellular networks and connected autonomous vehicles.IEEE network35, 4 (2020), 255–261

work page 2020
[15]

Peng Hu and Jinhuan Zhang. 2020. 5G-enabled fault detection and diagnostics: How do we achieve efficiency?IEEE Internet of Things Journal7, 4 (2020), 3267– 3281

work page 2020
[16]

Siva Rama Krishna Kottapalli, Karthik Hubli, Sandeep Chandrashekhara, Garima Jain, Sunayana Hubli, Gayathri Botla, and Ramesh Doddaiah. 2025. Foundation models for time series: A survey.arXiv preprint arXiv:2504.04011(2025)

work page arXiv 2025
[17]

Kirill Krinkin, Alexander Vodyaho, Igor Kulikov, and Nataly Zhukova. 2020. Models of telecommunications network monitoring based on knowledge graphs. In2020 9th Mediterranean Conference on Embedded Computing (MECO). IEEE, 1–7

work page 2020
[18]

Samir Kumar. 2025. Nokia launches Nokia RAN Digital Twin to turbo-charge AI-native 6G, powered by NVIDIA Aerial Omniverse Digital Twin. InNokia Engineering Blog

work page 2025
[19]

2025.5G/5G-Advanced Networks: Planning, Design, and Optimization

Christofer Larsson. 2025.5G/5G-Advanced Networks: Planning, Design, and Optimization. Academic Press

work page 2025
[20]

Zhenyu Lei, Qiong Wu, JIANXIONG DONG, Yinhan He, Emily Dodwell, Yushun Dong, and Jundong Li. [n. d.]. Reforming the Mechanism: Editing Reasoning Pat- terns in LLMs with Circuit Reshaping. InThe Fourteenth International Conference on Learning Representations

work page
[21]

João PSH Lima, Álvaro AM de Medeiros, Eduardo P de Aguiar, Edelberto F Silva, Vicente A de Sousa, Marcelo L Nunes, and Alysson L Reis. 2023. Deep learning-based handover prediction for 5G and beyond networks. InICC 2023- IEEE International Conference on Communications. IEEE, 3468–3473

work page 2023
[22]

An Liu, Zhe Huang, Min Li, Yubo Wan, Wenrui Li, Tony Xiao Han, Chenchen Liu, Rui Du, Danny Kai Pin Tan, Jianmin Lu, et al. 2022. A survey on fundamental limits of integrated sensing and communication.IEEE Communications Surveys & Tutorials24, 2 (2022), 994–1034

work page 2022
[23]

Chenghao Liu, Taha Aksu, Juncheng Liu, Xu Liu, Hanshu Yan, Quang Pham, Silvio Savarese, Doyen Sahoo, Caiming Xiong, and Junnan Li. 2025. Moirai 2.0: When less is more for time series forecasting.arXiv preprint arXiv:2511.11698 (2025)

work page arXiv 2025
[24]

Ali Maatouk, Nicola Piovesan, Fadhel Ayed, Antonio De Domenico, and Mer- ouane Debbah. 2024. Large language models for telecom: Forthcoming impact on the industry.IEEE Communications Magazine63, 1 (2024), 62–68

work page 2024
[25]

Wooseok Nam, Dongwoon Bai, Jungwon Lee, and Inyup Kang. 2014. Advanced interference management for 5G cellular networks.IEEE Communications Maga- zine52, 5 (2014), 52–60

work page 2014
[26]

Huan X Nguyen, Ramona Trestian, Duc To, and Mallik Tatipamula. 2021. Digital twin for 5G and beyond.IEEE Communications Magazine59, 2 (2021), 10–15

work page 2021
[27]

Gaoyang Pang, Wanchun Liu, Chentao Yue, Daniel E Quevedo, Karl H Johans- son, Branka Vucetic, and Yonghui Li. 2026. Toward Wireless Human-Machine Collaboration in the 6G Era.arXiv preprint arXiv:2602.22662(2026)

work page arXiv 2026
[28]

Seongmin Park, Sungmoon Kwon, Youngkwon Park, Dowon Kim, and Ilsun You

work page
[29]

Session management for security systems in 5g standalone network.IEEE Access10 (2022), 73421–73436

work page 2022
[30]

Imtiaz Parvez, Ali Rahmati, Ismail Guvenc, Arif I Sarwat, and Huaiyu Dai. 2018. A survey on low latency towards 5G: RAN, core network and caching solutions. IEEE Communications Surveys & Tutorials20, 4 (2018), 3098–3130

work page 2018
[31]

Diego Frazatto Pedroso, Luís Almeida, Lucas Eduardo Gulka Pulcinelli, William Akihiro Alves Aisawa, Inês Dutra, and Sarita Mazzini Bruschi. 2025. Anomaly detection and root cause analysis in cloud-native environments using large language models and Bayesian networks.IEEE Access(2025)

work page 2025
[32]

Jordi Pérez-Romero, Oriol Sallent, Ramon Ferrús, and Ramón Agustí. 2015. Arti- ficial intelligence-based 5G network capacity planning and operation. In2015 International Symposium on Wireless Communication Systems (ISWCS). IEEE, 246–250

work page 2015
[33]

Matteo Pozza, Patrick K Nicholson, Diego F Lugones, Ashwin Rao, Hannu Flinck, and Sasu Tarkoma. 2020. On reconfiguring 5G network slices.IEEE Journal on Selected Areas in Communications38, 7 (2020), 1542–1554

work page 2020
[34]

Guanqiao Qu, Qiyuan Chen, Wei Wei, Zheng Lin, Xianhao Chen, and Kaibin Huang. 2025. Mobile edge intelligence for large language models: A contempo- rary survey.IEEE Communications Surveys & Tutorials27, 6 (2025), 3820–3860

work page 2025
[35]

Banoth Ravi and Utkarsh Verma. 2025. Spectrum allocation in 5G and beyond intelligent ubiquitous networks.International Journal of Network Management 35, 1 (2025), e2315

work page 2025
[36]

Sharief Saleh, Pinjun Zheng, Xing Liu, Hui Chen, Musa Furkan Keskin, Basuki Priyanto, Martin Beale, Yasaman Ettefagh, Gonzalo Seco-Granados, Tareq Y Al-Naffouri, et al. 2025. Integrated 6G TN and NTN localization: Challenges, opportunities, and advancements.IEEE Communications Standards Magazine (2025)

work page 2025
[37]

Adnan Shahid, Adrian Kliks, Ahmed Al-Tahmeesschi, Ahmed Elbakary, Alexan- dros Nikou, Ali Maatouk, Ali Mokh, Amirreza Kazemi, Antonio De Domenico, Athanasios Karapantelakis, et al. 2025. Large-scale AI in telecom: Charting the roadmap for innovation, scalability, and enhanced digital experiences.arXiv preprint arXiv:2503.04184(2025)

work page arXiv 2025
[38]

Rakesh Shrestha, Rojeena Bajracharya, and Shiho Kim. 2021. 6G enabled un- manned aerial vehicle traffic management: A perspective.IEEe Access9 (2021), 91119–91136

work page 2021
[39]

Ma- rina, and Bozidar Radunovic

Chuanhao Sun, Ujjwal Pawar, Molham Khoja, Xenofon Foukas, Mahesh K. Ma- rina, and Bozidar Radunovic. 2024. SpotLight: Accurate, explainable and efficient anomaly detection for Open RAN. InProceedings of the 30th Annual International Conference on Mobile Computing and Networking. ACM. The 30th Annual Inter- national Conference On Mobile Computing And Netwo...

work page 2024
[40]

Harsh Tataria, Mansoor Shafi, Andreas F Molisch, Mischa Dohler, Henrik Sjö- land, and Fredrik Tufvesson. 2021. 6G wireless systems: Vision, requirements, challenges, insights, and opportunities.Proc. IEEE109, 7 (2021), 1166–1199

work page 2021
[41]

Lei Yang, Shaobo Li, Yizong Zhang, Caichao Zhu, and Zihao Liao. 2024. Deep learning-assisted unmanned aerial vehicle flight data anomaly detection: A review.IEEE Sensors Journal24, 20 (2024), 31681–31695

work page 2024
[42]

Hao Yu, Masoud Shokrnezhad, Tarik Taleb, Richard Li, and JaeSeung Song. 2023. Toward 6g-based metaverse: Supporting highly-dynamic deterministic multi- user extended reality services.IEEE Network37, 4 (2023), 30–38

work page 2023
[43]

Mohammad Zeeshan, Rahul Raj, Amit Anand, Ankur Pandey, Mohammad Tabrez Quasim, Joaquín Torres-Sospedra, Sudhir Kumar, and Kapal Dev. 2025. Knowl- edge distillation-based AIoT framework for efficient wireless gesture sensing in B5G/6G networks.IEEE Network(2025)

work page 2025
[44]

Jiamu Zhang, Shaochen Zhong, Andrew Ye, Zirui Liu, Sebastian Zhao, Kaixiong Zhou, Li Li, Soo-Hyun Choi, Rui Chen, Xia Hu, et al. 2025. Flexible Group Count Enables Hassle-Free Structured Pruning. InProceedings of the Computer Vision and Pattern Recognition Conference. 4807–4818

work page 2025
[45]

Shunliang Zhang. 2019. An overview of network slicing for 5G.IEEE Wireless Communications26, 3 (2019), 111–117

work page 2019
[46]

Hao Zhou, Chengming Hu, Ye Yuan, Yufei Cui, Yili Jin, Can Chen, Haolun Wu, Dun Yuan, Li Jiang, Di Wu, et al . 2024. Large language model (llm) for telecommunications: A comprehensive survey on principles, key techniques, and opportunities.IEEE Communications Surveys & Tutorials27, 3 (2024), 1955–2005

work page 2024

[1] [1]

Bharat Agarwal, Mohammed Amine Togou, Marco Marco, and Gabriel-Miro Muntean. 2022. A comprehensive survey on radio resource management in 5G HetNets: Current solutions, future trends and open issues.IEEE Communications Surveys & Tutorials24, 4 (2022), 2495–2534

work page 2022

[2] [2]

Hafiz Farooq Ahmad, Wajid Rafique, Raihan Ur Rasool, Abdulaziz Alhumam, Zahid Anwar, and Junaid Qadir. 2023. Leveraging 6G, extended reality, and IoT big data analytics for healthcare: A review.Computer Science Review48 (2023), 100558

work page 2023

[3] [3]

Irfan Ahmed, Hedi Khammari, Adnan Shahid, Ahmed Musa, Kwang Soon Kim, Eli De Poorter, and Ingrid Moerman. 2018. A survey on hybrid beamforming tech- niques in 5G: Architecture and system model perspectives.IEEE Communications Surveys & Tutorials20, 4 (2018), 3060–3097

work page 2018

[4] [4]

Abdul Fatir Ansari, Oleksandr Shchur, Jaris Küken, Andreas Auer, Boran Han, Pedro Mercado, Syama Sundar Rangapuram, Huibin Shen, Lorenzo Stella, Xiyuan Zhang, et al. 2025. Chronos-2: From univariate to universal forecasting.arXiv preprint arXiv:2510.15821(2025)

work page internal anchor Pith review Pith/arXiv arXiv 2025

[5] [5]

Abdul Fatir Ansari, Lorenzo Stella, Caner Turkmen, Xiyuan Zhang, Pedro Mercado, Huibin Shen, Oleksandr Shchur, Syama Sundar Rangapuram, Sebas- tian Pineda Arango, Shubham Kapoor, et al. 2024. Chronos: Learning the language of time series.arXiv preprint arXiv:2403.07815(2024)

work page internal anchor Pith review Pith/arXiv arXiv 2024

[6] [6]

Sihem Baccari, Mohamed Hadded, Hakim Ghazzai, Haifa Touati, and Mourad Elhadef. 2024. Anomaly detection in connected and autonomous vehicles: A survey, analysis, and research challenges.IEEE access12 (2024), 19250–19276

work page 2024

[7] [7]

Osman Tugay Basaran, Hammad Zafar, Martin Kasparick, Falko Dressler, and Slawomir Stańczak. 2025. Next-Gen AI-on-RAN: AI-native, Interoperable, and GPU-Accelerated Testbed Towards 6G Open-RAN. InICC 2025-IEEE International Conference on Communications. IEEE, 5362–5367

work page 2025

[8] [8]

Robin Chataut, Mary Nankya, and Robert Akl. 2024. 6G networks and the AI revolution—Exploring technologies, applications, and emerging challenges. Sensors24, 6 (2024), 1888

work page 2024

[9] [9]

Daihang Chen, Yonghui Liu, Mingyi Zhou, Yanjie Zhao, Haoyu Wang, Shuai Wang, Xiao Chen, Tegawendé F Bissyandé, Jacques Klein, and Li Li. 2025. Llm for mobile: An initial roadmap.ACM Transactions on Software Engineering and Methodology34, 5 (2025), 1–29

work page 2025

[10] [10]

Na Chen, Jingyu Zhou, Hui Guan, Nan Xu, Sheng Xue, Shuting Li, and Zhiqiong Liu. 2023. 5G charging mechanism based on dynamic step size.IEEE Access11 (2023), 15069–15081

work page 2023

[11] [11]

Ben Cohen, Emaad Khwaja, Kan Wang, Charles Masson, Elise Ramé, Youssef Doubli, and Othmane Abou-Amal. 2024. Toto: Time series optimized transformer for observability.arXiv preprint arXiv:2407.07874(2024)

work page arXiv 2024

[12] [12]

Austin Feng, Andreas Varvarigos, Ioannis Panitsas, Daniela Fernandez, Jinbiao Wei, Yuwei Guo, Jialin Chen, Ali Maatouk, Leandros Tassiulas, and Rex Ying

work page

[13] [13]

TelecomTS: A Multi-Modal Observability Dataset for Time Series and Language Analysis.arXiv preprint arXiv:2510.06063(2025)

work page internal anchor Pith review Pith/arXiv arXiv 2025

[14] [14]

Jianhua He, Kun Yang, and Hsiao-Hwa Chen. 2020. 6G cellular networks and connected autonomous vehicles.IEEE network35, 4 (2020), 255–261

work page 2020

[15] [15]

Peng Hu and Jinhuan Zhang. 2020. 5G-enabled fault detection and diagnostics: How do we achieve efficiency?IEEE Internet of Things Journal7, 4 (2020), 3267– 3281

work page 2020

[16] [16]

Siva Rama Krishna Kottapalli, Karthik Hubli, Sandeep Chandrashekhara, Garima Jain, Sunayana Hubli, Gayathri Botla, and Ramesh Doddaiah. 2025. Foundation models for time series: A survey.arXiv preprint arXiv:2504.04011(2025)

work page arXiv 2025

[17] [17]

Kirill Krinkin, Alexander Vodyaho, Igor Kulikov, and Nataly Zhukova. 2020. Models of telecommunications network monitoring based on knowledge graphs. In2020 9th Mediterranean Conference on Embedded Computing (MECO). IEEE, 1–7

work page 2020

[18] [18]

Samir Kumar. 2025. Nokia launches Nokia RAN Digital Twin to turbo-charge AI-native 6G, powered by NVIDIA Aerial Omniverse Digital Twin. InNokia Engineering Blog

work page 2025

[19] [19]

2025.5G/5G-Advanced Networks: Planning, Design, and Optimization

Christofer Larsson. 2025.5G/5G-Advanced Networks: Planning, Design, and Optimization. Academic Press

work page 2025

[20] [20]

Zhenyu Lei, Qiong Wu, JIANXIONG DONG, Yinhan He, Emily Dodwell, Yushun Dong, and Jundong Li. [n. d.]. Reforming the Mechanism: Editing Reasoning Pat- terns in LLMs with Circuit Reshaping. InThe Fourteenth International Conference on Learning Representations

work page

[21] [21]

João PSH Lima, Álvaro AM de Medeiros, Eduardo P de Aguiar, Edelberto F Silva, Vicente A de Sousa, Marcelo L Nunes, and Alysson L Reis. 2023. Deep learning-based handover prediction for 5G and beyond networks. InICC 2023- IEEE International Conference on Communications. IEEE, 3468–3473

work page 2023

[22] [22]

An Liu, Zhe Huang, Min Li, Yubo Wan, Wenrui Li, Tony Xiao Han, Chenchen Liu, Rui Du, Danny Kai Pin Tan, Jianmin Lu, et al. 2022. A survey on fundamental limits of integrated sensing and communication.IEEE Communications Surveys & Tutorials24, 2 (2022), 994–1034

work page 2022

[23] [23]

Chenghao Liu, Taha Aksu, Juncheng Liu, Xu Liu, Hanshu Yan, Quang Pham, Silvio Savarese, Doyen Sahoo, Caiming Xiong, and Junnan Li. 2025. Moirai 2.0: When less is more for time series forecasting.arXiv preprint arXiv:2511.11698 (2025)

work page arXiv 2025

[24] [24]

Ali Maatouk, Nicola Piovesan, Fadhel Ayed, Antonio De Domenico, and Mer- ouane Debbah. 2024. Large language models for telecom: Forthcoming impact on the industry.IEEE Communications Magazine63, 1 (2024), 62–68

work page 2024

[25] [25]

Wooseok Nam, Dongwoon Bai, Jungwon Lee, and Inyup Kang. 2014. Advanced interference management for 5G cellular networks.IEEE Communications Maga- zine52, 5 (2014), 52–60

work page 2014

[26] [26]

Huan X Nguyen, Ramona Trestian, Duc To, and Mallik Tatipamula. 2021. Digital twin for 5G and beyond.IEEE Communications Magazine59, 2 (2021), 10–15

work page 2021

[27] [27]

Gaoyang Pang, Wanchun Liu, Chentao Yue, Daniel E Quevedo, Karl H Johans- son, Branka Vucetic, and Yonghui Li. 2026. Toward Wireless Human-Machine Collaboration in the 6G Era.arXiv preprint arXiv:2602.22662(2026)

work page arXiv 2026

[28] [28]

Seongmin Park, Sungmoon Kwon, Youngkwon Park, Dowon Kim, and Ilsun You

work page

[29] [29]

Session management for security systems in 5g standalone network.IEEE Access10 (2022), 73421–73436

work page 2022

[30] [30]

Imtiaz Parvez, Ali Rahmati, Ismail Guvenc, Arif I Sarwat, and Huaiyu Dai. 2018. A survey on low latency towards 5G: RAN, core network and caching solutions. IEEE Communications Surveys & Tutorials20, 4 (2018), 3098–3130

work page 2018

[31] [31]

Diego Frazatto Pedroso, Luís Almeida, Lucas Eduardo Gulka Pulcinelli, William Akihiro Alves Aisawa, Inês Dutra, and Sarita Mazzini Bruschi. 2025. Anomaly detection and root cause analysis in cloud-native environments using large language models and Bayesian networks.IEEE Access(2025)

work page 2025

[32] [32]

Jordi Pérez-Romero, Oriol Sallent, Ramon Ferrús, and Ramón Agustí. 2015. Arti- ficial intelligence-based 5G network capacity planning and operation. In2015 International Symposium on Wireless Communication Systems (ISWCS). IEEE, 246–250

work page 2015

[33] [33]

Matteo Pozza, Patrick K Nicholson, Diego F Lugones, Ashwin Rao, Hannu Flinck, and Sasu Tarkoma. 2020. On reconfiguring 5G network slices.IEEE Journal on Selected Areas in Communications38, 7 (2020), 1542–1554

work page 2020

[34] [34]

Guanqiao Qu, Qiyuan Chen, Wei Wei, Zheng Lin, Xianhao Chen, and Kaibin Huang. 2025. Mobile edge intelligence for large language models: A contempo- rary survey.IEEE Communications Surveys & Tutorials27, 6 (2025), 3820–3860

work page 2025

[35] [35]

Banoth Ravi and Utkarsh Verma. 2025. Spectrum allocation in 5G and beyond intelligent ubiquitous networks.International Journal of Network Management 35, 1 (2025), e2315

work page 2025

[36] [36]

Sharief Saleh, Pinjun Zheng, Xing Liu, Hui Chen, Musa Furkan Keskin, Basuki Priyanto, Martin Beale, Yasaman Ettefagh, Gonzalo Seco-Granados, Tareq Y Al-Naffouri, et al. 2025. Integrated 6G TN and NTN localization: Challenges, opportunities, and advancements.IEEE Communications Standards Magazine (2025)

work page 2025

[37] [37]

Adnan Shahid, Adrian Kliks, Ahmed Al-Tahmeesschi, Ahmed Elbakary, Alexan- dros Nikou, Ali Maatouk, Ali Mokh, Amirreza Kazemi, Antonio De Domenico, Athanasios Karapantelakis, et al. 2025. Large-scale AI in telecom: Charting the roadmap for innovation, scalability, and enhanced digital experiences.arXiv preprint arXiv:2503.04184(2025)

work page arXiv 2025

[38] [38]

Rakesh Shrestha, Rojeena Bajracharya, and Shiho Kim. 2021. 6G enabled un- manned aerial vehicle traffic management: A perspective.IEEe Access9 (2021), 91119–91136

work page 2021

[39] [39]

Ma- rina, and Bozidar Radunovic

Chuanhao Sun, Ujjwal Pawar, Molham Khoja, Xenofon Foukas, Mahesh K. Ma- rina, and Bozidar Radunovic. 2024. SpotLight: Accurate, explainable and efficient anomaly detection for Open RAN. InProceedings of the 30th Annual International Conference on Mobile Computing and Networking. ACM. The 30th Annual Inter- national Conference On Mobile Computing And Netwo...

work page 2024

[40] [40]

Harsh Tataria, Mansoor Shafi, Andreas F Molisch, Mischa Dohler, Henrik Sjö- land, and Fredrik Tufvesson. 2021. 6G wireless systems: Vision, requirements, challenges, insights, and opportunities.Proc. IEEE109, 7 (2021), 1166–1199

work page 2021

[41] [41]

Lei Yang, Shaobo Li, Yizong Zhang, Caichao Zhu, and Zihao Liao. 2024. Deep learning-assisted unmanned aerial vehicle flight data anomaly detection: A review.IEEE Sensors Journal24, 20 (2024), 31681–31695

work page 2024

[42] [42]

Hao Yu, Masoud Shokrnezhad, Tarik Taleb, Richard Li, and JaeSeung Song. 2023. Toward 6g-based metaverse: Supporting highly-dynamic deterministic multi- user extended reality services.IEEE Network37, 4 (2023), 30–38

work page 2023

[43] [43]

Mohammad Zeeshan, Rahul Raj, Amit Anand, Ankur Pandey, Mohammad Tabrez Quasim, Joaquín Torres-Sospedra, Sudhir Kumar, and Kapal Dev. 2025. Knowl- edge distillation-based AIoT framework for efficient wireless gesture sensing in B5G/6G networks.IEEE Network(2025)

work page 2025

[44] [44]

Jiamu Zhang, Shaochen Zhong, Andrew Ye, Zirui Liu, Sebastian Zhao, Kaixiong Zhou, Li Li, Soo-Hyun Choi, Rui Chen, Xia Hu, et al. 2025. Flexible Group Count Enables Hassle-Free Structured Pruning. InProceedings of the Computer Vision and Pattern Recognition Conference. 4807–4818

work page 2025

[45] [45]

Shunliang Zhang. 2019. An overview of network slicing for 5G.IEEE Wireless Communications26, 3 (2019), 111–117

work page 2019

[46] [46]

Hao Zhou, Chengming Hu, Ye Yuan, Yufei Cui, Yili Jin, Can Chen, Haolun Wu, Dun Yuan, Li Jiang, Di Wu, et al . 2024. Large language model (llm) for telecommunications: A comprehensive survey on principles, key techniques, and opportunities.IEEE Communications Surveys & Tutorials27, 3 (2024), 1955–2005

work page 2024