arxiv: 2604.17440 · v1 · submitted 2026-04-19 · 📡 eess.SY · cs.SY

Recognition: unknown

WirelessAgent: A Unified Agent Design for General Wireless Resource Allocation Problem without Current Channel State Information

Ran Yi , Ruopeng Xu , Dongshu Zhao , Zhaoyang Zhang , Baolin Chen , Kai-Kit Wong , Hyundong Shin , Zhaohui Yang

Authors on Pith no claims yet

Pith reviewed 2026-05-10 05:43 UTC · model grok-4.3

classification 📡 eess.SY cs.SY

keywords wireless resource allocationchannel state information predictionAI agent designmulti-objective optimizationnatural language interfacespectrum efficiencyenergy efficiencyadaptive scheduling

0 comments

The pith

An AI agent can solve wireless resource allocation without current channel state information by predicting missing data and accepting natural language instructions.

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

The paper develops a unified WirelessAgent design for general wireless resource allocation when full current channel state information is unavailable, which defeats conventional optimization. It supplies a sense-repair-decide-act workflow that first uses an AI model to predict the missing channel values and then deploys an agent on the Coze platform so operators can steer multi-objective scheduling through ordinary conversation. A multi-objective problem is posed that trades spectrum efficiency against energy efficiency, solved by adaptive algorithms that react to the predicted channels. Simulations report that the AI channel predictor cuts root-mean-square error by up to 67 percent versus traditional estimators and that the resulting schedules keep overall system performance more balanced than baseline methods. This matters because real networks rarely supply perfect, timely CSI, so any practical method must operate reliably from incomplete data.

Core claim

The central claim is that a general agent built around AI-predicted channel data and a conversational Coze interface enables reliable multi-objective wireless resource allocation even when current channel state information is absent, with the AI predictor lowering RMSE by up to 67 percent and the adaptive scheduler producing more balanced spectrum-energy performance than conventional baselines.

What carries the argument

The sense-repair-decide-act workflow in which AI prediction repairs incomplete CSI and the Coze agent translates natural-language commands into adaptive multi-objective scheduling decisions.

If this is right

The AI method reduces the root mean square error by approximately up to 67% compared to the traditional approach.
The data-driven scheduling balances system performance compared to conventional baseline approaches.
Network operators can steer the allocation of spectrum and energy resources through natural language conversations rather than manual parameter tuning.
Adaptive algorithms allow the same agent framework to satisfy different user priorities without requiring current CSI.

Where Pith is reading between the lines

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

If the prediction accuracy holds across mobility patterns not tested in simulation, the same workflow could be applied to other resource problems such as power control or beamforming under partial information.
Deployment would still require checking whether the conversational agent introduces latency or misinterpretation that offsets the reported gains in a real-time network.
The approach might be combined with existing network management systems to let operators adjust objectives on the fly without rewriting optimization code.

Load-bearing premise

The AI channel predictor must remain accurate enough under real propagation conditions to let the multi-objective optimizer produce usable schedules, and the Coze agent must turn natural-language inputs into correct scheduling actions without adding new errors.

What would settle it

Measure actual channel realizations in a live multi-user wireless testbed, feed the same inputs to both the proposed AI predictor and a standard estimator, and verify whether the AI version reduces RMSE by roughly 67 percent while the resulting allocations still balance spectrum and energy metrics; if the gap disappears or performance becomes unbalanced, the claim fails.

Figures

Figures reproduced from arXiv: 2604.17440 by Baolin Chen, Dongshu Zhao, Hyundong Shin, Kai-Kit Wong, Ran Yi, Ruopeng Xu, Zhaohui Yang, Zhaoyang Zhang.

**Figure 1.** Figure 1: The proposed agent-enabled general resource allocation framework. The workflow includes intent recognition, AI-based channel reconstruction for [PITH_FULL_IMAGE:figures/full_fig_p002_1.png] view at source ↗

**Figure 2.** Figure 2: Comparison of channel gain reconstruction for a randomly selected [PITH_FULL_IMAGE:figures/full_fig_p005_2.png] view at source ↗

**Figure 3.** Figure 3: System sum rate versus maximum transmit power [PITH_FULL_IMAGE:figures/full_fig_p005_3.png] view at source ↗

read the original abstract

This paper investigates the agent design for solving the wireless resource allocation problem without sufficient channel state information (CSI), which cannot be effectively solved via conventional method. In the considered wireless agent design, we provide the general sense-repair-decide-act workflow, which can be used to intelligently solve general wireless resource allocation problem. A multi-objective optimization problem is formulated to adaptively satisfy different user requirements including both spectrum and energy efficiency. This work addresses the challenge of incomplete CSI for multiple optimization objectives. To solve this problem, we use an artificial intelligence (AI) model to predict missing channel data and construct an agent on the Coze platform, allowing the network operators to optimize multiple objectives through natural language conversations. To tackle the resource scheduling under different objectives, we develop adaptive algorithms. Simulation results validate the effectiveness of our proposed design, demonstrating that the proposed AI method reduces the root mean square error by approximately up to 67\% compared to the traditional approach. Moreover, the data-driven scheduling balances system performance compared to conventional baseline approaches.

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

The paper sketches a sense-repair-decide-act agent on Coze that predicts missing CSI and lets operators steer multi-objective wireless scheduling in natural language, but the reported 67% RMSE gain and balanced performance rest on an unspecified prediction model with no visible checks against realistic error patterns.

read the letter

The new piece here is the explicit workflow that turns incomplete CSI into a repair step before feeding an adaptive scheduler, then wraps the whole thing in a Coze-based agent so users can change spectrum-versus-energy priorities by chatting. That framing is cleaner than most prior AI-for-wireless papers that stop at prediction or single-objective RL. The simulations apparently show the AI predictor cutting RMSE by up to 67% versus a conventional baseline and the scheduler keeping throughput and energy use in better balance across scenarios. Those numbers are the main empirical hook and they are worth a look if the baselines are standard water-filling or greedy allocation methods. Credit for trying to make the system controllable without retraining every time the objective shifts. The soft spot is that the abstract and the reported results give almost no architecture, training corpus, loss, or hyper-parameter details for the predictor, nor any description of how the Coze agent is prompted or constrained to respect power and interference limits. Without those, it is impossible to tell whether the RMSE drop comes from a strong model or from an easy test set, and whether the agent actually produces feasible schedules or just plausible-sounding ones. The stress-test note is right on this: the end-to-end gain cannot be attributed to the workflow until we see sensitivity to prediction error correlation, user mobility, or multi-cell interference. The paper is aimed at the intersection of LLM agents and wireless systems people who already accept simulation-only evidence at this stage. It is coherent enough on its own terms to deserve a serious referee who can ask for the missing model cards and ablation runs rather than a desk reject. I would bring it to a reading group only if someone has already implemented the Coze part and can show the prompts.

Referee Report

3 major / 1 minor

Summary. The manuscript proposes WirelessAgent, a unified agent design for general wireless resource allocation without current channel state information (CSI). It outlines a sense-repair-decide-act workflow, uses an AI model to predict missing channel data, constructs an agent on the Coze platform to enable natural-language multi-objective optimization (spectrum and energy efficiency), and develops adaptive scheduling algorithms. Simulation results are reported to show that the AI prediction reduces RMSE by up to 67% versus a traditional approach and that the data-driven scheduling achieves balanced performance relative to conventional baselines.

Significance. If the performance claims hold under rigorous verification, the work could contribute to practical wireless systems by addressing incomplete CSI through AI prediction combined with LLM-based agents for intuitive, multi-objective control. The general workflow and emphasis on natural-language interaction represent a timely direction for 5G/6G resource management. No machine-checked proofs, open code, or parameter-free derivations are provided, so reproducibility and novelty relative to existing AI-for-wireless literature remain to be established.

major comments (3)

[Abstract] Abstract: the central claim that 'the proposed AI method reduces the root mean square error by approximately up to 67% compared to the traditional approach' is presented without any description of the AI model architecture, training corpus, loss function, baseline definition, channel model, number of users, or statistical significance testing. This renders the quantitative result unverifiable and load-bearing for the paper's contribution.
[Abstract] Abstract: the multi-objective optimization and adaptive algorithms are described only at a high level; no formulation, pseudocode, or analysis of how prediction errors from the AI model propagate through the Coze-agent decisions to the final scheduling is given, leaving the 'balanced performance' claim without technical grounding.
[Abstract] The manuscript does not report any sensitivity analysis of the end-to-end system to realistic CSI prediction error statistics (correlation, mobility, multi-user interference), which is required to substantiate that the AI-predicted channels remain accurate enough for reliable multi-objective optimization.

minor comments (1)

[Abstract] The abstract would benefit from a brief statement of the wireless scenario (e.g., single-cell vs. multi-cell, frequency band, mobility model) to allow readers to assess applicability.

Simulated Author's Rebuttal

3 responses · 0 unresolved

We thank the referee for the constructive comments and the recommendation for major revision. We address each major comment below and will revise the manuscript accordingly to improve clarity, verifiability, and technical depth.

read point-by-point responses

Referee: [Abstract] Abstract: the central claim that 'the proposed AI method reduces the root mean square error by approximately up to 67% compared to the traditional approach' is presented without any description of the AI model architecture, training corpus, loss function, baseline definition, channel model, number of users, or statistical significance testing. This renders the quantitative result unverifiable and load-bearing for the paper's contribution.

Authors: We agree that the abstract would benefit from additional context to make the key quantitative claim more verifiable on its own. The AI model architecture, training details, loss function, baseline (traditional approach), channel model, number of users, and statistical significance testing (via multiple Monte Carlo runs) are described in the main body of the manuscript. To address this, we will revise the abstract to include a concise summary of these elements along with pointers to the relevant sections. revision: yes
Referee: [Abstract] Abstract: the multi-objective optimization and adaptive algorithms are described only at a high level; no formulation, pseudocode, or analysis of how prediction errors from the AI model propagate through the Coze-agent decisions to the final scheduling is given, leaving the 'balanced performance' claim without technical grounding.

Authors: We acknowledge that the abstract is high-level. The multi-objective optimization formulation and adaptive scheduling algorithms (including pseudocode) appear in Sections II and IV of the manuscript. We will revise the abstract to reference these more explicitly. Additionally, we will add a new analysis subsection examining the propagation of AI prediction errors through the Coze-agent decisions to the final resource allocation outcomes, supported by targeted simulations. revision: yes
Referee: The manuscript does not report any sensitivity analysis of the end-to-end system to realistic CSI prediction error statistics (correlation, mobility, multi-user interference), which is required to substantiate that the AI-predicted channels remain accurate enough for reliable multi-objective optimization.

Authors: We agree that sensitivity analysis is necessary to strengthen the claims. The current manuscript emphasizes nominal performance; we will add a dedicated sensitivity analysis in the revised version. This will include simulations varying channel prediction error correlation, user mobility (e.g., Doppler spread), and multi-user interference levels, demonstrating the robustness of the end-to-end sense-repair-decide-act workflow for multi-objective optimization. revision: yes

Circularity Check

0 steps flagged

No significant circularity; claims rest on external simulation benchmarks

full rationale

The paper's core workflow (AI prediction of missing CSI followed by Coze-based agent and adaptive scheduling) is presented as a general design whose performance is validated via simulation comparisons to traditional methods and baselines, yielding up to 67% RMSE reduction. No equations, self-definitions, or self-citations are quoted that reduce any claimed prediction or result to its own fitted inputs by construction. The derivation chain depends on training an external AI model and running simulations against independent baselines, remaining self-contained and falsifiable outside the paper's own parameters.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Only the abstract is available, so no explicit free parameters, axioms, or invented entities are identifiable. The multi-objective formulation and AI prediction likely rely on standard wireless channel models and machine learning assumptions not detailed here.

pith-pipeline@v0.9.0 · 5505 in / 1130 out tokens · 25085 ms · 2026-05-10T05:43:26.683653+00:00 · methodology

discussion (0)

Reference graph

Works this paper leans on

140 extracted references · 12 canonical work pages

[1]

Mao, Yijie and Clerckx, Bruno and Li, Victor O. K. , journal=. Rate-Splitting for Multi-Antenna Non-Orthogonal Unicast and Multicast Transmission:. 2019 , volume=

2019
[2]

Comparison of Pearson correlation coefficient and distance correlation in Correlation Power Analysis on Digital Multiplier , year=

Kundrata, Jurica and Fujimoto, Daisuke and Hayashi, Yuichi and Barić, Adrijan , booktitle=. Comparison of Pearson correlation coefficient and distance correlation in Correlation Power Analysis on Digital Multiplier , year=
[3]

IEEE Journal on Selected Areas in Communications , year=

Energy efficient fluid antenna relay (FAR)-assisted wireless communications , author=. IEEE Journal on Selected Areas in Communications , year=
[4]

How Organic Networking meets 6G Campus Network Management Challenges , year=

Corici, Marius-Iulian and Eichhorn, Fabian and Gowtham, Varun and Magedanz, Thomas and Modroiu, Elena-Ramona and Schreiner, Florian , booktitle=. How Organic Networking meets 6G Campus Network Management Challenges , year=
[5]

, booktitle=

Alodadi, Mohammad and Janeja, Vandana P. , booktitle=. Similarity in Patient Support Forums Using TF-IDF and Cosine Similarity Metrics , year=
[6]

Deterministic Channel Access Using MU EDCA in OFDMA-based Wi-Fi Networks , year=

Schneider, Ben and Chongaroonngamsaeng, Chitiphat and Richerzhagen, Bjoern and Bahr, Michael and Carle, Georg , booktitle=. Deterministic Channel Access Using MU EDCA in OFDMA-based Wi-Fi Networks , year=
[7]

Behara, Aparna and Venkatesh, T. G. , journal=. Fluid-Limit Model for Dynamic MU-OFDMA Resource Allocation of Wi-Fi6 Networks , year=
[8]

Multiuser Access via OFDMA Technology in High Density IEEE 802.11ax WLANs: A Survey , year=

Brahmi, Saloua and Yazid, Mohand and Omar, Mawloud , booktitle=. Multiuser Access via OFDMA Technology in High Density IEEE 802.11ax WLANs: A Survey , year=
[9]

Dynamic sectorisation based on genetic algorithms for OFDMA networks , year=

Dapeng Zhang and Cuthbert, Laurie , booktitle=. Dynamic sectorisation based on genetic algorithms for OFDMA networks , year=
[10]

arXiv preprint arXiv:2010.07852 , year=

On hybrid quantum and classical computing algorithms for mixed-integer programming , author=. arXiv preprint arXiv:2010.07852 , year=

work page arXiv 2010
[11]

Proceedings of the Thirtieth Annual ACM-SIAM Symposium on Discrete Algorithms , pages=

Optimizing quantum optimization algorithms via faster quantum gradient computation , author=. Proceedings of the Thirtieth Annual ACM-SIAM Symposium on Discrete Algorithms , pages=. 2019 , organization=

2019
[12]

IEEE Trans

Temporal spectrum sharing based on primary user activity prediction , author=. IEEE Trans. Wireless Commun. , volume=. 2010 , month=

2010
[13]

IEEE Access , volume=

Semi-online computational offloading by dueling deep-Q network for user behavior prediction , author=. IEEE Access , volume=. 2020 , month=

2020
[14]

Characterizing user behavior and network performance in a public wireless

Balachandran, Anand and Voelker, Geoffrey M and Bahl, Paramvir and Rangan, P Venkat , booktitle=. Characterizing user behavior and network performance in a public wireless. 2002 , month=

2002
[15]

Federated learning for

Yang, Zhaohui and Chen, Mingzhe and Wong, Kai-Kit and Poor, H Vincent and Cui, Shuguang , journal=. Federated learning for. 2022 , month=

2022
[16]

ACM Trans

Telco user activity level prediction with massive mobile broadband data , author=. ACM Trans. Intelligent Syst. Technology (TIST) , volume=. 2016 , publisher=

2016
[17]

Learning based primary user activity prediction in cognitive radio networks for efficient dynamic spectrum access , author=. Proc. Int. Conf. Signal Process. Commun. (SPCOM) , pages=. 2016 , month=

2016
[18]

IEEE Commun

A survey on machine-learning techniques in cognitive radios , author=. IEEE Commun. Surveys & Tut. , volume=
[19]

Applied Sciences , VOLUME =

Khan, Naimat Ullah and Wan, Wanggen and Riaz, Rabia and Jiang, Shuitao and Wang, Xuzhi , TITLE =. Applied Sciences , VOLUME =. 2023 , MONTH=

2023
[20]

Primary user activity prediction based joint topology control and stable routing in mobile cognitive networks , year=

Xue, Yan and Tang, Can and Tang, Feilong and Yang, Yanqin and Li, Jie and Guo, Minyi and Wu, Jinsong , booktitle=. Primary user activity prediction based joint topology control and stable routing in mobile cognitive networks , year=
[21]

Primary User Activity Prediction in DSA Networks using Recurrent Structures , year=

Roy, Debashri and Mukherjee, Tathagata and Chatterjee, Mainak and Pasiliao, Eduardo , booktitle=. Primary User Activity Prediction in DSA Networks using Recurrent Structures , year=
[22]

Short-Term User Activity Prediction with Massive Mobile Broadband Data , year=

Xiao, Jiakun and Chen, Chen and Hou, Chunyan and Yuan, Xiaojie , booktitle=. Short-Term User Activity Prediction with Massive Mobile Broadband Data , year=
[23]

Deep Learning for an Effective Nonorthogonal Multiple Access Scheme , year=

Gui, Guan and Huang, Hongji and Song, Yiwei and Sari, Hikmet , journal=. Deep Learning for an Effective Nonorthogonal Multiple Access Scheme , year=
[24]

Machine Learning for Predictive On-Demand Deployment of Uavs for Wireless Communications , year=

Zhang, Qianqian and Mozaffari, Mohammad and Saad, Walid and Bennis, Mehdi and Debbah, Merouane , booktitle=. Machine Learning for Predictive On-Demand Deployment of Uavs for Wireless Communications , year=
[25]

Machine Learning for Predictive Deployment of

Lu, Linyan and Hu, Ye and Zhang, Yirun and Jia, Guangyu and Nie, Jiangtian and Shikh-Bahaei, Mohammad , booktitle=. Machine Learning for Predictive Deployment of. 2020 , month=

2020
[26]

Machine Learning for Predictive Deployment of

Guo, Feiyang and Lu, Linyan and Zang, Zelin and Shikh-Bahaei, Mohammad , journal=. Machine Learning for Predictive Deployment of. 2023 , volume=

2023
[27]

Expert Systems with Applications , volume=

Cellular traffic prediction with machine learning: A survey , author=. Expert Systems with Applications , volume=. 2022 , publisher=

2022
[28]

Traffic Prediction for Reconfigurable Access Scheme in Correlated Traffic MTC Networks , year=

Shoaei, Atoosa Dalili and Nguyen, Duc Tuong and Le-Ngoc, Tho , booktitle=. Traffic Prediction for Reconfigurable Access Scheme in Correlated Traffic MTC Networks , year=
[29]

Cellular Traffic Prediction via a Deep Multi-Reservoir Regression Learning Network for Multi-Access Edge Computing , year=

Li, Yingqi and Sun, Xiaochuan and Zhang, Haijun and Li, Zhigang and Qin, Linlin and Sun, Chenwei and Ji, Zhanlin , journal=. Cellular Traffic Prediction via a Deep Multi-Reservoir Regression Learning Network for Multi-Access Edge Computing , year=
[30]

Intelligent and Application-Aware Network Traffic Prediction in Smart Access Gateways , year=

Zhang, Jielun and Ye, Feng and Qian, Yi , journal=. Intelligent and Application-Aware Network Traffic Prediction in Smart Access Gateways , year=
[31]

Traffic Prediction and Random Access Control Optimization: Learning and Non-Learning-Based Approaches , year=

Jiang, Nan and Deng, Yansha and Nallanathan, Arumugam , journal=. Traffic Prediction and Random Access Control Optimization: Learning and Non-Learning-Based Approaches , year=
[32]

Joint user access mode selection and content popularity prediction in non-orthogonal multiple access-based

Yan, Shi and Qi, Lin and Zhou, Yangcheng and Peng, Mugen and Rahman, GM Shafiqur , journal=. Joint user access mode selection and content popularity prediction in non-orthogonal multiple access-based. 2019 , month=

2019
[33]

Content popularity prediction in fog radio access networks:

Wu, Yuting and Jiang, Yanxiang and Bennis, Mehdi and Zheng, Fuchun and Gao, Xiqi and You, Xiaohu , booktitle=. Content popularity prediction in fog radio access networks:. 2020 , organization=

2020
[34]

Multi-Head Attention Based Popularity Prediction Caching in Social Content-Centric Networking With Mobile Edge Computing , year=

Liang, Jie and Zhu, Dali and Liu, Haitao and Ping, Heng and Li, Ting and Zhang, Hangsheng and Geng, Liru and Liu, Yinlong , journal=. Multi-Head Attention Based Popularity Prediction Caching in Social Content-Centric Networking With Mobile Edge Computing , year=
[35]

Content popularity prediction via deep learning in cache-enabled fog radio access networks , author=. Proc. IEEE Global Commun. Conf. (GLOBECOM) , pages=. 2019 , organization=

2019
[36]

Mobility Prediction:

Zhang, Hongtao and Dai, Lingcheng , journal=. Mobility Prediction:. 2019 , volume=

2019
[37]

Mobility Prediction for 5G Core Networks , year=

Jeong, Jaeseong and Roeland, Dinand and Derehag, Jesper and Johansson, Åke Ai and Umaashankar, Venkatesh and Sun, Gordon and Eriksson, Goran , journal=. Mobility Prediction for 5G Core Networks , year=
[38]

Fattore, Umberto and Liebsch, Marco and Brik, Bouziane and Ksentini, Adlen , booktitle=. Auto
[39]

Computer Networks , volume=

Joint user association and resource allocation in HetNets based on user mobility prediction , author=. Computer Networks , volume=. 2020 , publisher=

2020
[40]

IEEE Trans

A new framework for multi-hop ABS-assisted 5G-networks with users’ mobility prediction , author=. IEEE Trans. Veh. Technol. , volume=. 2022 , month=

2022
[41]

and Guan, Xiaohong , journal=

Sun, Feiyang and Wang, Pinghui and Zhao, Junzhou and Xu, Nuo and Zeng, Juxiang and Tao, Jing and Song, Kaikai and Deng, Chao and Lui, John C.S. and Guan, Xiaohong , journal=. Mobile Data Traffic Prediction by Exploiting Time-Evolving User Mobility Patterns , year=
[42]

and Yao, Tong and Zuo, Wuheng , journal=

Ding, Jihong and Liu, Huazhong and Yang, Laurence T. and Yao, Tong and Zuo, Wuheng , journal=. Multiuser Multivariate Multiorder Markov-Based Multimodal User Mobility Pattern Prediction , year=
[43]

IEEE Journal on Selected Areas in Communications , volume=

Energy efficient semantic communication over wireless networks with rate splitting , author=. IEEE Journal on Selected Areas in Communications , volume=. 2023 , publisher=

2023
[44]

IEEE Communications Magazine , volume=

From semantic communication to semantic-aware networking: Model, architecture, and open problems , author=. IEEE Communications Magazine , volume=. 2021 , publisher=

2021
[45]

2011 IEEE Network Science Workshop , pages=

Towards a theory of semantic communication , author=. 2011 IEEE Network Science Workshop , pages=. 2011 , organization=

2011
[46]

Semantic communications: Principles and challenges,

Semantic communications: Principles and challenges , author=. arXiv preprint arXiv:2201.01389 , year=

work page arXiv
[47]

Beyond transmitting bits: Context, semantics, and task-oriented communications , author=. IEEE J. Sel. Areas Commun. , volume=. 2022 , month=

2022
[48]

Edge learning for

Xu, Wei and Yang, Zhaohui and Ng, Derrick Wing Kwan and Levorato, Marco and Eldar, Yonina C and Debbah, M. Edge learning for. IEEE J. Sel. Topics Signal Process. , volume=. 2023 , month=

2023
[49]

arXiv preprint arXiv:2203.06692 , year=

Towards semantic communications: A paradigm shift , author=. arXiv preprint arXiv:2203.06692 , year=

work page arXiv
[50]

IEEE Wireless Commun

Resource allocation for text semantic communications , author=. IEEE Wireless Commun. Lett. , volume=. 2022 , month=

2022
[51]

Heterogeneous semantic and bit communications: A semi-

Mu, Xidong and Liu, Yuanwei and Guo, Li and Al-Dhahir, Naofal , journal=. Heterogeneous semantic and bit communications: A semi-. 2023 , month=

2023
[52]

Zhang, Wenyu and Bai, Kaiyuan and Zeadally, Sherali and Zhang, Haijun and Shao, Hua and Ma, Hui and Leung, Victor C. M. , journal=. 2024 , month=

2024
[53]

Deep Learning Enabled Semantic Communication Systems , year=

Xie, Huiqiang and Qin, Zhijin and Li, Geoffrey Ye and Juang, Biing-Hwang , journal=. Deep Learning Enabled Semantic Communication Systems , year=
[54]

2022 IEEE 96th Vehicular Technology Conference (VTC2022-Fall) , pages=

Performance Optimization of Energy Efficient Semantic Communications over Wireless Networks , author=. 2022 IEEE 96th Vehicular Technology Conference (VTC2022-Fall) , pages=. 2022 , organization=

2022
[55]

2021 IEEE Global Communications Conference (GLOBECOM) , pages=

Federated learning based audio semantic communication over wireless networks , author=. 2021 IEEE Global Communications Conference (GLOBECOM) , pages=. 2021 , organization=

2021
[56]

arXiv preprint arXiv:2301.01421 , year=

Secure semantic communications: Fundamentals and challenges , author=. arXiv preprint arXiv:2301.01421 , year=

work page arXiv
[57]

IEEE Open Journal of the Computer Society , volume=

Blockchain-aided secure semantic communication for ai-generated content in metaverse , author=. IEEE Open Journal of the Computer Society , volume=. 2023 , publisher=

2023
[58]

IEEE Wireless Communications , volume=

Semantic communications: Overview, open issues, and future research directions , author=. IEEE Wireless Communications , volume=. 2022 , publisher=

2022
[59]

IEEE Wireless Communications , volume=

Rethinking modern communication from semantic coding to semantic communication , author=. IEEE Wireless Communications , volume=. 2022 , publisher=

2022
[60]

IEEE Communications Surveys & Tutorials , year=

Semantic communications for future internet: Fundamentals, applications, and challenges , author=. IEEE Communications Surveys & Tutorials , year=
[61]

Online Resource Allocation for Semantic-Aware Edge Computing Systems , year=

Cang, Yihan and Chen, Ming and Yang, Zhaohui and Hu, Yuntao and Wang, Yinlu and Huang, Chongwen and Zhang, Zhaoyang , journal=. Online Resource Allocation for Semantic-Aware Edge Computing Systems , year=
[62]

arXiv preprint arXiv:2301.00912 , year=

Distributed machine learning for uav swarms: Computing, sensing, and semantics , author=. arXiv preprint arXiv:2301.00912 , year=

work page arXiv
[63]

Vincent and Cui, Shuguang , journal=

Wang, Yining and Chen, Mingzhe and Luo, Tao and Saad, Walid and Niyato, Dusit and Poor, H. Vincent and Cui, Shuguang , journal=. Performance Optimization for Semantic Communications: An Attention-Based Reinforcement Learning Approach , year=
[64]

QoE-Aware Resource Allocation for Semantic Communication Networks , year=

Yan, Lei and Qin, Zhijin and Zhang, Rui and Li, Yongzhao and Ye Li, Geoffrey , booktitle=. QoE-Aware Resource Allocation for Semantic Communication Networks , year=
[65]

arXiv preprint arXiv:2309.11736 , year=

Resource Allocation for Semantic-Aware Mobile Edge Computing Systems , author=. arXiv preprint arXiv:2309.11736 , year=

work page arXiv
[66]

arXiv preprint arXiv:2309.14587 , year=

Joint Communication and Computation Framework for Goal-Oriented Semantic Communication with Distortion Rate Resilience , author=. arXiv preprint arXiv:2309.14587 , year=

work page arXiv
[67]

arXiv preprint arXiv:2311.06854 , year=

Multiuser Resource Allocation for Semantic-Relay-Aided Text Transmissions , author=. arXiv preprint arXiv:2311.06854 , year=

work page arXiv
[68]

2023 IEEE/CIC International Conference on Communications in China (ICCC Workshops) , pages=

Semantic Information Extraction for Text Data with Probability Graph , author=. 2023 IEEE/CIC International Conference on Communications in China (ICCC Workshops) , pages=. 2023 , organization=

2023
[69]

Exploiting Semantic Communication for Non-Orthogonal Multiple Access , year=

Mu, Xidong and Liu, Yuanwei , journal=. Exploiting Semantic Communication for Non-Orthogonal Multiple Access , year=
[70]

Non-Orthogonal Multiple Access Enhanced Multi-User Semantic Communication , year=

Li, Weizhi and Liang, Haotai and Dong, Chen and Xu, Xiaodong and Zhang, Ping and Liu, Kaijun , journal=. Non-Orthogonal Multiple Access Enhanced Multi-User Semantic Communication , year=
[71]

Semantic-Based Precoding Design for Multi-User

Kim, Minsu and Kim, Seongjun and Kwak, Jeongho and Lee, Jemin , journal=. Semantic-Based Precoding Design for Multi-User. 2023 , month=

2023
[72]

Multimodal and Multiuser Semantic Communications for Channel-Level Information Fusion , year=

Luo, Xuewen and Gao, Ruobin and Chen, Hsiao-Hwa and Chen, Shuyi and Guo, Qing and Suganthan, Ponnuthurai Nagaratnam , journal=. Multimodal and Multiuser Semantic Communications for Channel-Level Information Fusion , year=
[73]

Task-Oriented Semantic Communication over Rate Splitting Enabled Wireless Control Systems for

Zeng, Cheng and Wang, Jun-Bo and Xiao, Ming and Ding, Changfeng and Chen, Yijian and Yu, Hongkang and Wang, Jiangzhou , journal=. Task-Oriented Semantic Communication over Rate Splitting Enabled Wireless Control Systems for. 2024 , month=

2024
[74]

Interest-Based Semantic Information Transmission with

Cheng, Yanyu and Niyato, Dusit and Du, Hongyang and Kang, Jiawen and Miao, Chunyan and Kim, Dong In , booktitle=. Interest-Based Semantic Information Transmission with. 2023 , month=

2023
[75]

Resource Allocation and Common Message Selection for Task-Oriented Semantic Information Transmission With

Cheng, Yanyu and Niyato, Dusit and Du, Hongyang and Kang, Jiawen and Xiong, Zehui and Miao, Chunyan and Kim, Dong In , journal=. Resource Allocation and Common Message Selection for Task-Oriented Semantic Information Transmission With. 2024 , month=

2024
[76]

Model division multiple access for semantic communications , author=. Front. Inform. Technol. Electron. Eng. , pages=. 2023 , month=

2023
[77]

arXiv preprint arXiv:2307.06027 , year=

Semantic Communications System with Model Division Multiple Access and Controllable Coding Rate for Point Cloud , author=. arXiv preprint arXiv:2307.06027 , year=

work page arXiv
[78]

IEEE Communications Surveys & Tutorials , year=

A survey on metaverse: Fundamentals, security, and privacy , author=. IEEE Communications Surveys & Tutorials , year=
[79]

IEEE Communications Surveys & Tutorials , year=

A full dive into realizing the edge-enabled metaverse: Visions, enabling technologies, and challenges , author=. IEEE Communications Surveys & Tutorials , year=
[80]

Guest editorial:

Brik, Bouziane and Moustafa, Hassnaa and Zhang, Yan and Lakas, Abderrahmane and Subramanian, Sriram , journal=. Guest editorial:. 2023 , publisher=

2023

Showing first 80 references.