pith. sign in

arxiv: 2604.12127 · v1 · submitted 2026-04-13 · 💻 cs.NI

BLAST: Blockchain-based LLM-powered Agentic Spectrum Trading

Anas Abognah , Otman Basir This is my paper

Pith reviewed 2026-05-10 15:18 UTC · model grok-4.3

classification 💻 cs.NI
keywords spectrum tradingblockchainLLM agentsVickrey auctiondynamic spectrum accesssocial welfareallocative efficiencyprivacy
0
0 comments X

The pith

LLM agents on a permissioned blockchain use Vickrey auctions to capture up to 71 percent of theoretical spectrum trading surplus through truthful bidding.

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

The paper presents BLAST, a system that places large-language-model agents inside a permissioned blockchain so they can trade radio spectrum without a central coordinator. Each agent follows a perceive-plan-act loop to assess channel value, choose bids, and execute trades while keeping actual bid numbers private. Experiments compare three trading rules and find that the second-price sealed-bid auction produces the highest social welfare and allocative efficiency. The same agents also generate more competitive markets and less concentrated ownership than simple heuristic agents. Privacy holds because only cryptographic hashes reach the public ledger.

Core claim

BLAST combines LLM agents that execute the cognitive-radio perceive-plan-act cycle with a permissioned blockchain to create an autonomous spectrum market. When the agents trade under three mechanisms—direct sale, first-price sealed-bid auction, and second-price (Vickrey) sealed-bid auction—the Vickrey format maximizes social welfare and allocative efficiency by reaching up to 71 percent of the theoretical surplus through truthful bidding. LLM agents further outperform non-LLM heuristic agents by raising market competition, lowering wealth and asset concentration, and increasing overall system welfare while keeping sensitive bid values inside private data collections.

What carries the argument

The sequential perceive-plan-act pipeline inside each LLM agent that lets the agent reason about economic value and market dynamics before submitting bids on the blockchain.

If this is right

  • The Vickrey mechanism is the best of the three tested rules for turning spectrum into social welfare.
  • Replacing heuristic agents with LLM agents measurably increases competition and reduces ownership concentration.
  • Sensitive bid information stays private because only hashes are written to the public ledger.
  • The same agent architecture can be applied to the three market rules without changing the underlying blockchain privacy layer.

Where Pith is reading between the lines

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

  • If the agents remain reliable, the approach could replace parts of centralized spectrum regulators with automated market clearing.
  • The same perceive-plan-act pattern might transfer to other scarce resources such as computing cycles or energy capacity.
  • Larger-scale deployments would need to test whether auction outcomes stay stable when dozens of agents interact simultaneously.

Load-bearing premise

LLM agents will keep reasoning strategically about bids and market dynamics without hallucinations or collusion that the tested scenarios did not reveal.

What would settle it

A repeated Vickrey auction run in which the LLM agents begin submitting bids that deviate from their true valuations or produce coordinated outcomes not seen in the original simulations.

Figures

Figures reproduced from arXiv: 2604.12127 by Anas Abognah, Otman Basir.

Figure 1
Figure 1. Figure 1: (a) Normalized Valuation vs SINR (Linear). (b) Utility vs Spectrum to win forces the agent to pay b ∗ , resulting in a negative payoff vi − b ∗ < 0. Since deviations never increase the payoff and can decrease it, truthful bidding is the dominant strategy. 2) First-Price Sealed-Bid Auction: In this auction mecha￾nism, the winner pays their own bid (pi = bi). Truthful bidding yields zero surplus (vi − bi = 0… view at source ↗
Figure 2
Figure 2. Figure 2: BLAST System Model A. The Blockchain Layer The blockchain serves as the immutable ”ground truth” for the system, recording spectrum ownership, managing the lifecycle of tokens, and executing auction logic via smart contracts. The blockchain network is comprised of Nodes representing wireless operators participating in the spectrum sharing marketplace in addition to any stakeholders such as governmental reg… view at source ↗
Figure 3
Figure 3. Figure 3: Mapping the BLAST Agent Pipeline to the Cognitive Cycle. [PITH_FULL_IMAGE:figures/full_fig_p007_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: illustrates the implemented agent details [PITH_FULL_IMAGE:figures/full_fig_p007_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Market dynamics for scenario 1 showing token ownership movements, [PITH_FULL_IMAGE:figures/full_fig_p009_5.png] view at source ↗
Figure 7
Figure 7. Figure 7: Scenario-1 (Heterogeneous Buyers) Total social welfare highlighting [PITH_FULL_IMAGE:figures/full_fig_p009_7.png] view at source ↗
Figure 8
Figure 8. Figure 8: Scenario-2 (Homogeneous Buyers) Total social welfare highlighting [PITH_FULL_IMAGE:figures/full_fig_p010_8.png] view at source ↗
Figure 9
Figure 9. Figure 9: Cumulative transaction-efficiency trajectories for Scenario 1, high [PITH_FULL_IMAGE:figures/full_fig_p010_9.png] view at source ↗
Figure 11
Figure 11. Figure 11: Scenario 1 (Heterogeneous Agents) LLM Agent vs Baseline non [PITH_FULL_IMAGE:figures/full_fig_p011_11.png] view at source ↗
Figure 13
Figure 13. Figure 13: Transaction Diagram of Second-price (Vickery) Sealed-Bid Auction [PITH_FULL_IMAGE:figures/full_fig_p012_13.png] view at source ↗
read the original abstract

The management of radio frequency spectrum is undergoing a paradigm shift from static, centralized command-and-control models to dynamic, market-driven approaches. However, the realization of Dynamic Spectrum Management has been hindered by the lack of an automated, trustworthy, and intelligent coordination infrastructure that can operate without a central authority while preserving participant privacy. In this paper, we introduce BLAST (Blockchain-based LLM-powered Agentic Spectrum Trading), a comprehensive framework that integrates Large Language Model (LLM) Agents with a permissioned blockchain infrastructure to create a fully autonomous, private, and secure spectrum trading ecosystem. We propose a novel agent architecture that implements the Cognitive Radio cycle through a sequential decision pipeline (perceive, plan, act) enabling agents to reason strategically about economic value and market dynamics. We evaluate the framework through three distinct market mechanisms: Direct Sale, First-Price Sealed-Bid, and Second-Price (Vickrey) Sealed-Bid auctions. Experimental results demonstrate that the Second-Price (Vickrey) auction is the optimal choice for maximizing social welfare and allocative efficiency, capturing up to 71% of the theoretical surplus by incentivizing truthful bidding. We also compare the proposed model against a baseline non-LLM heuristic agentic model and show that utilizing LLM agents yields significant improvements in market competition, reduced wealth and asset concentration, and increased system welfare. Furthermore, we validate the system's privacy preservation, confirming that sensitive bid values remain isolated in private data collections while only cryptographic hashes are committed to the public ledger.

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.

Referee Report

3 major / 3 minor

Summary. The paper introduces BLAST, a framework integrating LLM-powered agents with a permissioned blockchain for autonomous, privacy-preserving dynamic spectrum trading. Agents follow a perceive-plan-act pipeline to reason about economic value and market dynamics. The work evaluates three mechanisms—Direct Sale, First-Price Sealed-Bid, and Second-Price (Vickrey) Sealed-Bid auctions—via simulation and claims that the Vickrey auction maximizes social welfare and allocative efficiency by capturing up to 71% of theoretical surplus through truthful bidding incentives. It further reports that LLM agents outperform a non-LLM heuristic baseline in market competition, reduced wealth/asset concentration, and system welfare, while validating privacy via private data collections on the ledger.

Significance. If the empirical results hold under rigorous controls, the work would be significant for dynamic spectrum management by providing a decentralized, agentic alternative to centralized allocation. The integration of LLMs for strategic auction reasoning on blockchain is novel, and the head-to-head comparison of auction formats plus LLM vs. heuristic agents could inform future DSM designs. The privacy mechanism adds practical value for permissioned environments. However, the absence of experimental details limits immediate impact.

major comments (3)
  1. [Experimental Results] Experimental Results section: The headline claims (Vickrey auction achieving up to 71% surplus capture, plus LLM-driven gains in competition, concentration, and welfare) are stated without any description of simulation parameters, number of runs, random seeds, statistical tests, LLM model/version, temperature, or prompt templates. This directly weakens the optimality conclusion and the attribution of improvements to the LLM agents rather than implementation artifacts.
  2. [Agent Architecture] Agent Architecture and Evaluation sections: The perceive-plan-act pipeline is asserted to enable reliable strategic reasoning and truthful bidding in Vickrey auctions, yet no robustness checks, failure-rate statistics, consistency metrics across seeds, or mitigation for LLM hallucinations/non-determinism are reported. The 71% surplus figure and cross-mechanism comparisons therefore rest on an unverified assumption that agents produce economically coherent outputs.
  3. [Market Mechanisms] Market Mechanisms section: The claim that Second-Price is optimal is presented as data-driven from simulation, but without sensitivity analysis to prompt variations, agent population size, or valuation distributions, it is unclear whether the welfare advantage generalizes or is an artifact of the specific experimental conditions.
minor comments (3)
  1. [Abstract] Abstract: The phrase 'up to 71%' should be accompanied by the precise conditions (e.g., agent count, valuation model) under which it was observed.
  2. [Privacy Validation] Privacy validation paragraph: More concrete details on the blockchain platform (e.g., Hyperledger Fabric chaincode structure or private collection configuration) would improve reproducibility.
  3. [System Model] Notation: The distinction between 'theoretical surplus' and realized welfare should be defined explicitly with an equation or reference to the valuation model.

Simulated Author's Rebuttal

3 responses · 0 unresolved

We thank the referee for the detailed and constructive feedback. The comments highlight important gaps in experimental transparency and robustness that we agree need to be addressed to strengthen the paper. Below we respond point-by-point to the major comments and indicate the revisions we will make.

read point-by-point responses

  1. Referee: [Experimental Results] Experimental Results section: The headline claims (Vickrey auction achieving up to 71% surplus capture, plus LLM-driven gains in competition, concentration, and welfare) are stated without any description of simulation parameters, number of runs, random seeds, statistical tests, LLM model/version, temperature, or prompt templates. This directly weakens the optimality conclusion and the attribution of improvements to the LLM agents rather than implementation artifacts.

    Authors: We agree that the Experimental Results section as currently written omits critical implementation details. This limits reproducibility and makes it difficult for readers to assess whether the reported 71% surplus and LLM advantages are robust. In the revised manuscript we will add a dedicated Experimental Setup subsection that specifies: the exact LLM (model name and version), temperature setting, full prompt templates (including system and user messages for perceive/plan/act stages), number of independent runs per configuration, random seeds used for reproducibility, agent population sizes, valuation generation process, and any statistical tests (e.g., t-tests or Wilcoxon rank-sum) applied to the welfare, competition, and concentration metrics. These additions will directly support the optimality claims and the attribution to LLM agents. revision: yes

  2. Referee: [Agent Architecture] Agent Architecture and Evaluation sections: The perceive-plan-act pipeline is asserted to enable reliable strategic reasoning and truthful bidding in Vickrey auctions, yet no robustness checks, failure-rate statistics, consistency metrics across seeds, or mitigation for LLM hallucinations/non-determinism are reported. The 71% surplus figure and cross-mechanism comparisons therefore rest on an unverified assumption that agents produce economically coherent outputs.

    Authors: The referee is correct that the current manuscript provides no quantitative evidence on the reliability of the perceive-plan-act pipeline or on how non-determinism and hallucinations were handled. Without such checks, the economic coherence of the agents' bids and the resulting 71% surplus figure cannot be fully validated. We will revise the Agent Architecture and Evaluation sections to include a new subsection titled “Agent Reliability and Robustness.” This subsection will report: (i) failure rates (e.g., invalid JSON outputs or incoherent bids) across runs, (ii) consistency metrics (e.g., bid variance for identical valuations across different random seeds), (iii) the mitigation techniques employed (structured output parsing, self-consistency sampling, and post-processing rules), and (iv) any observed hallucination incidents. These additions will allow readers to evaluate the assumption that the agents produce economically coherent outputs. revision: yes

  3. Referee: [Market Mechanisms] Market Mechanisms section: The claim that Second-Price is optimal is presented as data-driven from simulation, but without sensitivity analysis to prompt variations, agent population size, or valuation distributions, it is unclear whether the welfare advantage generalizes or is an artifact of the specific experimental conditions.

    Authors: We acknowledge that the optimality conclusion for the Vickrey auction rests on a single set of experimental conditions and lacks sensitivity analysis. While the chosen parameters were intended to reflect realistic spectrum-trading scenarios, the absence of variation testing leaves open the possibility that the welfare advantage is configuration-specific. In the revised manuscript we will add a Sensitivity Analysis subsection under Market Mechanisms. This will present results for: (i) alternative prompt phrasings, (ii) agent population sizes ranging from 10 to 100, and (iii) different valuation distributions (uniform, normal, and empirical distributions derived from historical spectrum data). We will report how the relative welfare, efficiency, and concentration metrics change across these conditions and will qualify the optimality claim accordingly. revision: yes

Circularity Check

0 steps flagged

Empirical simulation framework exhibits no circular derivation chain

full rationale

The paper's core claims rest on simulation experiments comparing auction mechanisms and LLM vs. heuristic agents, with results such as 71% surplus capture presented as observed outcomes rather than closed-form derivations. No equations, parameter fits, or self-citations are invoked in a load-bearing way that reduces the reported welfare or efficiency metrics to the inputs by construction. The evaluation is data-driven from agent interactions in a blockchain setting, remaining independent of the patterns that would trigger circularity flags.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

The framework rests on the unproven premise that current LLMs can perform reliable economic reasoning in spectrum markets; no independent evidence or formal verification is supplied. No explicit free parameters or new physical entities are introduced in the abstract.

pith-pipeline@v0.9.0 · 5568 in / 1225 out tokens · 53612 ms · 2026-05-10T15:18:59.905139+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

42 extracted references · 42 canonical work pages

  1. [1]

    A Survey of Dynamic Spectrum Access: Signal Processing and Networking Perspectives,

    Q. Zhao and A. Swami, “A Survey of Dynamic Spectrum Access: Signal Processing and Networking Perspectives,” in2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP ’07, vol. 4, 2007, pp. IV–1349–IV–1352

    work page 2007

  2. [2]

    A Survey on Blockchain for Dynamic Spectrum Sharing,

    L. Perera, P. Ranaweera, S. Kusaladharma, S. Wang, and M. Liyanage, “A Survey on Blockchain for Dynamic Spectrum Sharing,”IEEE Open Journal of the Communications Society, vol. 5, pp. 1753–1802, 2024

    work page 2024

  3. [3]

    Blockchain-Enabled Credible Multi-Operator Spectrum Sharing in UA V Communication Systems,

    Q. Wang, C. Qian, S. Mia, H. Zhang, H. Zhao, Y . Lu, and H. Zhu, “Blockchain-Enabled Credible Multi-Operator Spectrum Sharing in UA V Communication Systems,”IEEE Transactions on Vehicular Tech- nology, vol. 74, no. 6, pp. 8989–9001, 2025

    work page 2025

  4. [4]

    AGI and LLM-Driven Spectrum Intelligence in Future Wireless Networks,

    S. Javaid, N. Khan, A. Alwarafy, and N. Saeed, “AGI and LLM-Driven Spectrum Intelligence in Future Wireless Networks,”IEEE Wireless Communications, pp. 1–10, 2025

    work page 2025

  5. [5]

    Smart Contract-Based Spec- trum Sharing Transactions for Multi-Operators Wireless Communication Networks,

    S. Zheng, T. Han, Y . Jiang, and X. Ge, “Smart Contract-Based Spec- trum Sharing Transactions for Multi-Operators Wireless Communication Networks,”IEEE Access, vol. 8, pp. 88 547–88 557, 2020

    work page 2020

  6. [6]

    Cognitive Radio for Flexible Mobile Multimedia Communi- cations,

    J. Mitola, “Cognitive Radio for Flexible Mobile Multimedia Communi- cations,” in1999 IEEE International Workshop on Mobile Multimedia Communications (MoMuC’99), 1999, pp. 3–10

    work page 1999

  7. [7]

    Cognitive Radio: Brain-Empowered Wireless Communica- tions,

    S. Haykin, “Cognitive Radio: Brain-Empowered Wireless Communica- tions,”IEEE Journal on Selected Areas in Communications, vol. 23, no. 2, pp. 201–220, 2005

    work page 2005

  8. [8]

    Facilitating Opportunities for Flexible Efficient and Reliable Spectrum Use Employing Cognitive Radio Technologies,

    FCC, “Facilitating Opportunities for Flexible Efficient and Reliable Spectrum Use Employing Cognitive Radio Technologies,” FCC Record Citation: 18 FCC Rcd 26859 (35), Washington, DC: USA, 2003. [Online]. Available: https://www.fcc.gov/document/ facilitating-opportunities-flexible-efficient-and-reliable-spectrum-1 SUBMITTED TO IEEE TRANSACTIONS ON COGNITIV...

    work page 2003

  9. [9]

    TV White Space Availability in Libya,

    A. Abognah and O. Basir, “TV White Space Availability in Libya,” in Cognitive Radio Oriented Wireless Networks, M. Weichold, M. Hamdi, M. Z. Shakir, M. Abdallah, G. K. Karagiannidis, and M. Ismail, Eds. Cham: Springer International Publishing, 2015, pp. 593–603

    work page 2015

  10. [10]

    Spectrum Access Sys- tem for the Citizen Broadband Radio Service,

    M. M. Sohul, M. Yao, T. Yang, and J. H. Reed, “Spectrum Access Sys- tem for the Citizen Broadband Radio Service,”IEEE Communications Magazine, vol. 53, no. 7, pp. 18–25, 2015

    work page 2015

  11. [11]

    Decentralized Spectrum Access System: Vision, Challenges, and a Blockchain Solution,

    Y . Xiao, S. Shi, W. Lou, C. Wang, X. Li, N. Zhang, Y . T. Hou, and J. H. Reed, “Decentralized Spectrum Access System: Vision, Challenges, and a Blockchain Solution,”IEEE Wireless Communications, vol. 29, no. 1, pp. 220–228, 2022

    work page 2022

  12. [12]

    Distributed Spectrum Sharing Using Blockchain: A Hyperledger Fabric Implementation,

    A. Abognah and O. Basir, “Distributed Spectrum Sharing Using Blockchain: A Hyperledger Fabric Implementation,” in2022 IEEE 1st Global Emerging Technology Blockchain Forum: Blockchain & Beyond (iGETblockchain), 2022, pp. 1–6

    work page 2022

  13. [13]

    Hyperledger Fabric Documentation,

    “Hyperledger Fabric Documentation,” https://hyperledger-fabric. readthedocs.io/en/latest/, (Date last accessed 2025-12-04). [Online]. Available: https://hyperledger-fabric.readthedocs.io/en/latest/

    work page 2025

  14. [14]

    Multi-Agent Reinforcement Learning for Dynamic Spectrum Access,

    H. Jiang, T. Wang, and S. Wang, “Multi-Agent Reinforcement Learning for Dynamic Spectrum Access,” inICC 2019 - 2019 IEEE International Conference on Communications (ICC), 2019, pp. 1–6

    work page 2019

  15. [15]

    A Cooperative Spectrum Sensing With Multi-Agent Reinforcement Learning Approach in Cog- nitive Radio Networks,

    A. Gao, C. Du, S. X. Ng, and W. Liang, “A Cooperative Spectrum Sensing With Multi-Agent Reinforcement Learning Approach in Cog- nitive Radio Networks,”IEEE Communications Letters, vol. 25, no. 8, pp. 2604–2608, 2021

    work page 2021

  16. [16]

    Deep Reinforcement Learning Agents for Dynamic Spectrum Access in Television Whitespace Cognitive Radio Networks,

    U. C. Ukpong, O. Idowu-Bismark, E. Adetiba, J. R. Kala, E. Owolabi, O. Oshin, A. Abayomi, and O. E. Dare, “Deep Reinforcement Learning Agents for Dynamic Spectrum Access in Television Whitespace Cognitive Radio Networks,”Scientific African, vol. 27, p. e02523, 2025. [Online]. Available: https: //www.sciencedirect.com/science/article/pii/S2468227624004654

    work page 2025

  17. [17]

    A Multi-Agent Reinforcement Learning Testbed for Cognitive Radio Applications,

    S. Vangaru, D. Rosen, D. Green, R. Rodriguez, M. Wiecek, A. Johnson, A. M. Jones, and W. C. Headley, “A Multi-Agent Reinforcement Learning Testbed for Cognitive Radio Applications,” in2025 IEEE 22nd Consumer Communications & Networking Conference (CCNC), 2025, pp. 1–9

    work page 2025

  18. [18]

    RadioLLM: Introducing Large Language Model into Cognitive Radio via Hybrid Prompt and Token Reprogrammings,

    S. Chen, Y . Zu, Z. Feng, S. Yang, and M. Li, “RadioLLM: Introducing Large Language Model into Cognitive Radio via Hybrid Prompt and Token Reprogrammings,”arXiv preprint arXiv:2501.17888, 2025

    work page arXiv 2025

  19. [19]

    LLM-Empowered Resource Allocation in Wireless Communications Systems,

    W. Lee and J. Park, “LLM-Empowered Resource Allocation in Wireless Communications Systems,”IEEE Access, vol. 14, pp. 15 260–15 272, 2026

    work page 2026

  20. [20]

    AI Agents Meet Blockchain: A Survey on Secure and Scalable Collaboration for Multi-Agents,

    M. M. Karim, D. H. Van, S. Khan, Q. Qu, and Y . Kholodov, “AI Agents Meet Blockchain: A Survey on Secure and Scalable Collaboration for Multi-Agents,”Future Internet, vol. 17, no. 2, p. 57, 2025

    work page 2025

  21. [21]

    AI-Driven Decentralized Network Management: Leveraging Multi-Agent Large Language Models for Scalable Optimization,

    H. Lee, M. Kim, S. Baek, W. Zhou, M. Debbah, and I. Lee, “AI-Driven Decentralized Network Management: Leveraging Multi-Agent Large Language Models for Scalable Optimization,”IEEE Communications Magazine, vol. 63, no. 6, pp. 50–56, 2025

    work page 2025

  22. [22]

    LLM Enabled Multi-Agent System for 6G Networks: Framework and Method of Dual- Loop Edge-Terminal Collaboration,

    Z. Qu, W. Wang, Z. Yu, B. Sun, Y . Li, and X. Zhang, “LLM Enabled Multi-Agent System for 6G Networks: Framework and Method of Dual- Loop Edge-Terminal Collaboration,”IEEE Communications Magazine, pp. 1–7, 2026

    work page 2026

  23. [23]

    Empowering Future Spectrum Management and Regulation With Large Language Models,

    H. Rutagemwa, A. Ghasemi, and P. Guinand, “Empowering Future Spectrum Management and Regulation With Large Language Models,” IEEE Intelligent Systems, vol. 40, no. 4, pp. 46–54, 2025

    work page 2025

  24. [24]

    SpectrumFM: A foundation model for intelligent spectrum management,

    F. Zhou, C. Liu, H. Zhang, W. Wu, Q. Wu, D. W. K. Ng, T. Q. S. Quek, and C.-B. Chae, “SpectrumFM: A Foundation Model for Intelligent Spectrum Management,” 2025. [Online]. Available: https://arxiv.org/abs/2505.06256

    work page arXiv 2025

  25. [25]

    Counterspeculation, Auctions, and Competitive Sealed Tenders,

    W. Vickrey, “Counterspeculation, Auctions, and Competitive Sealed Tenders,”The Journal of Finance, vol. 16, no. 1, pp. 8–37, 1961

    work page 1961

  26. [26]

    Decentralized Spectrum Sensing in Cognitive Radio Networks via Federated Learning and Blockchain,

    A. Abognah and O. Basir, “Decentralized Spectrum Sensing in Cognitive Radio Networks via Federated Learning and Blockchain,” in2025 International Libyan Conference for Information and Communications Technologies (ILCICT), 2025

    work page 2025

  27. [27]

    A Survey on Dynamic Spec- trum Access Techniques in Cognitive Radio,

    A. Garhwal, R. Bhatt, and S. Garhwal, “A Survey on Dynamic Spec- trum Access Techniques in Cognitive Radio,”International Journal of Computer Applications, vol. 48, no. 12, pp. 20–25, 2012

    work page 2012

  28. [28]

    RFRL Gym: A Reinforcement Learning Testbed for Cognitive Radio Applications,

    D. Rosen, I. Rochez, C. McIrvin, J. Lee, K. D’Alessandro, M. Wiecek, N. Hoang, R. Saffarini, S. Philips, V . Jones, W. Ivey, Z. Harris-Smart, Z. Harris-Smart, Z. Chin, A. Johnson, A. M. Jones, and W. C. Headley, “RFRL Gym: A Reinforcement Learning Testbed for Cognitive Radio Applications,” in2023 International Conference on Machine Learning and Applicatio...

    work page 2023

  29. [29]

    BSM-6G: Blockchain-Based Dynamic Spectrum Management for 6G Networks: Addressing Inter- operability and Scalability,

    D. Cuellar, M. Sallal, and C. Williams, “BSM-6G: Blockchain-Based Dynamic Spectrum Management for 6G Networks: Addressing Inter- operability and Scalability,”IEEE Access, vol. 12, pp. 59 643–59 664, 2024

    work page 2024

  30. [30]

    A Multi-Leader Multi-Follower Stackelberg Game for Dynamic Spectrum Sharing in a Blockchain Enabled Cell-Free Massive MIMO Scenario,

    G. Femenias, M. F. Hinarejos, F. Riera-Palou, J.-L. Ferrer-Gomila, and A. Jaume-Barcel ´o, “A Multi-Leader Multi-Follower Stackelberg Game for Dynamic Spectrum Sharing in a Blockchain Enabled Cell-Free Massive MIMO Scenario,”IEEE Open Journal of the Communications Society, 2025

    work page 2025

  31. [31]

    FastFabric: Scaling Hyperledger Fabric to 20,000 Transactions per Second,

    C. Gorenflo, S. Lee, L. Golab, and S. Keshav, “FastFabric: Scaling Hyperledger Fabric to 20,000 Transactions per Second,” in2019 IEEE International Conference on Blockchain and Cryptocurrency (ICBC), 2019, pp. 455–463

    work page 2019

  32. [32]

    Large Language Models for Wireless Networks: An Overview from the Prompt Engineering Perspective,

    H. Zhou, C. Hu, D. Yuan, Y . Yuan, D. Wu, X. Chen, H. Tabassum, and X. Liu, “Large Language Models for Wireless Networks: An Overview from the Prompt Engineering Perspective,”IEEE Wireless Communications, vol. 32, no. 4, pp. 98–106, 2025

    work page 2025

  33. [33]

    LLM-Enhanced Dynamic Spectrum Management for Integrated Non-Terrestrial and Terrestrial Networks: A Multi-Objective Optimization Approach,

    H. M. Ali Zeeshan, A. Ahmad, S. Ali Hassan, M. Sohaib Jamal Solaija, and S. Hussain Chauhdary, “LLM-Enhanced Dynamic Spectrum Management for Integrated Non-Terrestrial and Terrestrial Networks: A Multi-Objective Optimization Approach,”Mobile Networks and Applications, Jan 2026. [Online]. Available: https://doi.org/10.1007/ s11036-026-02490-z

    work page 2026

  34. [34]

    arXiv preprint arXiv:2411.05990 , year=

    W. Hua, O. Liu, L. Li, A. Amayuelas, J. Chen, L. Jiang, M. Jin, L. Fan, F. Sun, W. Wang, and Others, “Game-Theoretic LLM Agent Workflow for Negotiation Games,”arXiv preprint arXiv:2411.05990, 2024

    work page arXiv 2024

  35. [35]

    Strategic behavior of large language models and the role of game structure versus contextual framing,

    N. Lor `e and B. Heydari, “Strategic behavior of large language models and the role of game structure versus contextual framing,” Scientific Reports, vol. 14, no. 1, p. 18490, 2024. [Online]. Available: https://doi.org/10.1038/s41598-024-69032-z

    work page doi:10.1038/s41598-024-69032-z 2024

  36. [36]

    LLM strategic reasoning: Agentic study through behavioral game theory,

    J. Jia, Z. Yuan, J. Pan, P. E. McNamara, and D. Chen, “LLM strategic reasoning: Agentic study through behavioral game theory,” in The Thirty-ninth Annual Conference on Neural Information Processing Systems, 2025. [Online]. Available: https://openreview.net/forum?id= XQrGTggLvT

    work page 2025

  37. [37]

    arXiv:2407.04467 [cs.AI] https://arxiv.org/abs/2407.04467

    N. Herr, F. Acero, R. Raileanu, M. P ´erez-Ortiz, and Z. Li, “Are Large Language Models Strategic Decision Makers? A Study of Performance and Bias in Two-Player Non-Zero-Sum Games,” vol. abs/2407.04467,

    work page arXiv

  38. [38]

    arXiv:2407.04467 [cs.AI] https://arxiv.org/abs/2407.04467

    [Online]. Available: https://doi.org/10.48550/arXiv.2407.04467

    work page doi:10.48550/arxiv.2407.04467

  39. [39]

    Autoflow: Automated workflow generation for large language model agents

    Z. Li, S. Xu, K. Mei, W. Hua, B. Rama, O. Raheja, H. Wang, H. Zhu, and Y . Zhang, “AutoFlow: Automated Workflow Generation for Large Language Model Agents,” vol. abs/2407.12821, 2024. [Online]. Available: https://doi.org/10.48550/arXiv.2407.12821

    work page doi:10.48550/arxiv.2407.12821 2024

  40. [40]

    Auction-Based Resource Allocation in Cognitive Radio Systems,

    E. Hossain, D. Niyato, P. Wang, and Y . Zhang, “Auction-Based Resource Allocation in Cognitive Radio Systems,” inIEEE Communications Magazine, 2012, pp. 109–120

    work page 2012

  41. [41]

    Auction-Based Spectrum Sharing,

    J. Huang, R. A. Berry, and M. L. Honig, “Auction-Based Spectrum Sharing,”ACM/Springer Mobile Networks and Applications Journal (MONET), vol. 11, no. 3, pp. 405–418, 2006

    work page 2006

  42. [42]

    Google Agent Development Kit (ADK),

    “Google Agent Development Kit (ADK),” https://docs.cloud. google.com/agent-builder/agent-development-kit/overview, (Date last accessed 2025-12-04). [Online]. Available: https://docs.cloud.google. com/agent-builder/agent-development-kit/overview

    work page 2025