Pith. sign in

REVIEW 3 major objections 6 minor 50 references

Agent abilities can be packaged as Meta-AaaS so metaverse services become autonomous, proactive, and embodied across virtual and physical spaces.

Reviewed by Pith at T0; open to challenge. T0 means a machine referee read the full paper against a public rubric. the ladder, T0–T4 →

Challenge this review Re-run · record.json Download PDF Read on arXiv ↗

T0 review · grok-4.5

2026-07-31 13:31 UTC pith:OY77WFOR

load-bearing objection Clean synthesis that names AMServ/Meta-AaaS and maps a research agenda; definitional, not demonstrated, and only modestly new against the authors’ own prior metaverse-services line. the 3 major comments →

arxiv 2607.28242 v1 pith:OY77WFOR submitted 2026-07-30 cs.SE cs.AIcs.MA

Agentic Metaverse Services: A New As-a-Service Paradigm

Xiaofei Xu , Quan Z. Sheng , Zhongjie Wang , Boualem Benatallah , Xiao Wang , Ruipeng Han This is my paper
classification cs.SE cs.AIcs.MA
keywords Agentic Metaverse ServicesMeta-AaaSAgent-as-a-Serviceagentic servicesmetaverse servicesservice computingGenAI agentsvirtual-physical fusion
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved

The pith

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

This paper argues that generative AI has turned software agents into goal-driven actors, and that those actors can be delivered the way cloud software is delivered: as Agent-as-a-Service. When that model is placed inside the metaverse, it yields Agentic Metaverse Services (AMServ)—services that perceive scenes, set goals, coordinate virtual and physical resources, and act through avatars, digital twins, or devices. Meta-AaaS is the proposed as-a-Service stack that encapsulates perception, decision, execution, collaboration, and content generation so those services can be registered, composed, run, and governed. The authors map the evolution from traditional agents and SaaS to this stack, give a layered architecture and four-stage operating loop, and sketch applications in healthcare, manufacturing, education, entertainment, and tourism. If the packaging works, service computing shifts from click-and-API interfaces to intent-driven, immersive delivery in mixed virtual–physical worlds.

Core claim

The central claim is that AMServ—intelligent, agent-driven services operating in metaverse environments—are realized by Meta-AaaS: an as-a-Service architecture that wraps agent capabilities as configurable, invocable, composable service entities with registration, discovery, orchestration, SLA, and governance, enabling autonomous, proactive, embodied, cross-space service delivery.

What carries the argument

Meta-AaaS (Agent-as-a-Service in the metaverse): a multi-layer platform that packages atomic agent capabilities (perception, cognition, decision-making, execution, collaboration, content generation) into composite AMServ and runs them through design, build, runtime, and maintenance phases with embodied interfaces and virtual–physical linkage.

Load-bearing premise

The paper assumes that persistent, non-deterministic, tool-using agents can be stably described, discovered, orchestrated, and held to enforceable quality and trust rules the way ordinary cloud software services are.

What would settle it

Build a multi-vendor Meta-AaaS catalogue of embodied agents in an open metaverse scene and measure whether third parties can discover, compose, and run them under stated SLAs without cascading failures, unsafe tool use, or unresolvable goal conflicts over a sustained multi-session workload.

Watch this falsifier — get emailed when new claim-graph text bears on it.

If this is right

  • Service interfaces move from GUIs and REST calls toward natural-language goals and multimodal embodied interaction.
  • Metaverse applications in care, factories, classrooms, games, and tourism can be assembled from reusable agent capability services rather than hard-wired apps.
  • Service ecosystems become multi-agent networks that recruit peers mid-task and co-evolve roles across virtual and physical spaces.
  • Governance must cover not only uptime and data isolation but hallucination, tool safety, spatial rules, and long-horizon reliability.
  • New research agendas open on service representation, proactive demand sensing, cross-time-space composition, and immersive delivery channels.

Where Pith is reading between the lines

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

  • Without shared identity, memory, and commitment schemas across worlds, the same agent capability may not port or compose, so interoperability standards become the practical bottleneck before any marketplace of AMServ can form.
  • Pay-as-you-go agent billing will need metrics beyond API calls—plan steps, tool risk, and embodiment cost—or providers cannot price non-deterministic agents fairly.
  • Proactive scene-driven delivery can erode user autonomy if ambient curation is always on; explicit consent and override controls are a natural next design requirement the architecture only sketches.
  • Evaluation will likely shift from uptime SLAs to trajectory-level audits (goal achievement, safety incidents, reputation cascades), tying service computing to ongoing agent-eval practice.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit.

Referee Report

3 major / 6 minor

Summary. This visionary paper synthesizes the evolution of AI agents (traditional → learning-based → LLM-empowered → self-evolving) and IT-enabled services (Web → cloud/XaaS → agentic) to define Agentic Metaverse Services (AMServ) and Meta-AaaS. AMServ are goal-driven, proactive, embodied agent services operating across virtual and cyber-physical metaverse spaces; Meta-AaaS is proposed as the as-a-Service architecture that encapsulates agent capabilities (perception, cognition, decision-making, execution, collaboration, content generation) into discoverable, composable, governable service units. The manuscript presents layered architectures (Figs. 1, 3, 5), a six-role agent taxonomy, a four-stage AMServ operating loop (Fig. 4), SaaS-vs-AaaS and agent-evolution comparisons (Tables I–II), five application sketches, and an open research agenda (§IV).

Significance. If accepted as a framing contribution, the paper usefully consolidates agentic AI, metaverse services, and classical service-computing machinery under a single named paradigm (AMServ/Meta-AaaS) and supplies reusable taxonomies and lifecycle diagrams that later empirical work can instantiate. Strengths include coherent comparative tables (I–II), an explicit role-based agent taxonomy tailored to metaverse needs (including evaluation/governance), and a structured research agenda that surfaces genuine open problems (cross-world portability, spatial governance, SLA transfer to non-deterministic agents). The contribution is definitional and architectural rather than empirical; its value is agenda-setting for service computing in immersive environments, not a demonstrated system result.

major comments (3)
  1. [§II.B, §II.E, Figs. 1, 3, 5] §II.B (AaaS layers; QoS & governance), §II.E (Meta-AaaS definition), and Figs. 1, 3, 5 assert that classical service-computing mechanisms—explicit capability descriptions, registration/discovery, orchestration, composition, and enforceable SLAs/trust—transfer to persistent, non-deterministic, tool-using, embodied agents. No reference interface, capability descriptor schema, composition worked example, or failure/SLA model is given for how hallucination, open tool use, long-horizon state, or cross-world embodiment are represented and enforced. This transfer is load-bearing for the claim that Meta-AaaS is an operational “as-a-Service” paradigm rather than a renaming of multi-agent stacks; at minimum the revision should add one concrete composition/SLA sketch or an explicit feasibility boundary.
  2. [§I.C, §II.E] Related work already includes agentic services computing (Deng et al.), AaaS-AN / agent networks (Zhu et al.), and the authors’ own metaverse-services and Big Service lines. The manuscript positions Meta-AaaS as a “new paradigm” but does not state crisp differentiators (e.g., what Meta-AaaS requires beyond Deng’s four-phase lifecycle plus embodiment/cross-world constraints). A short comparison table or paragraph fixing scope relative to these baselines is needed so novelty is auditable rather than nominal.
  3. [§III.B, Fig. 4] §III.B application sketches (healthcare, manufacturing, education, entertainment, tourism) remain scenario prose. None is mapped onto the Meta-AaaS layers, atomic capability services, or the four-stage loop of Fig. 4, so they do not stress-test discovery, composition, virtual–physical actuation, or governance. One end-to-end walk-through (roles invoked, interfaces, feedback into maintenance) would substantially strengthen the central architectural claim.
minor comments (6)
  1. [Abstract, §I, §V] Abstract and §I repeatedly promise that AMServ/Meta-AaaS “will bring great opportunities” and “promote rapid development”; tone down promotional forecasting in favor of scoped claims about the proposed framing.
  2. [Table I, Table II] Table I header spacing/typography (“COMPARISON OF THEFOUREVOLUTIONARYTYPES”) and similar concatenated titles (Table II, several section heads) need copy-editing.
  3. [Fig. 2, Fig. 3] Fig. 2 and Fig. 3 are dense; axis/layer labels and the distinction between “AMServ Collaboration Hyperchain” vs “Orchestration Hyperchain” are hard to parse at column width. Consider simplifying or splitting.
  4. [§II.C, §III.A] “Metaverse-Ware” is used as an execution substrate (§II.C, §III.A, Fig. 5) but never defined beyond a pointer to prior work; a one-sentence operational definition would help standalone readers.
  5. [§IV] §IV lists nine research topics at similar depth; a short prioritization or dependency note (what must be solved before SLA-backed Meta-AaaS is credible) would improve the agenda’s usefulness.
  6. Minor grammar/article issues recur (e.g., “the agent’s abilities are encapsulated, such as perception…”; “an Agentic Metaverse Service, denoted as AMServ, is produced”). A full proofread pass is warranted.

Circularity Check

1 steps flagged

Visionary synthesis with mild author-program self-continuation; no derivation-by-construction or fitted-prediction circularity.

specific steps
  1. self citation load bearing [§I.C Related Work; §II.C Metaverse and Metaverse Services]
    "Xu et al. [1], [33], [34] identified the key characteristics of metaverse services, including immersive interaction, virtual-real fusion, and cross-world service aggregation... Accordingly, Metaverse services can be regarded as an upgraded instantiation of the Big Service paradigm [25], i.e., Big Service 2.0..."

    The paper’s staging of metaverse services (and thus the substrate for AMServ/Meta-AaaS) rests substantially on the lead authors’ own prior conceptual papers rather than independent external formalization. This is program self-continuation that frames the ‘new paradigm,’ not a numeric or theorem-level reduction; it slightly elevates circularity risk without forcing the central architectural claims.

full rationale

This is a conceptual/agenda paper proposing named paradigms (AMServ, Meta-AaaS), layered architectures, role taxonomies, and open research topics. It contains no equations, fitted parameters, uniqueness theorems, or empirical predictions that could reduce to inputs by construction. The SaaS→AaaS and agent-evolution narratives are standard literature synthesis; application sketches and the §IV agenda are forward-looking rather than forced results. The only mild circularity-adjacent pattern is load-bearing reliance on the authors’ prior Big Service / metaverse-services framing to position Metaverse services as ‘Big Service 2.0’ and then AMServ as the next step—normal research-program continuation, not Eq.X≡Eq.Y. Definitional naming of AMServ/Meta-AaaS is expected in a paradigm proposal and does not manufacture a false first-principles claim. Score 2 reflects one non-decisive self-citation strand; central content (AaaS layers, agent roles, Meta-AaaS lifecycle, research topics) remains independently stated.

Axiom & Free-Parameter Ledger

0 free parameters · 5 axioms · 3 invented entities

The paper’s load-bearing content is conceptual. It inherits standard service-computing and agent assumptions, assumes GenAI/LLM agents plus metaverse infrastructure are sufficiently mature to host SLA-governed agent services, and introduces named service entities (AMServ, Meta-AaaS) whose existence is definitional rather than evidenced by external measurement.

axioms (5)
  • domain assumption LLM/agentic AI systems can sustain closed-loop perception–reasoning–planning–action with tool use and multi-agent collaboration at service quality suitable for production metaverse workloads.
    Invoked throughout §I–II when elevating agents from chatbots to primary service units; not validated in-paper.
  • domain assumption Classical services-computing mechanisms (registration, discovery, orchestration, composition, SLAs, monitoring, value management) transfer to persistent, non-deterministic, stateful agents.
    Stated in §II.B AaaS definition and architecture; central to calling the result an as-a-Service paradigm.
  • domain assumption The metaverse is a technically feasible, persistent, interoperable virtual–physical ecosystem in which business processes are organized as services (Big Service 2.0).
    §II.C and Fig. 2; builds on authors’ prior metaverse-services framing and general metaverse surveys.
  • ad hoc to paper Agent functional roles can be factored into perception, planning/decision, execution, content generation, social collaboration, and evaluation/governance as composable building blocks.
    §II.D taxonomy; useful design choice, not derived from a uniqueness argument or empirical clustering.
  • ad hoc to paper AMServ operates as a four-stage loop: scene perception & demand recognition → matching & solution generation → virtual–physical execution → optimization & scenario iteration.
    §III.A and Fig. 4; process model postulated for the paradigm.
invented entities (3)
  • Agentic Metaverse Service (AMServ) no independent evidence
    purpose: Name the class of intelligent, agent-driven composite services operating in metaverse / cyber-physical environments.
    Defined in Abstract and §II.E with characteristics (autonomy, proactivity, embodiment, cross-time-space convergence, collaboration, evolvability); no independent operational deployment is shown.
  • Meta-AaaS no independent evidence
    purpose: Name the as-a-Service implementation architecture and platform for constructing, deploying, composing, and governing AMServ.
    §II.E and Fig. 3/5; packaging construct rather than a shipped platform with external adopters or benchmarks.
  • Metaverse-Ware (as AMServ execution substrate) no independent evidence
    purpose: Serve as the metaverse-side counterpart to software through which plans are deployed via avatars, NPCs, digital humans, and twins.
    Referenced in §II.C and §III.A; term continues authors’ prior metaverse-services vocabulary without a formal specification here.

pith-pipeline@v1.2.0-daily-grok45 · 21310 in / 3672 out tokens · 75178 ms · 2026-07-31T13:31:25.336802+00:00 · methodology

0 comments
read the original abstract

Generative Artificial Intelligence (GenAI) is reconstructing the digital virtual world, upgrading agents through enhancing their abilities in autonomous learning, multi-modal interaction, content generation, and collaborative decision-making. In particular, the shift from conversational chatbots to agentic AI, the most recent significant technical breakthrough of GenAI, has brought a new form of services, agentic services and Agent-as-a-Service (AaaS), in which the agent's abilities are encapsulated, such as perception, decision-making, execution, collaboration, and content generation, to provide the customized agent services to users. The metaverse is a virtual ecosystem for human life, work, creation, and entertainment, supported by the new generation of digital technologies. Through combining agentic services and the metaverse, an Agentic Metaverse Service, denoted as AMServ, is produced for metaverse business processing, as a new form of metaverse service. The AaaS in the metaverse environment, denoted as Meta-AaaS, as an approach to realize AMServ, has become a new paradigm of agentic services and service computing. This paper overviews the evolution and new features of agents and services empowered by GenAI, reveals the roles and principles of agentic services in the metaverse environment, presents the forms, characteristics, and principles of the AMServ and the Meta-AaaS, discusses the typical application examples of the AMServ and the Meta-AaaS, and finally points out the new tendencies and research directions of the AMServ and the Meta-AaaS. The AMServ and the Meta-AaaS will bring great opportunities to human society and services in the AI era, and promote the rapid development of emerging service industries in the future.

Figures

Figures reproduced from arXiv: 2607.28242 by Boualem Benatallah, Quan Z. Sheng, Ruipeng Han, Xiaofei Xu, Xiao Wang, Zhongjie Wang.

Figure 1
Figure 1. Figure 1: The conceptual architecture of AaaS also reduce the cost of adopting agent technologies for organizations that do not maintain full agent stacks internally. Multimodal interfaces allow users to interact with AaaS through natural channels, while standardized agentic APIs support coordination among AaaS instances and external systems. After deployment, learning mechanisms can update decision policies or serv… view at source ↗
Figure 2
Figure 2. Figure 2: The conceptual architecture of the Metaverse services [PITH_FULL_IMAGE:figures/full_fig_p006_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: The conceptual architecture of the Meta-AaaS [PITH_FULL_IMAGE:figures/full_fig_p007_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: The principle of AMServ composition, agent-as-a-service definition, knowledge and tool binding, multimodal interface specification, agentic service testing, while the latter supports service registration, discovery, invocation, operation, scheduling, coordination, monitoring, maintenance, evolution, feedback collection, and governance. Compared to the AMServ which describe the function and behavior of agen… view at source ↗
Figure 5
Figure 5. Figure 5: The architecture of Meta-AaaS B. Applications of Agentic Metaverse Services and Meta-AaaS Among numerous applications of AMServ and Meta-AaaS, five typical examples are briefly mentioned here to illustrate how Meta-AaaS can be applied to realize AMServ in practice. Healthcare and Elderly-Care. In the healthcare and elderly-care domains, AMServ can support continuous monitoring of users’ physiological state… view at source ↗

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

50 extracted references · 4 linked inside Pith

  1. [1]

    Metaverse services: The way of services towards the future,

    X. Xu, Q. Z. Sheng, B. Benatallah, Z. Chen, R. Gazda, A. E. Saddik, and M. P. Singh, “Metaverse services: The way of services towards the future,” in2023 IEEE International Conference on Web Services (ICWS). IEEE, 2023, pp. 179–185

    2023

  2. [2]

    The Emerging Metaverse: IEEE ISEMV 2024 Retrospective and Future Directions,

    L. Nisiotis, C. Metra, J. Athavale, D. Milojcic, S. Dukes, J. Ranaweera, and S.-K. Hawkins, “The Emerging Metaverse: IEEE ISEMV 2024 Retrospective and Future Directions,”Computer, vol. 58, no. 4, pp. 58–64, 2025

    2024

  3. [3]

    McCarthyet al.,Programs with common sense

    J. McCarthyet al.,Programs with common sense. RLE and MIT Computation Center Cambridge, MA, USA, 1960

    1960

  4. [4]

    A universal modular actor formalism for artificial intelligence,

    C. Hewitt, P. Bishop, and R. Steiger, “A universal modular actor formalism for artificial intelligence,” inProceedings of the 3rd International Joint Conference on Artificial Intelligence, ser. IJCAI’73. San Francisco, CA, USA: Morgan Kaufmann Publishers Inc., 1973, p. 235–245

    1973

  5. [5]

    The rise and potential of large language model based agents: A survey,

    Z. Xi, W. Chen, X. Guo, W. He, Y . Ding, B. Hong, M. Zhang, J. Wang, S. Jin, E. Zhouet al., “The rise and potential of large language model based agents: A survey,”Science China Information Sciences, vol. 68, no. 2, p. 121101, 2025

    2025

  6. [6]

    A comprehensive survey of self-evolving ai agents: A new paradigm bridging foundation models and lifelong agentic systems,

    J. Fang, Y . Peng, X. Zhang, Y . Wang, X. Yi, G. Zhang, Y . Xu, B. Wu, S. Liu, Z. Liet al., “A comprehensive survey of self-evolving ai agents: A new paradigm bridging foundation models and lifelong agentic systems,”arXiv preprint arXiv:2508.07407, 2025

    Pith/arXiv arXiv 2025

  7. [7]

    A survey of self-evolving agents: On path to artificial super intelligence,

    H.-a. Gao, J. Geng, W. Hua, M. Hu, X. Juan, H. Liu, S. Liu, J. Qiu, X. Qi, Y . Wuet al., “A survey of self-evolving agents: On path to artificial super intelligence,”arXiv preprint arXiv:2507.21046, vol. 1, 2025

    Pith/arXiv arXiv 2025

  8. [8]

    Intelligent agents: Theory and practice,

    M. Wooldridge and N. R. Jennings, “Intelligent agents: Theory and practice,”The Knowledge Engineering Review, vol. 10, no. 2, pp. 115–152, 1995

    1995

  9. [9]

    Bdi agents: from theory to practice

    A. S. Rao, M. P. Georgeffet al., “Bdi agents: from theory to practice.” inIcmas, vol. 95, 1995, pp. 312–319

    1995

  10. [10]

    Human-level control through deep reinforcement learning,

    V . Mnih, K. Kavukcuoglu, D. Silver, A. A. Rusu, J. Veness, M. G. Bellemare, A. Graves, M. Riedmiller, A. K. Fidjeland, G. Ostrovski et al., “Human-level control through deep reinforcement learning,” Nature, vol. 518, no. 7540, pp. 529–533, 2015

    2015

  11. [11]

    Mastering the game of go with deep neural networks and tree search,

    D. Silver, A. Huang, C. J. Maddison, A. Guez, L. Sifre, G. Van Den Driessche, J. Schrittwieser, I. Antonoglou, V . Panneershelvam, M. Lanctotet al., “Mastering the game of go with deep neural networks and tree search,”Nature, vol. 529, no. 7587, pp. 484–489, 2016

    2016

  12. [12]

    Chain-of-thought prompting elicits reasoning in large language models,

    J. Wei, X. Wang, D. Schuurmans, M. Bosma, F. Xia, E. Chi, Q. V . Le, D. Zhouet al., “Chain-of-thought prompting elicits reasoning in large language models,”Advances in Neural Information Processing Systems, vol. 35, pp. 24 824–24 837, 2022

    2022

  13. [13]

    React: Synergizing reasoning and acting in language models,

    S. Yao, J. Zhao, D. Yu, N. Du, I. Shafran, K. R. Narasimhan, and Y . Cao, “React: Synergizing reasoning and acting in language models,” inThe Eleventh International Conference on Learning Representations, 2022

    2022

  14. [14]

    Toolformer: Language models can teach themselves to use tools,

    T. Schick, J. Dwivedi-Yu, R. Dessì, R. Raileanu, M. Lomeli, E. Hambro, L. Zettlemoyer, N. Cancedda, and T. Scialom, “Toolformer: Language models can teach themselves to use tools,”Advances in Neural Information Processing Systems, vol. 36, pp. 68 539–68 551, 2023

    2023

  15. [15]

    Reflexion: Language agents with verbal reinforcement learning,

    N. Shinn, F. Cassano, A. Gopinath, K. Narasimhan, and S. Yao, “Reflexion: Language agents with verbal reinforcement learning,” Advances in Neural Information Processing Systems, vol. 36, pp. 8634–8652, 2023

    2023

  16. [16]

    Generative agents: Interactive simulacra of human behavior,

    J. S. Park, J. O’Brien, C. J. Cai, M. R. Morris, P. Liang, and M. S. Bernstein, “Generative agents: Interactive simulacra of human behavior,” inProceedings of the 36th Annual ACM Symposium on User Interface Software and Technology, 2023, pp. 1–22

    2023

  17. [17]

    Welcome to the era of experience,

    D. Silver and R. S. Sutton, “Welcome to the era of experience,”Google AI, vol. 1, p. 11, 2025

    2025

  18. [18]

    A Service Computing Manifesto: the Next 10 Years,

    A. Bouguettaya, M. P. Singh, M. N. Huhns, Q. Z. Sheng, H. Dong, Q. Yu, A. G. Neiat, S. Mistry, B. Benatallah, B. Medjahed, M. Ouzzani, F. Casati, X. Liu, H. Wang, D. Georgakopoulos, L. Chen, S. Nepal, Z. Malik, A. Erradi, Y . Wang, M. B. Blake, S. Dustdar, F. Leymann, and M. P. Papazoglou, “A Service Computing Manifesto: the Next 10 Years,”Communications ...

    2017

  19. [19]

    Service-oriented computing: a research roadmap,

    M. P. Papazoglou, P. Traverso, S. Dustdar, and F. Leymann, “Service-oriented computing: a research roadmap,”International Journal of Cooperative Information Systems, vol. 17, no. 02, pp. 223–255, 2008

    2008

  20. [20]

    Bouguettaya, Q

    A. Bouguettaya, Q. Z. Sheng, and F. Daniel, Eds.,Web Services Foundations. Springer, 2014

    2014

  21. [21]

    Cloud computing and emerging it platforms: Vision, hype, and reality for delivering computing as the 5th utility,

    R. Buyya, C. S. Yeo, S. Venugopal, J. Broberg, and I. Brandic, “Cloud computing and emerging it platforms: Vision, hype, and reality for delivering computing as the 5th utility,”Future Generation Computer Systems, vol. 25, no. 6, pp. 599–616, 2009

    2009

  22. [22]

    A Taxonomy and Survey of Cloud Resource Orchestration Techniques,

    D. Weerasiri, M. C. Barukh, B. Benatallah, Q. Z. Sheng, and R. Ranjan, “A Taxonomy and Survey of Cloud Resource Orchestration Techniques,” ACM Computing Surveys, vol. 50, no. 2, pp. 26:1–26:41, 2017

    2017

  23. [23]

    Agentic services computing,

    S. Deng, H. Zhao, Z. Wang, G. Cheng, P. Chen, W. Qian, Z. Ling, J. Yin, A. Y . Zomaya, and S. Dustdar, “Agentic services computing,” arXiv preprint arXiv:2509.24380, 2025

    Pith/arXiv arXiv 2025

  24. [24]

    Web services composition: A decade’s overview,

    Q. Z. Sheng, X. Qiao, A. V . Vasilakos, C. Szabo, S. Bourne, and X. Xu, “Web services composition: A decade’s overview,”Information Sciences, vol. 280, pp. 218–238, 2014

    2014

  25. [25]

    From big data to big service,

    X. Xu, Q. Z. Sheng, L.-J. Zhang, Y . Fan, and S. Dustdar, “From big data to big service,”Computer, vol. 48, no. 7, pp. 80–83, 2015

    2015

  26. [26]

    A Paradigm Shift in Service Research: The Case of Service Composition,

    M. Aiello, “A Paradigm Shift in Service Research: The Case of Service Composition,”IEEE Transactions on Services Computing, vol. 18, no. 3, pp. 1213–1215, 2025

    2025

  27. [27]

    Hugginggpt: Solving ai tasks with chatgpt and its friends in hugging face,

    Y . Shen, K. Song, X. Tan, D. Li, W. Lu, and Y . Zhuang, “Hugginggpt: Solving ai tasks with chatgpt and its friends in hugging face,”Advances in Neural Information Processing Systems, vol. 36, pp. 38 154–38 180, 2023

    2023

  28. [28]

    Autogen: Enabling next-gen llm applications via multi-agent conversations,

    Q. Wu, G. Bansal, J. Zhang, Y . Wu, B. Li, E. Zhu, L. Jiang, X. Zhang, S. Zhang, J. Liuet al., “Autogen: Enabling next-gen llm applications via multi-agent conversations,” inFirst Conference on Language Modeling, 2024

    2024

  29. [29]

    Camel: Communicative agents for

    G. Li, H. Hammoud, H. Itani, D. Khizbullin, and B. Ghanem, “Camel: Communicative agents for "mind" exploration of large language model society,”Advances in Neural Information Processing Systems, vol. 36, pp. 51 991–52 008, 2023

    2023

  30. [30]

    Ai agents vs. agentic ai: A conceptual taxonomy, applications and challenges,

    R. Sapkota, K. I. Roumeliotis, and M. Karkee, “Ai agents vs. agentic ai: A conceptual taxonomy, applications and challenges,”Information Fusion, p. 103599, 2025

    2025

  31. [31]

    Agent-as-a-service based on agent network,

    Y . Zhu, H. Liu, J. Wang, B. Li, Z. Yin, and Y . Liao, “Agent-as-a-service based on agent network,”arXiv preprint arXiv:2505.08446, 2025

    Pith/arXiv arXiv 2025

  32. [32]

    Information Technology — Metamodel Framework for Interoperability (MFI) — Part 9: On Demand Model Selection Based on RGPS,

    ISO/IEC, “Information Technology — Metamodel Framework for Interoperability (MFI) — Part 9: On Demand Model Selection Based on RGPS,” ISO/IEC TR 19763-9:2015, 2015

    2015

  33. [33]

    Metaverse services in computing and engineering education,

    X. Xu and J. Impagliazzo, “Metaverse services in computing and engineering education,”Frontiers of Digital Education, vol. 1, no. 2, pp. 132–141, 2024

    2024

  34. [34]

    Guest Editors’ Introduction: Metaverse Services,

    Q. Z. Sheng, X. Xu, and B. Benatallah, “Guest Editors’ Introduction: Metaverse Services,”IEEE Transactions on Services Computing, vol. 19, no. 3, 2026

    2026

  35. [35]

    Toward Agentic AI Networking in 6G: A Generative Foundation Model-as-Agent Approach,

    Y . Xiao, G. Shi, and P. Zhang, “Toward Agentic AI Networking in 6G: A Generative Foundation Model-as-Agent Approach,”IEEE Communications Magazine, vol. 63, no. 9, pp. 68–74, 2025

    2025

  36. [36]

    Sp 800-145. the nist definition of cloud computing,

    P. Mell and T. Grance, “Sp 800-145. the nist definition of cloud computing,” Gaithersburg, MD, USA, Tech. Rep., 2011

    2011

  37. [37]

    Everything as a service (xaas) on the cloud: origins, current and future trends,

    Y . Duan, G. Fu, N. Zhou, X. Sun, N. C. Narendra, and B. Hu, “Everything as a service (xaas) on the cloud: origins, current and future trends,” in2015 IEEE 8th International Conference on Cloud Computing. IEEE, 2015, pp. 621–628

    2015

  38. [38]

    Stephenson,Snow Crash

    N. Stephenson,Snow Crash. Penguin UK, 1994

    1994

  39. [39]

    Ball,The metaverse: and how it will revolutionize everything

    M. Ball,The metaverse: and how it will revolutionize everything. Liveright Publishing, 2022

    2022

  40. [40]

    3D Virtual Worlds and the Metaverse: Current Status and Future Possibilities,

    J. D. N. Dionisio, W. G. B. III, and R. Gilbert, “3D Virtual Worlds and the Metaverse: Current Status and Future Possibilities,”ACM Computing Surveys, vol. 45, no. 3, 2013

    2013

  41. [41]

    A Survey on Metaverse: Fundamentals, Security, and Privacy,

    Y . Wang, Z. Su, N. Zhang, R. Xing, D. Liu, T. H. Luan, and X. Shen, “A Survey on Metaverse: Fundamentals, Security, and Privacy,”IEEE Communications Surveys & Tutorials, vol. 25, no. 1, pp. 319–352, 2023

    2023

  42. [42]

    How Big Service and Internet of Services Drive Business Innovation and Transformation,

    H. Shi, H. Xu, X. Xu, and Z. Wang, “How Big Service and Internet of Services Drive Business Innovation and Transformation,” inProceedings of the 34th International Conference on Advanced Information Systems Engineering (CAiSE 2022), ser. Lecture Notes in Computer Science, X. Franch, G. Poels, F. Gailly, and M. Snoeck, Eds. Leuven, Belgium: Springer, 2022,...

    2022

  43. [43]

    An Internet of Things Service Roadmap,

    A. Bouguettaya, Q. Z. Sheng, B. Benatallah, A. G. Neiat, S. Mistry, A. Ghose, S. Nepal, and L. Yao, “An Internet of Things Service Roadmap,”Communications of the ACM, vol. 64, no. 9, pp. 86–95, 2021

    2021

  44. [44]

    The Self-Serv Environment for Web Services Composition,

    B. Benatallah, Q. Z. Sheng, and M. Dumas, “The Self-Serv Environment for Web Services Composition,”IEEE Internet Computing, vol. 7, no. 1, pp. 40–48, 2003

    2003

  45. [45]

    Agentic Artificial Intelligence (AI): Architectures, Taxonomies, and Evaluation of Large Language Model Agents,

    A. V , G. G. R., and R. Buyya, “Agentic Artificial Intelligence (AI): Architectures, Taxonomies, and Evaluation of Large Language Model Agents,” 2026. [Online]. Available: https://arxiv.org/abs/2601.12560

    arXiv 2026

  46. [46]

    Web Service Composition: A Survey of Techniques and Tools,

    A. L. Lemos, F. Daniel, and B. Benatallah, “Web Service Composition: A Survey of Techniques and Tools,”ACM Computing Surveys, vol. 48, no. 3, pp. 33:1–33:41, 2016

    2016

  47. [47]

    Q. Z. Sheng, Y . Liu, and L. Yao,Harnessing Artificial Intelligence and Pervasive Internet of Things for an Empowered Aging. Springer, May 2026

    2026

  48. [48]

    Enhancing Wisdom Manufacturing as Industrial Metaverse for Industry and Society 5.0,

    X. Yao, N. Ma, J. Zhang, K. Wang, E. Yang, and M. Faccio, “Enhancing Wisdom Manufacturing as Industrial Metaverse for Industry and Society 5.0,”Journal of Intelligent Manufacturing, vol. 35, pp. 235–255, 2024

    2024

  49. [49]

    Ethics and cultural background as key factors for an attractive metaverse,

    T. Catarci, G. De Nicola, and D. Raffini, “Ethics and cultural background as key factors for an attractive metaverse,”Communications of the ACM, vol. 67, no. 12, pp. 78–84, 2024

    2024

  50. [50]

    Metaverse tourism: Conceptual framework and research propositions,

    C. Koo, J. Kwon, N. Chung, and J. Kim, “Metaverse tourism: Conceptual framework and research propositions,”Current Issues in Tourism, vol. 26, no. 20, pp. 3268–3274, 2023

    2023