pith. sign in

arxiv: 2605.00570 · v1 · submitted 2026-05-01 · 💻 cs.NI

Beyond Per-Request QoS: Coordinating Industrial Workflows with B5G/6G Network Capabilities

Qize Guo , Bjoern Riemer , Tarik Taleb , Yan Chen , Hao Yu , Hemant Zope This is my paper

Pith reviewed 2026-05-09 18:43 UTC · model grok-4.3

classification 💻 cs.NI
keywords B5G networksindustrial workflowsQoS coordinationcapability-aware planningservice continuitydemand trajectoryworkflow completion
0
0 comments X

The pith

A coordination framework lets B5G/6G networks expose sustainable QoS profiles so industrial workflows can map phases and submit demand trajectories for joint planning.

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

Current per-request QoS handling treats each workflow phase in isolation and cannot anticipate upcoming demands or near-term network limits, leading to avoidable disruptions. The paper introduces a bounded-window approach in which the network discloses the QoS profiles it can sustain, the industrial application maps its sequence of phases onto those profiles, and both sides assess the resulting trajectory together. Coordinated updates handle changes during execution. A real B5G video-inspection deployment plus large-scale simulation show measurable gains in continuity, fewer rejections, and higher completion rates under load. This matters because future industrial services will consist of multi-phase workflows whose requirements vary sharply and whose failures are costly.

Core claim

Within a bounded planning window the network exposes the QoS profiles it can sustainably support; the industrial side maps upcoming workflow phases to these disclosed capabilities and submits the resulting demand trajectory for joint assessment, with support for coordinated updates when conditions change.

What carries the argument

Capability-aware coordination framework that exposes sustainable QoS profiles, maps workflow phases to them, and jointly evaluates demand trajectories.

If this is right

  • Service continuity improves because foreseeable mismatches between workflow demands and network capabilities are resolved before execution.
  • Disruptive rejections decrease because the joint assessment occurs against a realistic, time-bounded capability disclosure.
  • Workflow completion rates rise under heavy load by allowing the system to plan the entire sequence rather than reacting phase by phase.
  • Dynamic updates become possible when network conditions change, preserving the same coordination benefits during execution.

Where Pith is reading between the lines

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

  • The same exposure-and-mapping pattern could be applied to other time-critical domains such as autonomous transport or smart-grid control.
  • Standardized interfaces for advertising sustainable QoS profiles would be needed before widespread adoption.
  • The framework implicitly requires that workflow phases can be described with sufficient precision to match network profiles.

Load-bearing premise

Networks can accurately expose the QoS profiles they can sustain over the planning window and workflows can be mapped to those profiles without large prediction errors or added overhead.

What would settle it

A deployment or simulation under heavy load in which the coordinated framework produces no statistically significant reduction in disruptive rejections or increase in workflow completion compared with standard per-request QoS.

Figures

Figures reproduced from arXiv: 2605.00570 by Bjoern Riemer, Hao Yu, Hemant Zope, Qize Guo, Tarik Taleb, Yan Chen.

Figure 1
Figure 1. Figure 1: Capability-aware coordination framework with a capability-bounded network agent and multiple phase-driven industrial view at source ↗
Figure 2
Figure 2. Figure 2: Two-stage coordination workflow between the network view at source ↗
Figure 3
Figure 3. Figure 3: 5G testbed case study. Left: testbed topology. Right: view at source ↗
Figure 4
Figure 4. Figure 4: Simulation results. (a)–(b) Aggregate demand and view at source ↗
read the original abstract

Beyond-5G (B5G) and 6G networks are expected to enable more complex industrial services, which often operate according to multi-phase workflows with phase-specific communication requirements. However, current interaction between applications and networks remains predominantly request-driven: Quality of Service (QoS) is requested at each workflow phase transition and evaluated independently, without explicit consideration of upcoming demand or network's near-term capability. This mismatch limits the ability of both sides to plan ahead, often resulting in foreseeable incompatibilities, even service disruptions. This article presents a capability-aware coordination framework for workflow-based industrial services. Within a bounded planning window, the network exposes the QoS profiles it can sustainably support, while the industrial side maps upcoming workflow phases to these disclosed capabilities and submits the resulting demand trajectory for joint assessment. The framework also supports coordinated updates when network conditions change during execution. An industrial video inspection case study on a real B5G system, complemented by large-scale simulation, illustrates that such coordination can improve service continuity, reduce disruptive rejections, and increase workflow completion under heavy load. The results suggest that future industrial networking should move beyond reactive per-request QoS handling toward forward-looking, capability-aware, workflow-level coordination.

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

2 major / 1 minor

Summary. The paper proposes a capability-aware coordination framework for multi-phase industrial workflows over B5G/6G networks. Rather than handling QoS on a per-request basis at each phase transition, the network exposes sustainable QoS profiles within a bounded planning window; the industrial side then maps upcoming workflow phases to these profiles and submits a demand trajectory for joint assessment, with support for coordinated updates on condition changes. An industrial video-inspection case study on a real B5G system plus large-scale simulation is presented to show gains in service continuity, fewer disruptive rejections, and higher workflow completion under heavy load.

Significance. If the empirical claims hold, the work would provide a concrete path from reactive per-request QoS to proactive, workflow-level coordination, which is relevant for time-sensitive industrial services expected in 6G. The absence of free parameters or self-referential definitions in the core proposal is a positive feature.

major comments (2)
  1. The abstract states that the video-inspection case study on a real B5G system and the large-scale simulation demonstrate improvements in continuity, rejections, and completion rates, yet the manuscript supplies no description of the experimental setup, chosen metrics, baselines, implementation details of the framework, or statistical significance of the reported gains. This absence prevents assessment of whether the data actually support the central claim.
  2. The framework's benefits depend on the network exposing accurate sustainable QoS profiles that remain valid for the planning-window duration and on low-error mapping of workflow phases to those profiles. No quantitative results are given for prediction error, coordination overhead (in messages or latency per transition), or realized-vs-exposed QoS mismatch under channel variability in either the case study or the simulation.
minor comments (1)
  1. The term 'demand trajectory' is introduced without a formal definition or example in the abstract; a short illustrative figure or pseudocode would clarify how phases are mapped to exposed profiles.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive and detailed review. The comments highlight important aspects of clarity and completeness in the evaluation. We address each major comment below and commit to revisions that strengthen the manuscript without altering its core contributions.

read point-by-point responses

  1. Referee: The abstract states that the video-inspection case study on a real B5G system and the large-scale simulation demonstrate improvements in continuity, rejections, and completion rates, yet the manuscript supplies no description of the experimental setup, chosen metrics, baselines, implementation details of the framework, or statistical significance of the reported gains. This absence prevents assessment of whether the data actually support the central claim.

    Authors: We acknowledge that the experimental details require more explicit and consolidated presentation to allow independent assessment. The manuscript contains the relevant information in Sections 4 (framework implementation details, including the coordination protocol and QoS profile mapping) and 5 (case study on the real B5G testbed with video-inspection workflow, simulation parameters, metrics defined as service continuity, rejection rate, and workflow completion rate, plus the per-request baseline). However, these elements are distributed and lack a concise summary or statistical analysis. We will revise the paper by adding a dedicated experimental methodology subsection early in Section 5, including a table of metrics and baselines, and by reporting statistical significance (e.g., confidence intervals or hypothesis tests) for the reported gains. The abstract will be updated to reference these elements briefly. This constitutes a major revision. revision: yes

  2. Referee: The framework's benefits depend on the network exposing accurate sustainable QoS profiles that remain valid for the planning-window duration and on low-error mapping of workflow phases to those profiles. No quantitative results are given for prediction error, coordination overhead (in messages or latency per transition), or realized-vs-exposed QoS mismatch under channel variability in either the case study or the simulation.

    Authors: We agree that explicit quantification of these assumptions is necessary to substantiate the framework's robustness. The current evaluation focuses on end-to-end outcomes (continuity, rejections, completion) under the stated conditions but does not isolate prediction error, signaling overhead, or QoS mismatch. In the revised version we will add targeted results: prediction accuracy of sustainable QoS profiles over the planning window, coordination overhead in number of messages and latency per transition, and realized-versus-exposed QoS deviation under channel variability. These will be reported for both the real B5G case study and the large-scale simulation, with new figures or tables as appropriate. This addition directly addresses the dependency on accurate profiles and mapping. revision: yes

Circularity Check

0 steps flagged

No circularity: framework proposal evaluated via external case study and simulation

full rationale

The paper introduces a capability-aware coordination framework for industrial workflows in B5G/6G networks. It describes the framework conceptually (network exposes sustainable QoS profiles within a planning window; industrial side maps phases and submits demand trajectory) and supports it with an industrial video inspection case study on a real B5G system plus large-scale simulation. No equations, fitted parameters, or derivations are present that reduce predictions to inputs by construction. No self-citation chains are load-bearing for the central claims, and the evaluation uses external benchmarks rather than internal redefinitions. This matches the default expectation of a non-circular proposal paper.

Axiom & Free-Parameter Ledger

0 free parameters · 2 axioms · 1 invented entities

The paper rests on domain assumptions about workflow structures and network capability exposure without introducing free parameters or new physical entities; the coordination framework is the primary addition.

axioms (2)
  • domain assumption Industrial services operate according to multi-phase workflows with phase-specific communication requirements
    Stated at the start of the abstract as the basis for the identified mismatch with current QoS handling.
  • domain assumption The network can expose QoS profiles it can sustainably support within a bounded planning window
    Core premise required for the industrial side to map phases and submit demand trajectories.
invented entities (1)
  • Demand trajectory no independent evidence
    purpose: Representation of mapped workflow phases submitted for joint network assessment
    Introduced as part of the coordination process to enable forward-looking planning.

pith-pipeline@v0.9.0 · 5535 in / 1421 out tokens · 40827 ms · 2026-05-09T18:43:47.631231+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

15 extracted references · 15 canonical work pages

  1. [1]

    Innovation Trends in I4.0 enabled by 5G and Beyond Networks,

    5G-PPP Technology Board, “Innovation Trends in I4.0 enabled by 5G and Beyond Networks,” 5G- PPP Technology Board, White Paper, Oct. 2023. [Online]. Available: https://5g-ppp.eu/wp-content/uploads/2023/10/ Innovation-Trends-in-I4.0-enabled-by-5G-and-Beyond-Networks.pdf

    work page 2023

  2. [2]

    The roadmap to 6g: Intelligent and lean networks,

    Y . Huang, Z. Tong, N. Li, Z. Shao, Q. Wang, and J. Wang, “The roadmap to 6g: Intelligent and lean networks,”IEEE Communications Magazine, vol. 63, no. 8, pp. 40–46, 2025

    work page 2025

  3. [3]

    Dynamic qos adaptation via exposed service apis for advanced cam use cases,

    B. Turkovic, R. van de Vlasakker, S. Potnuru, Y . Shiferaw, R. S. Schwartz, P.-P. Schackmann, G. Kov ´acs, A. Forrai, G. Kakes, and P. Span, “Dynamic qos adaptation via exposed service apis for advanced cam use cases,” in2025 Joint European Conference on Networks and Communications & 6G Summit (EuCNC/6G Summit), 2025, pp. 345– 350

    work page 2025

  4. [4]

    Next-gen connectivity: Dynamic qos optimization for 5g standalone and vertical integration,

    V . Charpentier, N. Slamnik-Krije ˇstorac, A. Akintola, M. Gasparroni, B. Obasola, L. Bruynseels, B. Gjorgjievski, G. Kia, X. Limani, J. F. Nunes Pinheiro, and J. M. Marquez-Barja, “Next-gen connectivity: Dynamic qos optimization for 5g standalone and vertical integration,” inIEEE INFOCOM 2024 - IEEE Conference on Computer Communi- cations Workshops (INFO...

    work page 2024

  5. [5]

    2023, accessed: 2026-01-11

    3GPP,5G System; Network Exposure Function (NEF) Northbound APIs; Stage 3, 3rd Generation Partnership Project (3GPP) Technical Specification TS 29.522, Dec. 2023, accessed: 2026-01-11. [Online]. Available: https://www.3gpp.org/DynaReport/29512.htm

    work page 2023

  6. [6]

    2024, alternative QoS Profile (AQP) mechanism

    3GPP,Policy and Charging Control Framework for the 5G System (5GS); Stage 2, 3rd Generation Partnership Project (3GPP) Technical Specification TS 23.503, Sep. 2024, alternative QoS Profile (AQP) mechanism

    work page 2024

  7. [7]

    Resource ReSerVation protocol (RSVP) – version 1 functional specification,

    R. Braden, L. Zhang, S. Berson, S. Herzog, and S. Jamin, “Resource ReSerVation protocol (RSVP) – version 1 functional specification,” RFC 2205, Sep. 1997

    work page 1997

  8. [8]

    The wsla framework: Specifying and mon- itoring service level agreements for web services,

    A. Keller and H. Ludwig, “The wsla framework: Specifying and mon- itoring service level agreements for web services,”Journal of Network and Systems Management, vol. 11, no. 1, pp. 57–81, 2003

    work page 2003

  9. [9]

    A survey on intent-driven end-to-end 6g mobile communication system,

    Y . Wang, C. Yang, T. Li, Y . Ouyang, X. Mi, and Y . Song, “A survey on intent-driven end-to-end 6g mobile communication system,”IEEE Communications Surveys & Tutorials, vol. 28, pp. 882–915, 2026

    work page 2026

  10. [10]

    An autonomous network orchestration framework integrating large language models with continual reinforce- ment learning,

    M. Shokrnezhad and T. Taleb, “An autonomous network orchestration framework integrating large language models with continual reinforce- ment learning,”IEEE Communications Magazine, vol. 63, no. 8, pp. 78–84, 2025

    work page 2025

  11. [11]

    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, Sep. 2025

    work page 2025

  12. [12]

    2024, predictive QoS via NWDAF analytics

    3GPP,Architecture enhancements for 5G System (5GS) to support network data analytics services, 3rd Generation Partnership Project (3GPP) Technical Specification TS 23.288, Jun. 2024, predictive QoS via NWDAF analytics

    work page 2024

  13. [13]

    Quality on demand (QoD) API,

    CAMARA Project, “Quality on demand (QoD) API,” Linux Foundation, GSMA Open Gateway, 2024, [Online]. Available: https://camaraproject. org/quality-on-demand/

    work page 2024

  14. [14]

    Enabling modular and intelligent iort systems: Integrating the model context protocol for semantic decoupling at the edge,

    Q. Guo, Y . Chen, T. Taleb, and C. Yang, “Enabling modular and intelligent iort systems: Integrating the model context protocol for semantic decoupling at the edge,”IEEE Internet of Things Magazine, vol. 9, no. 1, pp. 39–46, 2026

    work page 2026

  15. [15]

    Berlin platform; 6G- SANDBOX SNS HE Project,

    B. Riemer, P. Merino, and M. Dieudonne, “Berlin platform; 6G- SANDBOX SNS HE Project,” https://6g-sandbox.eu/pilot-6g-sites/ berlin/, 2026, [Accessed 18-03-2026]

    work page 2026