Pith.

Networking and Internet Architecture · arXiv:2611.16801 v1 · submitted 12 Nov 2026 · 23 references

Agentic Orchestration for SLA-Constrained Network Slicing in Programmable Mobile Data Planes

Rodrigo Moreira, Larissa Ferreira Rodrigues Moreira, Joberto S. B. Martins, Tereza C. Carvalho, Flávio de Oliveira Silva

The paper says

“The Third Generation Partnership Project (3GPP) Technical Specification 23.501 (Release 17) defines Maximum Bit Rate (MBR) enforcement at the User Plane Function (UPF) in fifth-generation (5G) networks.”

more of the abstract

Supporting differentiated service-level agreements across the radio access and core networks requires the UPF to enforce MBR limits according to configured slice priorities. During overload, the challenge is to adapt these limits while preserving that differentiation and avoiding oscillations. Building on programmable enforcement and intelligent orchestration, we propose an agentic control loop combining UPF telemetry with locally hosted Large Language Model (LLM) selection from a finite set of admissible rate candidates. Deterministic logic validates each selection and derives Packet Forwarding Control Protocol (PFCP) updates. The evaluated runs show no oscillations or fallbacks and unchanged highest-priority rate limits. These observations establish configuration preservation; delivered per-class QoS protection remains unmeasured.

from the abstract

Pith says

Machine review · deepseek-v4-flash · 13 Nov 2026 · what was read was not recorded · not checked by a person

It can be wrong. Challenge this review or reply to it.

Holds up, with conditions. Honest integration paper that delivers exactly what it claims—a working control loop—but the LLM's role is decorative, not load-bearing, and the authors say so themselves. This line is wrong

5 major objections · 7 minor

How often objections from reviews like this one are right: not yet measured

Are you an author? What you can do.

Not checked: figures, code, what the 23 references say.

The paper says, at §V, b161, b164, b165

The review did not quote this passage.

A classifier read this sentence of the paper as acknowledging the concern (probability 0.95):

“The incremental benefit of LLM selection requires a deterministic selector with identical candidates, telemetry, constraints, and timing.”

Pith says: Objection 1 of 5 · major

The paper explicitly states that the incremental benefit of LLM selection is untested and requires a deterministic selector with identical candidates, telemetry, constraints, and timing. This is a central claim of the paper (agentic orchestration with LLM), yet the evaluation does not isolate the LLM's contribution.

more of objection 1

Without this comparison, the paper's title and framing overstate the role of the LLM. The authors should either provide such a comparison or adjust the claims to reflect that the LLM is a replaceable component whose benefit is not demonstrated.

The paper says, at §V, b7, b50, b56, b118

The review did not quote this passage.

A classifier read this sentence of the paper as acknowledging the concern (probability 0.96):

“Without per-class measurements, the lower aggregate throughput cannot be attributed to a service-protection benefit.”

Pith says: Objection 2 of 5 · major

The paper repeatedly states that delivered per-class QoS protection is unmeasured. However, the problem statement (Figure 1) and the motivation rely on protecting Gold traffic during overload. Without per-class throughput, loss, or latency measurements, the paper cannot support the claim that the proposed controller preserves priority differentiation.

more of objection 2

The aggregate throughput results (Table III) show that agentic controllers deliver less throughput than Static and Greedy, but without per-class data, this cannot be attributed to service protection. The authors should either provide per-class measurements or explicitly reframe the contribution as configuration preservation only, not QoS protection.

The paper says, at §V, b122, b164

The review did not quote this passage.

A classifier read this sentence of the paper as acknowledging the concern (probability 0.64):

“The evidence concerns configuration preservation and operational integration; delivered per-class QoS, autonomous phase detection, and the incremental benefit of LLM selection remain open.”

Pith says: Objection 3 of 5 · major

The evaluation uses a known traffic schedule with pre-labeled phases (A, B, C, D). The paper acknowledges that autonomous phase detection is not assessed. This is a significant limitation because the controller relies on the phase label to identify the affected class and to apply monotone filtering.

more of objection 3

In a real deployment, the controller would need to detect overload autonomously. The authors should discuss how the system could be extended to detect phases without external labels, or at least acknowledge that the current evaluation does not test this capability.

The paper says, at §V, Table IV, b146

The review did not quote this passage.

A classifier read this sentence of the paper as acknowledging the concern (probability 0.81):

“Their comparison therefore evaluates both changes together.”

Pith says: Objection 4 of 5 · major

The paper reports that E4b (proposed) has zero oscillations and zero fallbacks, while E4 (unconstrained) has 80 oscillations and 50 fallbacks. However, the comparison between E4 and E4b conflates two changes: monotone candidate filtering and deterministic action derivation. The paper acknowledges this (b110) but does not disentangle their effects.

more of objection 4

It is unclear whether the improvement is due to the filtering alone, the action derivation alone, or both. The authors should design an ablation study to isolate the contribution of each component.

The paper says, at §V, b158

The review did not quote this passage.

A classifier read this sentence of the paper as acknowledging the concern (probability 0.91):

“Traffic continuity between windows and overload-to-enforcement delay are not reported.”

Pith says: Objection 5 of 5 · major

The paper states that traffic continuity between windows and overload-to-enforcement delay are not reported. This is a critical metric for a real-time control loop. Without knowing the delay from overload detection to MBR update, it is impossible to assess whether the controller can react quickly enough to prevent QoS degradation. The authors should measure and report this delay, or at least discuss the implications of the observed latencies (median 2.72 s, 95th percentile 3.53 s) on the control loop's effectiveness.

7 minor objections

The paper says, at §III, Step 2

Pith says: minor objection 1 of 7

The description of candidate construction uses the term 'phase label supplied by the experimental schedule.' This should be clarified: the controller uses the known schedule to identify the affected class. In a real deployment, this would not be available. The authors should note this assumption explicitly.

The paper says, at §IV, Table II

Pith says: minor objection 2 of 7

The table lists initial MBR values and settings for E2 and E3, but it does not show the MBR values for E4 and E4b. It would be helpful to include the initial configuration used by all controllers for clarity.

show 5 more

The paper says, at §V, Figure 4

Pith says: minor objection 3 of 7

The figure shows aggregate throughput and policing ratio, but the axes are not clearly labeled. The y-axis for policing ratio is labeled 'Policing Ratio (app-QER-red ÷ received)' but the formula uses 'received' while the text defines ρ = r/(r+p). This inconsistency should be resolved.

The paper says, at §V, b120

Pith says: minor objection 4 of 7

The Mann-Whitney U test p-value is reported as 1.83×10^{-4} for all six comparisons between E4 and conventional policies. The paper notes that identical rank statistics yield identical p-values despite different throughput gaps. This is correct but could be misinterpreted. The authors should clarify that the test only assesses whether the distributions differ, not the magnitude of the difference.

The paper says, at §V, Figure 10

Pith says: minor objection 5 of 7

The figure shows a strong correlation (r=0.976) between token volume and LLM request latency. The authors should discuss whether this correlation is expected and whether it has implications for the control loop's timing predictability.

The paper says, at §VI, b165

Pith says: minor objection 6 of 7

The conclusion lists future work items, but it would be helpful to prioritize them. The most critical gap is the lack of per-class QoS measurements, which should be addressed before any claims about service protection can be made.

The paper says, at General

Pith says: minor objection 7 of 7

The paper uses the term 'agentic' extensively but does not define it clearly. A brief definition or reference to the agentic AI literature would help readers unfamiliar with the term.

What would settle it

Implement a deterministic selector that, given the same telemetry deltas, candidate set, and phase label, selects the candidate that minimizes the absolute difference between delivered throughput and a target (e.g., 90% of offered load) while respecting monotonicity. Run the same 10 trials per phase. If the deterministic selector matches or exceeds E4b on any metric (throughput, oscillations, fallbacks), then the LLM provides no measurable benefit in this setting.

from the skeptic's reading

How the review went

4 readings by deepseek-v4-flash · 13 Nov 2026

  1. Reader holds up, with conditions confidence high
  2. Skeptic agrees 7 s · 11,147 tokens read, 635 written
  3. Editor wrote the verdict above 8 s · 12,033 tokens read, 740 written
  4. Referee major revision: 5 major objections, 7 minor 12 s · 11,447 tokens read, 1,478 written

Not run on this paper: the simulated authors' defence.

Pith did not check this review's objections against the paper.

The review in full

The review in brief, machine-written

This paper does what it says on the tin: it wires together UPF telemetry, an LLM-based candidate selector, deterministic validation, and PFCP actuation on a real BESS-UPF data plane, and shows that the resulting loop runs without oscillations or fallbacks while preserving configured Gold MBR limits. That integration is real, and the authors are unusually honest about what they have and haven't shown. The paper is worth a read if you work on programmable data planes or 5G/6G QoS enforcement and want to see one concrete way to close a telemetry-to-actuation loop.

What is actually new is the specific assembly: SLA-monotone candidate filtering, deterministic action derivation that decouples the model's output from the PFCP command, and the audit trail. The individual pieces are off-the-shelf (BESS-UPF, Qwen2.5-7B, PFCP), but the end-to-end integration on a two-site FABRIC testbed is not something I've seen before. The evaluation is clean: ten independent runs per controller, Mann-Whitney U tests, clear event counting.

Now the soft spots, which the paper flags itself. The big one: the LLM's incremental benefit over a deterministic rule-based selector is completely untested (b161, b165). The only comparison that involves the LLM is E4 (unconstrained agentic) vs E4b (proposed with monotone filtering and deterministic derivation), but that conflates the effect of the LLM with the effect of the filtering/derivation. The paper could be replaced by a simple rule like 'reduce Bronze by 10% each window until plateau' and we wouldn't know if the result would be the same or better. The authors acknowledge this openly, but it means the title's 'agentic orchestration' is doing more rhetorical work than the evidence supports. Second, delivered per-class QoS is unmeasured (b7, b50, b56, b118). The paper only reports aggregate throughput and policing ratio, so we cannot tell whether the control loop actually protects Gold/Silver/Bronze service, which is the whole point of the exercise. Third, the evaluation uses a known traffic schedule with pre-labeled phases (b164), so autonomous overload detection is not assessed. These are not fatal flaws—the paper is honest about them—but they limit what can be concluded.

Who is this for? Researchers building programmable UPF control loops who want a reference implementation and a clear statement of what integration looks like on real hardware. It is not for someone looking for evidence that LLMs improve QoS enforcement, because that evidence is absent.

Recommendation: I would send this to peer review. The integration is real, the implementation is available, and the paper is honest about its limitations. A good reviewer will ask for the missing comparison and per-class measurements, but the paper as a snapshot of a working system is worth publishing as a demo or short paper. I would not cite it for claims about LLM benefit, but I would cite it for the integration architecture and the SLA-monotone candidate policy.

The strongest objection

The paper's central architectural claim is that an LLM-based selector is part of a working agentic control loop. However, the evaluation explicitly does not compare against a deterministic selector that uses the same candidate set, telemetry, constraints, and timing (b161, b165). The only comparison is between E4 (unconstrained agentic) and E4b (proposed with monotone filtering and deterministic action derivation), but this conflates the effect of the LLM with the effect of the filtering/derivation. The paper acknowledges this gap (b161, b164, b165), but it means the core claim that the LLM provides any benefit—or even that the LLM is necessary—is unsupported. Without this comparison, the system could be replaced by a simple rule (e.g., 'reduce Bronze by 10% each window until plateau') and achieve the same or better results. The paper's own strongest claim (b159) is about integration, not about LLM advantage, but the title and framing imply agentic orchestration as a novel contribution. The load-bearing assumption is that the LLM selection is a meaningful component; this is untested and therefore the central claim is weaker than presented.

The reader's weakest_assumption correctly identifies that the LLM benefit is untested. The paper's own limitations (b161, b164, b165) state this explicitly. My concern is that the paper's framing and title imply a novel contribution from the LLM, but the evaluation cannot support that. The strongest claim (b159) is about integration, which is supported, but the paper's novelty hinges on the LLM component. The reader's verdict is CONDITIONAL, and I agree that this is appropriate. The concrete test I propose would directly address this gap. I do not recommend changing the verdict because the paper honestly states the limitation, and the integration claim is supported. However, if the authors intend to claim LLM benefit, they need this comparison. The paper's own sentences (b161, b165) show they are aware of this, so the verdict remains CONDITIONAL with the same condition: the LLM benefit must be tested. I agree with the reader's assessment.

The referee's report

If the integration is robust and the approach can be extended to unannounced traffic transitions and per-class QoS measurements, it could contribute to practical network slicing enforcement. However, the current evaluation does not demonstrate that the LLM component provides any benefit over a deterministic selector, and the lack of per-class QoS measurements limits the significance of the results.

Pith's reading of the paper (a machine's summary, not the authors')

This paper tries to establish that an agentic control loop using a local LLM to select among precomputed rate candidates can adjust per-session bandwidth limits in a 5G user-plane data plane during overload, while preserving the configured limits of the highest-priority slices and avoiding oscillations. The authors demonstrate a working integration of telemetry, LLM-based selection, deterministic validation, and PFCP actuation on a real BESS-UPF DPDK pipeline. The core claim is that the proposed architecture, which combines SLA-monotone candidate generation with deterministic action derivation, can reduce control events and eliminate oscillations and fallbacks compared to an unconstrained agentic variant. However, the paper explicitly acknowledges that delivered per-class QoS protection remains unmeasured, that autonomous phase detection is not assessed, and that the incremental benefit of LLM selection over a deterministic selector with identical candidates is untested. The significance, if true, is that it provides a path toward more adaptable and safer QoS enforcement in programmable mobile data planes, combining the flexibility of LLM-based reasoning with the reliability of deterministic constraints, but the evidence is limited to configuration preservation and operational integration under a known traffic schedule.

What carries the argument. The SLA-monotone candidate policy is the central mechanism. It defines rules for constructing the set of admissible MBR vectors during each control window: (i) Gold slices are pinned to their initial MBR values, (ii) during overload, candidates may only maintain or reduce the affected class MBR within the current phase (monotone tightening), and (iii) during recovery, the candidate set collapses to the initial MBR vector. This policy, combined with deterministic validation that checks the LLM-selected candidate against the rate budget and monotonicity rules, ensures that the controller cannot increase the affected class MBR during overload or violate the priority ordering. The paper shows that this filtering alone eliminates the oscillations and fallbacks observed in the unconstrained variant E4, independent of the selector's quality.

Core claim. The paper demonstrates a working integration of a telemetry-aware agentic control loop for adapting configured per-session MBR limits on a real BESS-UPF data plane. The controller combines UPF telemetry with a locally hosted LLM (Qwen2.5-7B-Instruct) that selects among a finite set of SLA-monotone MBR candidates. The key innovation is the separation of candidate selection from deterministic validation and action derivation: the LLM chooses a candidate identifier, but the controller independently validates the choice against the rate budget and monotonicity rules, and derives the PFCP update. In the evaluated runs with known traffic phases, this approach preserved Gold slice limits across all 480 windows, eliminated oscillations and fallbacks that occurred in the unconstrained agentic variant (E4), and reduced the number of MBR modifications from 124 to 32. The paper claims this demonstrates configuration preservation and operational integration, but explicitly states that delivered per-class QoS protection, autonomous phase detection, and the incremental benefit of LLM selection over a deterministic selector remain unmeasured and open.

The premise it rests on. The paper assumes that having an LLM select among precomputed MBR candidates provides a benefit over a deterministic selector (e.g., a simple rule or lookup table) that uses the same candidates, telemetry, constraints, and timing, but this assumption is explicitly untested and identified as an open issue.

If the paper is right (Pith's inferences, not the authors')

If the agentic control loop works as demonstrated, it provides a template for combining LLM-based decision making with hard safety constraints in network control loops, potentially applicable beyond 5G slicing to any scenario requiring runtime adaptation with priority preservation.

The reduction of control events from 124 to 32 and the elimination of oscillations and fallbacks suggest that SLA-monotone candidate filtering can substantially improve the stability and predictability of LLM-driven network control, even without improvements in the selector itself.

The working integration of telemetry, LLM inference, deterministic validation, and PFCP actuation on a real DPDK pipeline demonstrates that such agentic loops are feasible with current hardware and software, not just simulations.

The explicit identification of gaps (unmeasured per-class QoS, no autonomous phase detection, untested LLM benefit over deterministic selector) sets a clear agenda for follow-up work to establish whether this architecture provides actual service-level benefits.

The paper's strongest evidence is for configuration preservation and operational integration, not for service-level QoS protection. A reader should infer that the claimed benefits are about stability and reliability of the control loop itself, not about improved throughput or latency for any traffic class. The aggregate throughput measurements do not show a clear advantage over simpler policies li

The lack of comparison with a deterministic selector using the same candidates, telemetry, and timing means the paper does not establish that the LLM adds value over a rule-based selector. The results could be replicated or even improved by a simple lookup table or heuristic that selects the most restrictive admissible candidate during overload. This is the most critical open question for the arch

The experiment uses a known traffic schedule with pre-labeled phases, so the controller never needs to autonomously detect overload or transition between phases. The paper's results say nothing about the system's ability to operate under unannounced traffic changes, which is the realistic operational condition. Future work would need to demonstrate autonomous phase detection or at least robustness

The median control interval of 44.4 seconds, which includes time outside the traffic window, suggests the loop operates at a timescale of tens of seconds, not milliseconds. This makes it suitable for slow-varying overload conditions but likely inadequate for burst-scale congestion control. The paper does not report overload-to-enforcement delay, which would be critical for assessing responsiveness

Check this review

Pith stored no record of this review's passes and took no fingerprint of it. Reviews made by code from 13 Nov 2026 on carry both.

How often reviews like this one are right

Reviews like this one: written by deepseek-v4-flash, where what was read was not recorded.

How often objections from reviews like this one are right: not yet measured

Every value above, in the review's public record (JSON)

Reviews by people

This review was written by a machine. No person has reviewed this paper on Pith yet. A scientist listed on Pith can review it for a fee, and their review is published here whatever it concludes.

Request a human review

How Pith checks papers · The full audit of this paper

The paper

Abstract

The Third Generation Partnership Project (3GPP) Technical Specification 23.501 (Release 17) defines Maximum Bit Rate (MBR) enforcement at the User Plane Function (UPF) in fifth-generation (5G) networks. Supporting differentiated service-level agreements across the radio access and core networks requires the UPF to enforce MBR limits according to configured slice priorities. During overload, the challenge is to adapt these limits while preserving that differentiation and avoiding oscillations. Building on programmable enforcement and intelligent orchestration, we propose an agentic control loop combining UPF telemetry with locally hosted Large Language Model (LLM) selection from a finite set of admissible rate candidates. Deterministic logic validates each selection and derives Packet Forwarding Control Protocol (PFCP) updates. The evaluated runs show no oscillations or fallbacks and unchanged highest-priority rate limits. These observations establish configuration preservation; delivered per-class QoS protection remains unmeasured.

The paper's own sentences, arranged, kept beside the review and separate from it. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. No sentence in this record was written by a model.

abstract compiled · 2026-11-13

The authors' main claim, as the classifier picked it out 0.65

“The evaluated runs show no oscillations or fallbacks and unchanged highest-priority rate limits.”

How the main claim is stated: asserted 1.00

What the abstract itself states, as probabilities: claims first 0.05 · states limitation 0.96 · human participants 0.03 · controlled comparison 0.10 · randomized assignment 0.02 · states quantitative result 0.12 · compares with prior results 0.10 · mentions code or data availability 0.03

The abstract, sentence by sentence

This table labels the abstract only (arXiv listing abstract v1). The number is the probability the classifier gave the label.

SentenceRoleThe authors' own workStates the main conclusionStrength
The Third Generation Partnership Project (3GPP) Technical Specification 23.501 (Release 17) defines Maximum Bit Rate (MBR) enforcement at the User Plane Function (UPF) in fifth-generation (5G) networks. background 1.00 0.03 0.02 asserted 1.00
Supporting differentiated service-level agreements across the radio access and core networks requires the UPF to enforce MBR limits according to configured slice priorities. background 1.00 0.05 0.03 asserted 1.00
During overload, the challenge is to adapt these limits while preserving that differentiation and avoiding oscillations. background 0.73 0.05 0.03 asserted 0.97
Building on programmable enforcement and intelligent orchestration, we propose an agentic control loop combining UPF telemetry with locally hosted Large Language Model (LLM) selection from a finite set of admissible rate candidates. contribution 0.64 0.83 0.08 asserted 0.93
Deterministic logic validates each selection and derives Packet Forwarding Control Protocol (PFCP) updates. method 0.99 0.82 0.05 asserted 1.00
The evaluated runs show no oscillations or fallbacks and unchanged highest-priority rate limits. result 1.00 0.94 0.33 asserted 1.00
These observations establish configuration preservation; delivered per-class QoS protection remains unmeasured. limitation 0.92 0.86 0.21 asserted 0.99

What kind of paper the classifier reports this is: method or tool 0.99 · evidence from observation or experiment 0.85

What was examined, and what was not

Sources read

  • arXiv listing abstract v1

Not examined

  • full text
  • figures and tables
  • references and citing sentences
  • relations to other papers

Levels run

  • P abstract

Not run

  • S sections
  • T body sentences
  • C citations
  • R cross-paper relations

How the labels were made

Compiled by classifier-1.13.0 via TypeSafe API, question bank abstract-p1-20260923, 2026-11-13: 1 request, 5,579 input tokens.

Every quoted sentence on this record is the authors'. Every label is from Pith's closed vocabulary, with the probability shown beside it. This record as JSON

Figures (9)
Figure 1 of the paper
Figure 1. Problem illustration for QoS enforcement at the UPF. Gold, Silver, and Bronze curves are schematic, with no measured per-class QoS values. Agentic Controller UPF-DPDK appQERLookup PFCP LLM Serving
Figure 2 of the paper
Figure 2. Agentic control loop for QoS enforcement in the UPF.
Figure 3 of the paper
Figure 3. Our experimental testbed
Figure 5 of the paper
Figure 5. Representative E4 behavior across the four traffic phases. The upper panel shows offered and delivered throughput, modifications, and fallbacks. The lower panel shows LLM request latency. 1 2 3 4 5 6 Phase B window 60 70 80 90 100 S5 MBR (Mbps) 70 60 70 60 70 60 73 69 68 68 68 68 E4 Unconstrained (n=10) E4b Proposed (n=10)
Figure 6 of the paper
Figure 6. Bronze slice MBR in Phase B under E4 and E4b. Figures 6 and 7 show the limitation of E4. It alternates between reducing and increasing the Bronze allocation in Phase B, with similar reversals for Silver in Phase C. Each candidate can pass the local checks even though successive choices reverse earlier adjustments. E4b removes candidates that increase the affected class MBR during overload within the same phase. This within-phase monotonicity follows from deterministic filtering, independently of the selector. The observed trajectories reach plateaus while Gold limits remain fixed
Figure 7 of the paper
Figure 7. Silver slice MBR in Phase C under E4 and E4b. Run 01 Run 02 Run 03 Run 04 Run 05 Run 06 Run 07 Run 08 Run 09 Run 10 Agentic Run 0 1 2 3 4 5 6 7 8 Count per run Oscillations Fallbacks
Figure 8 of the paper
Figure 8. Oscillations and fallbacks in the E4 runs. consecutive MBR vectors within one phase follow the pattern 𝑥 → 𝑦 → 𝑥, with 𝑥 ̸= 𝑦. A fallback retains the current vector after validation rejects the model output. E4 fallbacks occur mainly during recovery because the selected vector conflicts with the declared action. E4b records neither event and applies fewer modifications in these runs; this observation provides no general reliability guarantee. No PFCP or datapath failures were observed. 0 5 10 15 20 25 30 Policing ratio (%) 520 540 560 580 Delivered throughput (Mbps) A B C D A 518.1…
Figure 9 of the paper
Figure 9. Aggregate throughput and policing ratio under E4 and E4b across traffic phases

Showing 8 of the paper's 9 figures. Figures are the authors', reproduced from the paper.

References (23)
  1. [1] R. Moreira, P. F. Rosa, R. L. A. Aguiar, and F. de Oliveira Silva, “NASOR: A network slicing approach for multiple Autonomous Systems,”Com- puter Communications, vol. 179, pp. 131–144, 2021. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S0140366421002917 on Pith
  2. [2] R. Moreira, R. Pasquini, J. S. Martins, T. C. Carvalho, and F. de Oliveira Silva, “AI-driven orchestration at scale: Estimating service metrics on national-wide testbeds,”Future Generation Computer Systems, vol. 174, p. 107971, 2026. [Online]. Available: https://www.sciencedir... on Pith
  3. [3] A. Patil, S. Prabhu, and P. Ashok, “5G Monetization Strategies and Business Models: An insightful Analysis for Telecommunications Service Providers,” in2024 5th International Conference on Data Intelligence and Cognitive Informatics (ICDICI), 2024, pp. 16–23 on Pith
  4. [4] I. Kochetkova, K. Leonteva, I. Ghebrial, and A. Khakimov, “Dynamic Spectrum Management for 5G NR Network Slicing: Frequency Realloca- tion Ensuring Slice Isolation and Revenue Maximization,”IEEE Access, vol. 13, pp. 208 414–208 438, 2025 on Pith
  5. [5] 3GPP, “System architecture for the 5G system (5GS),” 3rd Generation Partnership Project, Technical Specification 23.501, Oct. 2024, version 17.14.0, Release 17 on Pith
  6. [6] Y . Kyung, D. Lee, J. Lee, H. Ko, S. Oh, J. Lee, and Y . Kim, “PDU Set-Based Traffic Handling for XR Service Support in 5G User Plane,” in 2024 15th International Conference on Information and Communication Technology Convergence (ICTC), 2024, pp. 2155–2156 on Pith
  7. [7] G. Damigos, E. Pagliari, S. Sandberg, and G. Nikolakopoulos, “5G- enabled robots: Differentiated connectivity for varying mission re- quirements through dynamic QoS,”IEEE Transactions on Vehicular Technology, pp. 1–16, 2025 on Pith
  8. [8] N. M. Yungaicela-Naula, V . Sharma, and S. Scott-Hayward, “RSLAQ- A Robust SLA-driven 6G O-RAN QoS xApp Using Deep Reinforcement Learning,”IEEE Transactions on Mobile Computing, pp. 1–17, 2026 on Pith
  9. [9] R. Moreira, L. F. Rodrigues Moreira, M. Leone Maciel Peixoto, and F. D. Oliveira Silva, “AGORA: Agentic Green Orchestration Architecture for Beyond 5G Networks,”IEEE Access, vol. 14, pp. 43 519–43 532, 2026 on Pith
  10. [10] A. Balasingam, M. Kotaru, and P. Bahl, “Application-Level service assurance with 5g RAN slicing,” in21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24). Santa Clara, CA: USENIX Association, Apr. 2024, pp. 841–857. [Online]. Available: https://www.use... on Pith
  11. [11] A. Yaqoob and G.-M. Muntean, “An Adaptive QoS-Aware Priority Scheduling Solution for Dynamic Radio Resource Allocation in Mul- tiservice 5G Network Slicing Environments,”IEEE Internet of Things Journal, vol. 13, no. 6, pp. 12 244–12 260, 2026 on Pith
  12. [12] M. Ya˘gcıo˘glu, “Enhanced Deep Reinforcement Learning-Driven Adaptive Network Slicing and Resource Allocation for URLLC in 5G Networks,” Journal of Network and Systems Management, vol. 34, no. 1, p. 33, Dec on Pith
  13. [13] M. H. Rahman, A. Jain, A. Da Silva, S. Singh, M. Roy Chowdhury, H. S. Dhillon, and M. Hong, “Leveraging O-RAN SC AI/ML Framework & Non-RT RIC for AI-Driven Network Slice QoS Optimization,” in2024 IEEE Globecom Workshops (GC Wkshps), 2024, pp. 1–6 on Pith
  14. [14] N. Phuc Tran, O. Delgado, and B. Jaumard, “Proactive Service Assurance in 5G and B5G Networks: A Closed-Loop Algorithm for End-to- End Network Slices,”IEEE Transactions on Network and Service Management, vol. 23, pp. 668–680, 2026 on Pith
  15. [15] M. S. Iqbal, M. Elangovan, C. Chen, and J.-C. Chen, “P4- QUPF: A P4-Based QoS Framework for 5G-UPF,”International Journal of Network Management, vol. 35, no. 6, p. e70028, 2025, e70028 NEM-24-1822.R1. [Online]. Available: https://onlinelibrary.wiley.com/doi/abs/10.1002/nem.70028 on Pithdoi:10.1002/nem.70028
  16. [16] R. A. Bakar, A. S. T. Ibrahim, F. Paolucci, A. Sgambelluri, P. Castoldi, F. Cugini, and J. J. Vegas Olmos, “6gupf: A dpu-based programmable user plane function for enhanced flow-based qos,” inGLOBECOM 2025 - 2025 IEEE Global Communications Conference, 2025, pp. 793–798 on Pith
  17. [17] V . Romain, T. Lejkin, S. Rovedakis, and S. Secci, “A Data-Centric Approach for User Plane Control to Improve QoS for Beyond 5G Sys- tems,” in2025 14th IFIP/IEEE International Conference on Performance Evaluation and Modeling in Wired and Wireless Networks (PEMWN), 2025, pp. 1–8 on Pith
  18. [18] S. Vashisht, S. Rani, and H. Feng, “Multimodal and Agentic Intelli- gence–Driven ML Fusion for Sustainable 6G Network Slicing,”IEEE Open Journal of the Communications Society, vol. 7, pp. 1643–1653, 2026 on Pith
  19. [19] D. Brodimas, A. Birbas, D. Kapolos, and S. Denazis, “Intent-Based Infrastructure and Service Orchestration Using Agentic-AI,”IEEE Open Journal of the Communications Society, vol. 6, pp. 7150–7168, 2025 on Pith
  20. [20] S. Huang and S. Ontañón, “A closer look at invalid action masking in policy gradient algorithms,”The International FLAIRS Conference Proceedings, vol. 35, 2022 on Pith
show 3 more
  1. [21] M. Alshiekh, R. Bloem, R. Ehlers, B. Könighofer, S. Niekum, and U. Topcu, “Safe reinforcement learning via shielding,”Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32, no. 1, 2018 on Pith
  2. [22] I. Baldin, A. Nikolich, J. Griffioen, I. I. S. Monga, K.-C. Wang, T. Lehman, and P. Ruth, “FABRIC: A National-Scale Programmable Experimental Network Infrastructure,”IEEE Internet Computing, vol. 23, no. 6, pp. 38–47, 2019 on Pith
  3. [2025] [Online]. Available: https://doi.org/10.1007/s10922-025-10009-2 on Pithdoi:10.1007/s10922-025-10009-2

Challenges and discussion

Disagree with the review, or know something it missed? Leave a comment, or challenge this review formally: a challenge becomes a permanent entry in this paper's record, and its decision is published here.

No comments yet.

Sign in to comment