mlsanityData to 14 Oct 2026

SoK: Semantic Decision Engines in Network Control Loops

arXiv 2610.06425 ↗First posted 5 Oct 2026cs.NI cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

A semantic decision engine such as Jev can return a valid answer and still miss a network deadline, select an infeasible action or leave the service unverified. We systematize 139 paper families by decision interface, execution path and check ownership. Fifty families claim that their engine fits a control loop or time budget, but only four support the claim with matched measurement. Across all 139, four report deadline attainment. The gap concentrates where the decision has no deterministic computation step. Those 72 families make 22 of the claims, none supported, and name a coverage owner in only two. Bounded tests under one event model show that each gap can reverse an admission verdict. A decision that meets a 10 s budget for every isolated request meets it for none once decisions queue ahead of replayed execution times. The same engine passes one coverage check and fails another. We derive a minimum reporting record, design rules and a research agenda for admitting decision engines to control loops.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 108 of its 168 references that are in the map. First posted on arXiv 5 Oct 2026.

Builds on

108 of 168 references.

References · 108

  1. 2024Guiding LLMs The Right Way: Fast, Non-Invasive Constrained Generationcited by 101
  2. 2025JSONSchemaBench: A Rigorous Benchmark of Structured Outputs for Language Modelscited by 71
  3. 2025ITBench: Evaluating AI Agents across Diverse Real-World IT Automation Taskscited by 51
  4. 2023Wireless Multi-Agent Generative AI: From Connected Intelligence to Collective Intelligencecited by 26
  5. 2019MOSS: End-to-End Dialog System Framework with Modular Supervisioncited by 20
  6. 2024LLM-Based Intent Processing and Network Optimization Using Attention-Based Hierarchical Reinforcement Learningcited by 14
  7. 2024Towards Explainable Network Intrusion Detection using Large Language Modelscited by 14
  8. 2023Making Network Configuration Human Friendlycited by 13
  9. 2024Intent Assurance using LLMs guided by Intent Driftcited by 13
  10. 2024Nissist: An Incident Mitigation Copilot based on Troubleshooting Guidescited by 12
  11. 2022OrchestRAN: Network Automation through Orchestrated Intelligence in the Open RANcited by 10
  12. 2024Large Language Models for Zero Touch Network Configuration Managementcited by 10
38 more
  1. 2025NetArena: Dynamic Benchmarks for AI Agents in Network Automationcited by 9
  2. 2025A Network Arena for Benchmarking AI Agents on Network Troubleshootingcited by 9
  3. 2026Replacing Large Language Models with Jev Decision Models for Low-Latency Edge Service Orchestrationcited by 9
  4. 2024Semantic Routing for Enhanced Performance of LLM-Assisted Intent-Based 5G Core Network Management and Orchestrationcited by 8
  5. 2025Intent-Based Network for RAN Management with Large Language Modelscited by 8
  6. 2024LLMcap: Large Language Model for Unsupervised PCAP Failure Detectioncited by 7
  7. 2025End-to-End Edge AI Service Provisioning Framework in 6G ORANcited by 7
  8. 2026Agentic AI Empowered Intent-Based Networking for 6Gcited by 7
  9. 2026WirelessBench: A Tolerance-Aware LLM Agent Benchmark for Wireless Network Intelligencecited by 6
  10. 2026Fast Intent-Driven Service Orchestration with Jev for 6G Edge Networkscited by 6
  11. 2024PreConfig: A Pretrained Model for Automating Network Configurationcited by 5
  12. 2025Towards End-to-End Network Intent Management with Large Language Modelscited by 5
  13. 2025ALLSTaR: Automated LLM-Driven Scheduler Generation and Testing for Intent-Based RANcited by 5
  14. 2026NetAgentBench: A State-Centric Benchmark for Evaluating Agentic Network Configurationcited by 5
  15. 2020Refining Network Intents for Self-Driving Networkscited by 4
  16. 2024MSADM: Large Language Model (LLM) Assisted End-to-End Network Health Management Based on Multi-Scale Semanticizationcited by 4
  17. 2026SADE: Symptom-Aware Diagnostic Escalation for LLM-Based Network Troubleshootingcited by 4
  18. 2024CAIP: Detecting Router Misconfigurations with Context-Aware Iterative Prompting of LLMscited by 3
  19. 2024NetOrchLLM: Mastering Wireless Network Orchestration with Large Language Modelscited by 3
  20. 2025An Autonomous Network Orchestration Framework Integrating Large Language Models with Continual Reinforcement Learningcited by 3
  21. 2025Toward an Intent-Based and Ontology-Driven Autonomic Security Response in Security Orchestration Automation and Responsecited by 3
  22. 2025A Secured Intent-Based Networking (sIBN) with Data-Driven Time-Aware Intrusion Detectioncited by 3
  23. 2026LEAD-Drift: Real-time and Explainable Intent Drift Detection by Learning a Data-Driven Risk Scorecited by 3
  24. 2026MILD: Multi-Intent Learning and Disambiguation for Proactive Failure Prediction in Intent-based Networkingcited by 3
  25. 2026Contract-based Agentic Intent Framework for Network Slicing in O-RANcited by 3
  26. 2026Benchmarking LLM-Driven Network Configuration Repaircited by 3
  27. 2018Automatic Intent-Based Secure Service Creation Through a Multilayer SDN Network Orchestrationcited by 2
  28. 2021Intent-based Network Management and Orchestration for Smart Distribution Gridscited by 2
  29. 2024Direct-Conflict Resolution in Intent-Driven Autonomous Networkscited by 2
  30. 2024Intent Profiling and Translation Through Emergent Communicationcited by 2
  31. 2025RAG-Enabled Intent Reasoning for Application-Network Interactioncited by 2
  32. 2025Towards a Playground to Democratize Experimentation and Benchmarking of AI Agents for Network Troubleshootingcited by 2
  33. 2025Leveraging Multi-Agent System (MAS) and Fine-Tuned Small Language Models (SLMs) for Automated Telecom Network Troubleshootingcited by 2
  34. 2025Network Self-Configuration based on Fine-Tuned Small Language Modelscited by 2
  35. 2026HYVE: Hybrid Views for LLM Context Engineering over Machine Datacited by 2
  36. 2026RAG-driven Multi-Agent LLM Framework with Task Decomposition for Beyond 5G Auto-Configurationcited by 2
  37. 2026Bridging High-Level Intent and Network Execution: Detecting Violations and Intent Drift Through Low-Level Traffic Analysiscited by 2
  38. 2026Evaluating Agentic Configuration Repair for Computer Networkscited by 2

50 most cited of 108 All 108 (JSON)

Built on by

Not cited yet.