# SoK: Semantic Decision Engines in Network Control Loops

arXiv: https://arxiv.org/abs/2610.06425 · HTML: https://mlsanity.com/paper/2610.06425/

## 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 (most cited first, 30 of 108)

- [Guiding LLMs The Right Way: Fast, Non-Invasive Constrained Generation](https://mlsanity.com/paper/2403.06988/) (2024)
- [JSONSchemaBench: A Rigorous Benchmark of Structured Outputs for Language Models](https://mlsanity.com/paper/2501.10868/) (2025)
- [ITBench: Evaluating AI Agents across Diverse Real-World IT Automation Tasks](https://mlsanity.com/paper/2502.05352/) (2025)
- [Wireless Multi-Agent Generative AI: From Connected Intelligence to Collective Intelligence](https://mlsanity.com/paper/2307.02757/) (2023)
- [MOSS: End-to-End Dialog System Framework with Modular Supervision](https://mlsanity.com/paper/1909.05528/) (2019)
- [LLM-Based Intent Processing and Network Optimization Using Attention-Based Hierarchical Reinforcement Learning](https://mlsanity.com/paper/2406.06059/) (2024)
- [Towards Explainable Network Intrusion Detection using Large Language Models](https://mlsanity.com/paper/2408.04342/) (2024)
- [Making Network Configuration Human Friendly](https://mlsanity.com/paper/2309.06342/) (2023)
- [Intent Assurance using LLMs guided by Intent Drift](https://mlsanity.com/paper/2402.00715/) (2024)
- [Nissist: An Incident Mitigation Copilot based on Troubleshooting Guides](https://mlsanity.com/paper/2402.17531/) (2024)
- [OrchestRAN: Network Automation through Orchestrated Intelligence in the Open RAN](https://mlsanity.com/paper/2201.05632/) (2022)
- [Large Language Models for Zero Touch Network Configuration Management](https://mlsanity.com/paper/2408.13298/) (2024)
- [NetArena: Dynamic Benchmarks for AI Agents in Network Automation](https://mlsanity.com/paper/2506.03231/) (2025)
- [A Network Arena for Benchmarking AI Agents on Network Troubleshooting](https://mlsanity.com/paper/2512.16381/) (2025)
- [Replacing Large Language Models with Jev Decision Models for Low-Latency Edge Service Orchestration](https://mlsanity.com/paper/2609.22753/) (2026)
- [Semantic Routing for Enhanced Performance of LLM-Assisted Intent-Based 5G Core Network Management and Orchestration](https://mlsanity.com/paper/2404.15869/) (2024)
- [Intent-Based Network for RAN Management with Large Language Models](https://mlsanity.com/paper/2507.14230/) (2025)
- [LLMcap: Large Language Model for Unsupervised PCAP Failure Detection](https://mlsanity.com/paper/2407.06085/) (2024)
- [End-to-End Edge AI Service Provisioning Framework in 6G ORAN](https://mlsanity.com/paper/2503.11933/) (2025)
- [Agentic AI Empowered Intent-Based Networking for 6G](https://mlsanity.com/paper/2601.06640/) (2026)
- [WirelessBench: A Tolerance-Aware LLM Agent Benchmark for Wireless Network Intelligence](https://mlsanity.com/paper/2603.21251/) (2026)
- [Fast Intent-Driven Service Orchestration with Jev for 6G Edge Networks](https://mlsanity.com/paper/2609.23136/) (2026)
- [PreConfig: A Pretrained Model for Automating Network Configuration](https://mlsanity.com/paper/2403.09369/) (2024)
- [Towards End-to-End Network Intent Management with Large Language Models](https://mlsanity.com/paper/2504.13589/) (2025)
- [ALLSTaR: Automated LLM-Driven Scheduler Generation and Testing for Intent-Based RAN](https://mlsanity.com/paper/2505.18389/) (2025)
- [NetAgentBench: A State-Centric Benchmark for Evaluating Agentic Network Configuration](https://mlsanity.com/paper/2604.09678/) (2026)
- [Refining Network Intents for Self-Driving Networks](https://mlsanity.com/paper/2008.05509/) (2020)
- [MSADM: Large Language Model (LLM) Assisted End-to-End Network Health Management Based on Multi-Scale Semanticization](https://mlsanity.com/paper/2406.08305/) (2024)
- [SADE: Symptom-Aware Diagnostic Escalation for LLM-Based Network Troubleshooting](https://mlsanity.com/paper/2605.04530/) (2026)
- [CAIP: Detecting Router Misconfigurations with Context-Aware Iterative Prompting of LLMs](https://mlsanity.com/paper/2411.14283/) (2024)

## 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.