ns-3 framework simulates intent-based Open RAN orchestration via dApps and a new ISS metric, reporting better intent satisfaction and lower resource use with moderate performance tradeoffs.
ALL- STaR: Automated LLM-driven scheduler generation and testing for intent-based RAN
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
fields
cs.NI 4years
2026 4verdicts
UNVERDICTED 4representative citing papers
AUGUSTE embeds online ML models in the 5G UL scheduler to predict packet arrivals and issue proactive grants, achieving ~10 ms median RTT at 7-10% overhead on a real OpenAirInterface testbed across three traffic patterns.
The paper presents GENESIS, an agentic AI framework for autonomous 6G RAN synthesis, research, and testing that converts intents into over-the-air validated solutions via composable primitives and a knowledge layer.
A1gent decouples LLM-based intent reasoning from deterministic near-real-time actuation in Open RAN using typed policies, guardrails, and a training-free tuner.
citing papers explorer
-
Intent-Based Orchestration in Open RAN: An ns-3 Simulation Framework
ns-3 framework simulates intent-based Open RAN orchestration via dApps and a new ISS metric, reporting better intent satisfaction and lower resource use with moderate performance tradeoffs.
-
AUGUSTE: Online-Learning dApp for Predictive URLLC Scheduling
AUGUSTE embeds online ML models in the 5G UL scheduler to predict packet arrivals and issue proactive grants, achieving ~10 ms median RTT at 7-10% overhead on a real OpenAirInterface testbed across three traffic patterns.
-
GENESIS: Harnessing AI Agents for Autonomous 6G RAN Synthesis, Research, and Testing
The paper presents GENESIS, an agentic AI framework for autonomous 6G RAN synthesis, research, and testing that converts intents into over-the-air validated solutions via composable primitives and a knowledge layer.
-
Agentic Open RAN: A Deterministic and Auditable Framework for Intent-Driven Radio Control
A1gent decouples LLM-based intent reasoning from deterministic near-real-time actuation in Open RAN using typed policies, guardrails, and a training-free tuner.