PRGA gates wireless intent execution with progressive evidence stages, cutting time-to-first-safe-action by 23-27% and control-plane bytes by 52-54% on 3GPP benchmarks while rejecting all stale inputs and staying within a 0.5pp unsafe-action margin.
Agentran: An agentic ai architecture for autonomous control of open 6g networks
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
verdicts
UNVERDICTED 7representative citing papers
Agentic-LTPO deploys multi-agent AI with retrieval-augmented verification to generate adaptive upper-level configurations in a bilevel optimizer for policy-driven physical layer problems, yielding 57.2% better long-term performance than traditional methods on cell-free MIMO beamforming.
A RAG-driven multi-agent LLM framework with task decomposition for Beyond 5G auto-configuration reports 94.4% success rate, a 22.7% gain over monolithic methods in OpenAirInterface emulator tests.
A1gent decouples LLM-based intent reasoning from deterministic near-real-time actuation in Open RAN using typed policies, guardrails, and a training-free tuner.
A reflection-driven framework with scenario, solver, simulation, and reflector agents uses simulation-in-the-loop to create self-correcting agentic AI for 6G RAN, reporting 17.1% throughput gains and other improvements.
AgentxGCore adds a multi-agent AI-native layer to the 3GPP xGC architecture for closed-loop optimization and self-adaptation using network planner and executor agents.
An LLM-agent framework with RAG automates assessment, justification, and remediation of RAN security compliance for evolving 6G standards.
citing papers explorer
-
Executor-Side Progressive Risk-Gated Actuation for Agentic AI in Wireless Supervisory Control
PRGA gates wireless intent execution with progressive evidence stages, cutting time-to-first-safe-action by 23-27% and control-plane bytes by 52-54% on 3GPP benchmarks while rejecting all stale inputs and staying within a 0.5pp unsafe-action margin.
-
Agentic AI for Bilevel Long-Term Optimization of Policy-Driven Physical Layer Systems
Agentic-LTPO deploys multi-agent AI with retrieval-augmented verification to generate adaptive upper-level configurations in a bilevel optimizer for policy-driven physical layer problems, yielding 57.2% better long-term performance than traditional methods on cell-free MIMO beamforming.
-
RAG-driven Multi-Agent LLM Framework with Task Decomposition for Beyond 5G Auto-Configuration
A RAG-driven multi-agent LLM framework with task decomposition for Beyond 5G auto-configuration reports 94.4% success rate, a 22.7% gain over monolithic methods in OpenAirInterface emulator tests.
-
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.
-
Reflection-Driven Self-Optimization 6G Agentic AI RAN via Simulation-in-the-Loop Workflows
A reflection-driven framework with scenario, solver, simulation, and reflector agents uses simulation-in-the-loop to create self-correcting agentic AI for 6G RAN, reporting 17.1% throughput gains and other improvements.
-
AgentxGCore: Agentic AI for Next-Generation Mobile Core Network
AgentxGCore adds a multi-agent AI-native layer to the 3GPP xGC architecture for closed-loop optimization and self-adaptation using network planner and executor agents.
-
Agentic AI for 6G: A New Paradigm for Autonomous RAN Security Compliance
An LLM-agent framework with RAG automates assessment, justification, and remediation of RAN security compliance for evolving 6G standards.