# Reflection-Driven Self-Optimization 6G Agentic AI RAN via Simulation-in-the-Loop Workflows

arXiv: https://arxiv.org/abs/2512.20640 · HTML: https://mlsanity.com/paper/2512.20640/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Agentic AI for wireless networks, one of 16 directions in LLM agents and tool use.
- Builds on 14 of its 17 references that are in the map.
- First posted on arXiv 8 Dec 2025.

## Placed in

- LLM agents and tool use / [Agentic AI for wireless networks](https://mlsanity.com/agents/agentic-ai-for-wireless-networks/)

## Builds on (most cited first, 14 of 14)

- [Overview of AI and Communication for 6G Network: Fundamentals, Challenges, and Future Research Opportunities](https://mlsanity.com/paper/2412.14538/) (2024)
- [Toward Edge General Intelligence with Agentic AI and Agentification: Concepts, Technologies, and Future Directions](https://mlsanity.com/paper/2508.18725/) (2025)
- [WirelessAgent: Large Language Model Agents for Intelligent Wireless Networks](https://mlsanity.com/paper/2505.01074/) (2025)
- [Towards Agentic AI Networking in 6G: A Generative Foundation Model-as-Agent Approach](https://mlsanity.com/paper/2503.15764/) (2025)
- [AgentRAN: An Agentic AI Architecture for Autonomous Control of Open 6G Networks](https://mlsanity.com/paper/2508.17778/) (2025)
- [LLM-Based Intent Processing and Network Optimization Using Attention-Based Hierarchical Reinforcement Learning](https://mlsanity.com/paper/2406.06059/) (2024)
- [Designing Network Algorithms via Large Language Models](https://mlsanity.com/paper/2404.01617/) (2024)
- [Adaptive Resource Allocation Optimization Using Large Language Models in Dynamic Wireless Environments](https://mlsanity.com/paper/2502.02287/) (2025)
- [LLM-OptiRA: LLM-Driven Optimization of Resource Allocation for Non-Convex Problems in Wireless Communications](https://mlsanity.com/paper/2505.02091/) (2025)
- [From Agentification to Self-Evolving Agentic AI for Wireless Networks: Concepts, Approaches, and Future Research Directions](https://mlsanity.com/paper/2510.05596/) (2025)
- [Edge Agentic AI Framework for Autonomous Network Optimisation in O-RAN](https://mlsanity.com/paper/2507.21696/) (2025)
- [Prompting Wireless Networks: Reinforced In-Context Learning for Power Control](https://mlsanity.com/paper/2506.06526/) (2025)
- [Agentic AI for Mobile Network RAN Management and Optimization](https://mlsanity.com/paper/2511.02532/) (2025)
- [Large Language Model-Driven Cross-Domain Orchestration Using Multi-Agent Workflow](https://mlsanity.com/paper/2410.10831/) (2024)

## Built on by (most cited first, 2 of 2)

- [Should I Have Expressed a Different Intent? Counterfactual Generation for LLM-Based Autonomous Control](https://mlsanity.com/paper/2601.20090/) (2026)
- [LLM-Powered Agentic AI for 5G/6G Networks: A Tutorial and Survey on Architectures, Protocols, and Standardization](https://mlsanity.com/paper/2607.16066/) (2026)

## Abstract (arXiv)

The escalating complexity of sixth-generation (6G) networks demands unprecedented levels of autonomy beyond the capabilities of traditional optimization-based and current AI-based resource management approaches. While agentic AI has emerged as a promising paradigm for autonomous RAN, current frameworks provide sophisticated reasoning capabilities but lack mechanisms for empirical validation and self-improvement. This article identifies simulation-in-the-loop validation as a critical enabler for truly autonomous networks, where AI agents can empirically verify decisions and learn from outcomes. We present the first reflection-driven self-optimization framework that integrates agentic AI with high-fidelity network simulation in a closed-loop architecture. Our system orchestrates four specialized agents, including scenario, solver, simulation, and reflector agents, working in concert to transform agentic AI into a self-correcting system capable of escaping local optima, recognizing implicit user intent, and adapting to dynamic network conditions. Extensive experiments validate significant performance improvements over non-agentic approaches: 17.1% higher throughput in interference optimization, 67% improved user QoS satisfaction through intent recognition, and 25% reduced resource utilization during low-traffic periods while maintaining service quality.