# AURA: Adaptive Unified Reasoning and Automation with LLM-Guided MARL for NextG Cellular Networks

arXiv: https://arxiv.org/abs/2511.17506 · HTML: https://mlsanity.com/paper/2511.17506/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 30 of its 53 references that are in the map.
- First posted on arXiv 2 Oct 2025.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)

## Builds on (most cited first, 30 of 30)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [The Rise and Potential of Large Language Model Based Agents: A Survey](https://mlsanity.com/paper/2309.07864/) (2023)
- [Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents](https://mlsanity.com/paper/2201.07207/) (2022)
- [RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback](https://mlsanity.com/paper/2309.00267/) (2023)
- [Deep Recurrent Q-Learning for Partially Observable MDPs](https://mlsanity.com/paper/1507.06527/) (2015)
- [A Comprehensive Survey of Neural Architecture Search: Challenges and Solutions](https://mlsanity.com/paper/2006.02903/) (2020)
- [Multi-Agent Deep Reinforcement Learning for Large-scale Traffic Signal Control](https://mlsanity.com/paper/1903.04527/) (2019)
- [A Survey of Reinforcement Learning Informed by Natural Language](https://mlsanity.com/paper/1906.03926/) (2019)
- [A Review of Cooperative Multi-Agent Deep Reinforcement Learning](https://mlsanity.com/paper/1908.03963/) (2019)
- [On the Effect of Pretraining Corpora on In-context Learning by a Large-scale Language Model](https://mlsanity.com/paper/2204.13509/) (2022)
- [LLM-based Multi-Agent Reinforcement Learning: Current and Future Directions](https://mlsanity.com/paper/2405.11106/) (2024)
- [Single and Multi-Agent Deep Reinforcement Learning for AI-Enabled Wireless Networks: A Tutorial](https://mlsanity.com/paper/2011.03615/) (2020)
- [Wireless Networks Design in the Era of Deep Learning: Model-Based, AI-Based, or Both?](https://mlsanity.com/paper/1902.02647/) (2019)
- [Artificial Intelligence-Enabled Intelligent 6G Networks](https://mlsanity.com/paper/1912.05744/) (2019)
- [Wireless Multi-Agent Generative AI: From Connected Intelligence to Collective Intelligence](https://mlsanity.com/paper/2307.02757/) (2023)
- [Overview of AI and Communication for 6G Network: Fundamentals, Challenges, and Future Research Opportunities](https://mlsanity.com/paper/2412.14538/) (2024)
- [LLM-Powered Decentralized Generative Agents with Adaptive Hierarchical Knowledge Graph for Cooperative Planning](https://mlsanity.com/paper/2502.05453/) (2025)
- [Generative AI for the Optimization of Next-Generation Wireless Networks: Basics, State-of-the-Art, and Open Challenges](https://mlsanity.com/paper/2405.17454/) (2024)
- [GenAINet: Enabling Wireless Collective Intelligence via Knowledge Transfer and Reasoning](https://mlsanity.com/paper/2402.16631/) (2024)
- [Generative AI for Game Theory-based Mobile Networking](https://mlsanity.com/paper/2404.09699/) (2024)
- [YOLO-MARL: You Only LLM Once for Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2410.03997/) (2024)
- [DM2: Decentralized Multi-Agent Reinforcement Learning for Distribution Matching](https://mlsanity.com/paper/2206.00233/) (2022)
- [MANSY: Generalizing Neural Adaptive Immersive Video Streaming With Ensemble and Representation Learning](https://mlsanity.com/paper/2311.06812/) (2023)
- [Towards Deep Learning-aided Wireless Channel Estimation and Channel State Information Feedback for 6G](https://mlsanity.com/paper/2209.01724/) (2022)
- [Meta-Analysis and Systematic Review for Anomaly Network Intrusion Detection Systems: Detection Methods, Dataset, Validation Methodology, and Challenges](https://mlsanity.com/paper/2308.02805/) (2023)
- [Curriculum Learning for Cooperation in Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2312.11768/) (2023)
- [Smart Routing with Precise Link Estimation: DSEE-Based Anypath Routing for Reliable Wireless Networking](https://mlsanity.com/paper/2405.10377/) (2024)

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

- [DR. WELL: Dynamic Reasoning and Learning with Symbolic World Model for Embodied LLM-Based Multi-Agent Collaboration](https://mlsanity.com/paper/2511.04646/) (2025)
- [Smart Adaptive Computing Across the Continuum: LLMs in IoT-Edge-Cloud Resource Management](https://mlsanity.com/paper/2609.09348/) (2026)

## Abstract (arXiv)

Next-generation (NextG) cellular networks are expected to manage dynamic traffic while sustaining high performance. Large language models (LLMs) provide strategic reasoning for 6G planning, but their computational cost and latency limit real-time use. Multi-agent reinforcement learning (MARL) supports localized adaptation, yet coordination at scale remains challenging. We present AURA, a framework that integrates cloud-based LLMs for high-level planning with base stations modeled as MARL agents for local decision-making. The LLM generates objectives and subgoals from its understanding of the environment and reasoning capabilities, while agents at base stations execute these objectives autonomously, guided by a trust mechanism that balances local learning with external input. To reduce latency, AURA employs batched communication so that agents update the LLM's view of the environment and receive improved feedback. In a simulated 6G scenario, AURA improves resilience, reducing dropped handoff requests by more than half under normal and high traffic and lowering system failures. Agents use LLM input in fewer than 60% of cases, showing that guidance augments rather than replaces local adaptability, thereby mitigating latency and hallucination risks. These results highlight the promise of combining LLM reasoning with MARL adaptability for scalable, real-time NextG network management.