HybridRAG-Based LLM Agents for Low-Carbon Optimization in Low-Altitude Economy Networks
- 25 November 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 25 (5) , 6547-6562
Abstract
Low-Altitude Economy Networks (LAENets) are emerging as a promising paradigm to support various low-altitude services through integrated air-ground infrastructure. To satisfy low-latency and high-computation demands, the integration of Unmanned Aerial Vehicles (UAVs) with Mobile Edge Computing (MEC) systems plays a vital role, which offloads computing tasks from terminal devices to nearby UAVs, enabling flexible and resilient service provisions for ground users. To promote the development of LAENets, it is significant to achieve low-carbon multi-UAV-assisted MEC networks. However, several challenges hinder this implementation, including the complexity of multi-dimensional UAV modeling and the difficulty of multi-objective coupled optimization. To this end, this paper proposes a novel Retrieval Augmented Generation (RAG)-based Large Language Model (LLM) agent framework for model formulation. Specifically, we develop HybridRAG by combining KeywordRAG, VectorRAG, and GraphRAG, empowering LLM agents to efficiently retrieve structural information from expert databases and generate more accurate optimization problems compared with traditional RAG-based LLM agents. After customizing carbon emission optimization problems for multi-UAV-assisted MEC networks, we propose a Double Regularization Diffusion-enhanced Soft Actor-Critic (R2DSAC) algorithm to solve the formulated multi-objective optimization problem. The R2DSAC algorithm incorporates diffusion entropy regularization and action entropy regularization to improve the performance of the diffusion policy. Furthermore, we dynamically mask unimportant neurons in the actor network to reduce the carbon emissions associated with model training. Simulation results demonstrate the reliability of the proposed HybridRAG-based LLM agent framework, which achieves a 6.6% improvement in F1 scores over traditional RAG, and validate the effectiveness of the R2DSAC algorithm, which outperforms the SAC algorithm by up to 64.17%.Keywords
All Related Versions
Funding Information
- National Natural Science Foundation of China (62071343)
- National Natural Science Foundation of China (62572132)
- National Natural Science Foundation of China (U2333202)
- National Natural Science Foundation of China (U22A2054)
- Guangdong Provincial Natural Science Foundation general program (2025A1515010137)
- Basic and Applied Basic Research Foundation of Guangdong Province (2023A1515140137)
- Collaborative Innovation Center of Novel Software Technology and Industrialization
- Guizhou Provincial Science and Technology Plan (QKHRC-KJZY[2025]021)
- Guizhou Provincial Science and Technology Plan (QKHPT-KXJZ[2025]003)
- Seatrium New Energy Laboratory, Singapore Ministry of Education (RT5/23)
- Seatrium New Energy Laboratory, Singapore Ministry of Education (RG24/24)
- Nanyang Technological University (NTU) Centre for Computational Technologies in Finance
- Research Innovation and Enterprise (RIE) 2025 Industry Alignment Fund-Industry Collaboration Projects (I2301E0026)
This publication has 34 references indexed in Scilit:
- Secure Physical Layer Communications for Low-Altitude Economy Networking: A SurveyIEEE Communications Surveys & Tutorials, 2025
- Generative AI for Low-Carbon Artificial Intelligence of Things with Large Language ModelsIEEE Internet of Things Magazine, 2024
- Hybrid RAG-Empowered Multimodal LLM for Secure Data Management in Internet of Medical Things: A Diffusion-Based Contract ApproachIEEE Internet of Things Journal, 2024
- Large Language Models and Artificial Intelligence Generated Content Technologies Meet Communication NetworksIEEE Internet of Things Journal, 2024
- Efficient and Emission-Reducing Blockchain-Enabled Multi-UAV-Assisted MEC System in IoT NetworksIEEE Internet of Things Journal, 2024
- Diffusion-Model-Based Incentive Mechanism With Prospect Theory for Edge AIGC Services in 6G IoTIEEE Internet of Things Journal, 2024
- Graph-Attention-Based Reinforcement Learning for Trajectory Design and Resource Assignment in Multi-UAV-Assisted CommunicationIEEE Internet of Things Journal, 2024
- From Generative AI to Generative Internet of Things: Fundamentals, Framework, and OutlooksIEEE Internet of Things Magazine, 2024
- Collaboration in the Sky: A Distributed Framework for Task Offloading and Resource Allocation in Multi-Access Edge ComputingIEEE Internet of Things Journal, 2022
- Delivery by drone: An evaluation of unmanned aerial vehicle technology in reducing CO 2 emissions in the delivery service industryTransportation Research Part D: Transport and Environment, 2018