HybridRAG-based LLM Agents for Low-Carbon Optimization in Low-Altitude Economy Networks

2025-06-19

AI Summary

To address the dual challenges of carbon reduction and multi-objective coupled optimization in low-altitude economy-oriented UAV-assisted mobile edge computing (UAV-MEC) networks, this paper proposes a large language model (LLM)-based intelligent agent framework leveraging hybrid retrieval-augmented generation (HybridRAG) to autonomously construct optimization models. Furthermore, we design a novel double-regularized diffusion-enhanced soft actor-critic algorithm (R²DSAC), integrating diffusion entropy and action entropy regularization, and incorporate dynamic neuron masking to enable sparse training—thereby reducing computational carbon footprint. Our key innovations include the first-ever tri-modal HybridRAG mechanism (combining keyword-, vector-, and graph-based retrieval) and the R²DSAC algorithm. Experimental results demonstrate significant improvements in both modeling accuracy and solution efficiency: under stringent latency and quality-of-service constraints, the proposed approach reduces system carbon emissions by 23.7%.

Technology Category

• Search and Optimization: Learning to Search
• Machine Learning: Efficient ML / Green AI
• Multiagent Systems: Mechanism Design

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Sustainability and carbon-aware systems for Web, mobile, and WoT
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

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 (R extsuperscript{2}DSAC) algorithm to solve the formulated multi-objective optimization problem. The R extsuperscript{2}DSAC 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 effectiveness and reliability of the proposed HybridRAG-based LLM agent framework and the R extsuperscript{2}DSAC algorithm.

Problem

• Optimize low-carbon multi-UAV MEC networks for LAENets
• Address multi-dimensional UAV modeling complexity challenges
• Solve multi-objective coupled optimization in UAV systems

Innovation

• HybridRAG combines KeywordRAG, VectorRAG, and GraphRAG
• R2DSAC algorithm with dual entropy regularization
• Dynamic neuron masking reduces training carbon emissions