One Request, Multiple Experts: LLM Orchestrates Domain Specific Models via Adaptive Task Routing

TL;DR

This paper introduces ADN-Agent, an architecture that uses a large language model to coordinate multiple domain-specific models in active distribution networks, improving efficiency and adaptability in complex energy system management.

Contribution

The paper presents a novel LLM-based architecture for orchestrating heterogeneous domain-specific models in energy networks, with a new communication mechanism and automated fine-tuning pipeline.

Findings

ADN-Agent outperforms existing LLM application paradigms.

The communication mechanism enables flexible interaction with diverse DSMs.

Automated fine-tuning enhances language-intensive subtask performance.

Abstract

With the integration of massive distributed energy resources and the widespread participation of novel market entities, the operation of active distribution networks (ADNs) is progressively evolving into a complex multi-scenario, multi-objective problem. Although expert engineers have developed numerous domain specific models (DSMs) to address distinct technical problems, mastering, integrating, and orchestrating these heterogeneous DSMs still entail considerable overhead for ADN operators. Therefore, an intelligent approach is urgently required to unify these DSMs and enable efficient coordination. To address this challenge, this paper proposes the ADN-Agent architecture, which leverages a general large language model (LLM) to coordinate multiple DSMs, enabling adaptive intent recognition, task decomposition, and DSM invocation. Within the ADN-Agent, we design a novel communication mechanism that provides a unified and flexible interface for diverse heterogeneous DSMs. Finally, for some language-intensive subtasks, we propose an automated training pipeline for fine-tuning small language models, thereby effectively enhancing the overall problem-solving capability of the system. Comprehensive comparisons and ablation experiments validate the efficacy of the proposed method and demonstrate that the ADN-Agent architecture outperforms existing LLM application paradigms.