arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2511.12484eess.SYcs.AIcs.SY
收藏

一个请求,多个专家:大语言模型通过自适应任务路由调度领域特定模型

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

Tsinghua University(清华大学);Hong Kong Polytechnic University(香港理工大学);Hefei University of Technology(合肥工业大学)

Xu Yang, Chenhui Lin, Haotian Liu, Qi Wang, Yue Yang, Wenchuan Wu

AI总结:

针对主动配电网运行的复杂调度难题,本文提出ADN-Agent架构,利用大语言模型协调领域特定模型,通过自适应任务路由等机制提升问题解决能力,性能优于现有大语言模型应用范式。

摘要:

随着大规模分布式能源资源的接入以及新型市场主体的广泛参与,主动配电网(ADNs)的运行正逐步演变为一个复杂、多场景、多目标的问题。尽管专家工程师已开发出众多领域特定模型(DSMs)以应对不同技术问题,但掌握、整合与调度这些异构DSMs仍会给ADN运营商带来相当大的开销。因此,亟需一种智能方法来统一这些DSMs并实现高效协调。为应对这一挑战,本文提出ADN-Agent架构,该架构利用通用大语言模型(LLM)协调多个DSMs,实现自适应意图识别、任务分解与DSM调用。在ADN-Agent内部,我们设计了一种新型通信机制,为各类异构DSMs提供统一且灵活的接口。最后,针对特定的语言密集型子任务,我们提出了一种用于微调小语言模型的自动化训练流程,从而有效提升系统的整体问题解决能力。综合对比与消融实验验证了所提方法的有效性,表明ADN-Agent架构优于现有的LLM应用范式。

英文摘要:

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, and 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 specific 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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑