arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2512.01099cs.AI
收藏

面向LLM系统的成本感知模型编排

Cost-Aware Model Orchestration for LLM-based Systems

Lancaster University(兰卡斯特大学)

Daria Smirnova, Hamid Nasiri, Marta Adamska, Zhengxin Yu, Peter Garraghan

AI总结:

本文提出一种考虑性能与成本权衡的成本感知模型选择方法,通过整合定量模型性能特征提升任务准确性、能效和编排效率。

摘要:

随着现代人工智能系统日益先进,它们能够利用多种工具和模型执行复杂任务。这些模型的编排任务越来越多地由大型语言模型(LLM)完成,这些模型依赖对模型的定性描述进行决策。然而,现有基于LLM的编排器提供的描述往往不反映真实的模型能力与性能特征,导致模型选择不优、任务准确性降低和成本增加。本文通过实证分析LLM编排限制,提出一种考虑性能-成本权衡的成本感知模型选择方法,通过在决策中整合定量模型性能特征。初始实验结果表明,所提方法在各种评估任务中将准确性提高了0.90%-11.92%,实现了高达54%的能效提升,并将编排器模型选择延迟从4.51秒降低到7.2毫秒。

英文摘要:

As modern artificial intelligence (AI) systems become more advanced and capable, they can leverage a wide range of tools and models to perform complex tasks. The task of orchestrating these models is increasingly performed by Large Language Models (LLMs) that rely on qualitative descriptions of models for decision-making. However, the descriptions provided to existing LLM-based orchestrators frequently do not reflect true model capabilities and performance characteristics, leading to suboptimal model selection, reduced task accuracy, and increased cost. In this paper, we conduct an empirical analysis of LLM-based orchestration limitations and propose a cost-aware model selection method that accounts for performance-cost trade-offs by incorporating quantitative model performance characteristics within decision-making. Initial experimental results demonstrate that our proposed method increases accuracy by 0.90%-11.92% across various evaluated tasks, achieves up to a 54% energy efficiency improvement, and reduces orchestrator model selection latency from 4.51 s to 7.2 ms.

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。

↑