arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2407.18690cs.AI
收藏

面向自动以数据为中心开发的协作演化策略

Collaborative Evolving Strategy for Automatic Data-Centric Development

Microsoft Research Asia(微软亚洲研究院)

Xu Yang, Haotian Chen, Wenjun Feng, Haoxue Wang, Zeqi Ye, Xinjie Shen, Xiao Yang, Shizhao Sun, Weiqing Liu, Jiang Bian

AI总结:

本文首次提出自动以数据为中心开发(AD^2)任务,并构建基于LLM的Co-STEER智能体,通过积累领域经验实现调度与实现能力的协作演化,显著提升了AD^2研究的性能。

摘要:

人工智能(AI)显著影响许多领域,这在很大程度上得益于用于机器学习模型的海量高质量数据。目前的重点是以数据为中心的AI策略,优先考虑数据开发而非模型设计的进展。使这一过程自动化至关重要。在本文中,我们作为首个工作引入了自动以数据为中心开发(AD^2)任务,并概述了其核心挑战,这些挑战需要类似领域专家的任务调度和实现能力,这在很大程度上是先前工作未曾探索的。通过利用大型语言模型(LLMs)强大的复杂问题解决能力,我们提出了一个基于LLM的自主智能体,配备了一种名为检索增强的协作知识学习增强演化(Co-STEER)的策略,以同时解决所有挑战。具体而言,我们提出的Co-STEER智能体通过我们提出的演化策略丰富了其领域知识,并通过积累和检索特定领域的实践经验来发展其调度和实现技能。随着调度的改进,实现能力得到加速。同时,随着实现反馈变得更加全面,调度准确性也随之提高。这两种能力通过实际反馈共同演化,实现了协作演化过程。广泛的实验结果表明,我们的Co-STEER智能体在AD^2研究中开辟了新天地,具有强大的可演化调度和实现能力,并展示了其组件的显著有效性。我们的Co-STEER为AD^2的进步铺平了道路。

英文摘要:

Artificial Intelligence (AI) significantly influences many fields, largely thanks to the vast amounts of high-quality data for machine learning models. The emphasis is now on a data-centric AI strategy, prioritizing data development over model design progress. Automating this process is crucial. In this paper, we serve as the first work to introduce the automatic data-centric development (AD^2) task and outline its core challenges, which require domain-experts-like task scheduling and implementation capability, largely unexplored by previous work. By leveraging the strong complex problem-solving capabilities of large language models (LLMs), we propose an LLM-based autonomous agent, equipped with a strategy named Collaborative Knowledge-STudying-Enhanced Evolution by Retrieval (Co-STEER), to simultaneously address all the challenges. Specifically, our proposed Co-STEER agent enriches its domain knowledge through our proposed evolving strategy and develops both its scheduling and implementation skills by accumulating and retrieving domain-specific practical experience. With an improved schedule, the capability for implementation accelerates. Simultaneously, as implementation feedback becomes more thorough, the scheduling accuracy increases. These two capabilities evolve together through practical feedback, enabling a collaborative evolution process. Extensive experimental results demonstrate that our Co-STEER agent breaks new ground in AD^2 research, possesses strong evolvable schedule and implementation ability, and demonstrates the significant effectiveness of its components. Our Co-STEER paves the way for AD^2 advancements.

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。

↑