Agent-in-the-loop to distill expert knowledge into artificial intelligence models: a survey

doi:10.1007/s10462-025-11255-1

	Agent-in-the-loop to distill expert knowledge into artificial intelligence models: a survey
	Gao, Jiayuan 1,2; Zhang, Yingwei 1,2; Chen, Yiqiang 1,2; Dong, Yihan 3; Chen, Yuanzhe 1,2; Song, Shuchao 1,2; Tang, Boshi 4; Gu, Yang 1,2
	2025-06-04
发表期刊	ARTIFICIAL INTELLIGENCE REVIEW
ISSN	0269-2821
卷号	58 期号:9 页码:55
摘要	Large-scale neural networks have revolutionized many general knowledge areas (e.g., computer vision and language processing), but are still rarely applied in many expert knowledge areas (e.g., healthcare), due to data sparsity and high annotation expenses. Human-in-the-loop machine learning (HIL-ML) incorporates expert domain knowledge into the modeling process, effectively addressing these challenges. Recently, some researchers have started using large models to substitute for certain tasks typically performed by humans. Although large models have limitations in expert knowledge areas, after being trained on trillions of examples, they have demonstrated advanced capabilities in reasoning, semantic understanding, grounding, and planning. These capabilities can serve as proxies of human, which introduces new opportunities and challenges in HIL-ML area. Based on the above, we summarize a more comprehensive framework, Agent-in-the-Loop Machine Learning (AIL-ML), where agent represents both humans and large models. AIL-ML can efficiently collaborate human and large model to construct vertical AI models with lower costs. This paper presents the first review of recent advancements in this area. First, we provide a formal definition of AIL-ML and discuss its related fields. Then, we categorize the AIL-ML methods based on data processing and model development, providing formal definitions for each, and present representative works in detail for each category. Third, we highlight relative applications of AIL-ML. Finally, we summarize the current literature and highlight future research directions.
关键词	Human-in-the-Loop Machine learning Deep learning Large language models
DOI	10.1007/s10462-025-11255-1
收录类别	SCI
语种	英语
资助项目	Natural Science Foundation of China ; Improvement Project of Chinese Academy of Sciences ; Science and Technology Innovation Program of Hunan Province[2022RC4006] ; Science and Technology Innovation Program of Hunan Province[2024 JJ9031] ; Innovation Funding of ICT, CAS ; [62302487]
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence
WOS记录号	WOS:001502355300008
出版者	SPRINGER
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/42320
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Chen, Yiqiang
作者单位	1.Chinese Acad Sci, Beijing Key Lab Mobile Comp & Pervas Device, Inst Comp Technol, Beijing, Peoples R China 2.Univ Chinese Acad Sci, Beijing, Peoples R China 3.Beijing Inst Technol, Beijing, Peoples R China 4.Tsinghua Univ, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Gao, Jiayuan,Zhang, Yingwei,Chen, Yiqiang,et al. Agent-in-the-loop to distill expert knowledge into artificial intelligence models: a survey[J]. ARTIFICIAL INTELLIGENCE REVIEW,2025,58(9):55.
APA	Gao, Jiayuan.,Zhang, Yingwei.,Chen, Yiqiang.,Dong, Yihan.,Chen, Yuanzhe.,...&Gu, Yang.(2025).Agent-in-the-loop to distill expert knowledge into artificial intelligence models: a survey.ARTIFICIAL INTELLIGENCE REVIEW,58(9),55.
MLA	Gao, Jiayuan,et al."Agent-in-the-loop to distill expert knowledge into artificial intelligence models: a survey".ARTIFICIAL INTELLIGENCE REVIEW 58.9(2025):55.