Skills are getting increasingly used in recent agentic frameworks, performing robustly with proprietary LLMs. Yet, their effectiveness for small and medium-sized open-source models (270M--80B) remains underexplored, especially under industrial, resource-constrained conditions. As such, we present a large-scale empirical study evaluating the skill paradigm's feasibility across two open-source classification tasks: one insurance-claim task based on proprietary data, and a set of Python programming problems. We find that very small models frequently fail to retrieve or select correct skills, substantially limiting their usefulness in the evaluated skill-augmented settings, while larger 30B--80B models gain substantial benefits from skill augmentation. Furthermore, we provide a deployment-oriented GPU profile, reporting VRAM time occupancy (GB$\cdot$min) across models under our evaluation settings---a deployment-oriented metric that may help characterize GPU-memory costs, where small and medium models are typically preferred for VRAM control. These results characterize how the benefits of skill augmentation vary with model scale, task complexity, and GPU budget, and provide deployment-oriented observations.
Harvard TH Chan School of Public Health(哈佛大学陈曾熙公共卫生学院);Vienna University of Economics and Business(维也纳经济与商业大学);University of Strasbourg(斯特拉斯堡大学);University of Lorraine(洛林大学);CNRS(法国国家科学研究中心);Quantum DataLab(量子数据实验室)
ArtisanCAD: An Industrial-Level CAD Agent with Expert-Grounded Knowledge Distillation
Peking University(北京大学);Eastern Institute of Technology(东方理工学院);Renmin University of China(中国人民大学);TenFong Technology Co., Ltd.(十方科技有限公司);IM Motors Technology Co., Ltd.(智己汽车科技有限公司)
IROSA: Interactive Robot Skill Adaptation using Natural Language
German Aerospace Center (DLR), Institute of Robotics and Mechatronics (RMC)(德国航空航天中心(DLR)机器人与机电研究所);School of Computation, Information and Technology (CIT), Technical University of Munich (TUM)(计算、信息与技术学院(CIT),慕尼黑技术大学)
MOMO: A framework for seamless physical, verbal, and graphical robot skill learning and adaptation
German Aerospace Center (DLR), Institute of Robotics and Mechatronics (RMC)(德国航空航天中心(DLR)机器人与机电研究所);School of Computation, Information and Technology (CIT), Technical University of Munich (TUM)(计算、信息与技术学院(CIT),慕尼黑技术大学)