Multi-agent AI systems have proven effective for complex reasoning. These systems are compounded by specialized agents, which collaborate through explicit communication, but incur substantial computational overhead. A natural question arises: can we achieve similar modularity benefits with a single agent that selects from a library of skills? We explore this question by viewing skills as internalized agent behaviors. From this perspective, a multi-agent system can be compiled into an equivalent single-agent system, trading inter-agent communication for skill selection. Our preliminary experiments suggest this approach can substantially reduce token usage and latency while maintaining competitive accuracy on reasoning benchmarks. However, this efficiency raises a deeper question that has received little attention: how does skill selection scale as libraries grow?
Drawing on principles from cognitive science, we propose that LLM skill selection exhibits bounded capacity analogous to human decision-making. We investigate the scaling behavior of skill selection and observe a striking pattern. Rather than degrading gradually, selection accuracy remains stable up to a critical library size, then drops sharply, indicating a phase transition reminiscent of capacity limits in human cognition. Furthermore, we find evidence that semantic confusability among similar skills, rather than library size alone, plays a central role in this degradation. This perspective suggests that hierarchical organization, which has long helped humans manage complex choices, may similarly benefit AI systems. Our initial results with hierarchical routing support this hypothesis. This work opens new questions about the fundamental limits of semantic-based skill selection in LLMs and offers a cognitive-grounded framework and practical guidelines for designing scalable skill-based agents.
SkillAdaptor: Self-Adapting Skills for LLM Agents from Trajectories
Zhejiang University（浙江大学）；Ant Digital Technologies, Ant Group（蚂蚁集团数字技术部）；Zhejiang University - Ant Group Joint Laboratory of Knowledge Graph（浙江大学-蚂蚁集团知识图谱联合实验室）
SkillSmith: Co-Evolving Skills and Tools for Self-Improving Agent Systems
Shanghai Jiao Tong University（上海交通大学）；Eastern Institute of Technology（东部技术研究所）；University of Science and Technology of China（中国科学技术大学）；Southeast University（东南大学）；Ningbo Institute of Digital Twin（宁波数字孪生研究所）
FORTIS: Benchmarking Over-Privilege in Agent Skills
University of Southern California（南加州大学）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Adobe Research（Adobe研究）；Arizona State University（亚利桑那州立大学）；University of Illinois Chicago（伊利诺伊大学芝加哥分校）；Johns Hopkins University（约翰霍普金斯大学）
EmbodiSkill: Skill-Aware Reflection for Self-Evolving Embodied Agents
Nanjing University（南京大学）；Huazhong University of Science and Technology（华中科技大学）；University of Science and Technology of China（中国科学技术大学）；Microsoft Research（微软研究院）；Institute for AI Industry Research (AIR) Tsinghua University（清华大学人工智能产业研究院）
Rethinking Self-Evolving Agent Skills: Feedback Dynamics over Multiple Rounds
The Hong Kong University of Science and Technology（香港科技大学）；Harbin Institute of Technology（哈尔滨工业大学）；Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））；Shanghai Jiao Tong University（上海交通大学）
DRIVE: Modeling Skills at the Reasoning and Interaction Levels for Web Agents under Continual Learning
College of Intelligence Science and Technology, National University of Defense Technology（智能科学与技术学院，国防科技大学）；College of Computer Science and Technology, National University of Defense Technology（计算机科学与技术学院，国防科技大学）
Demystifying Agent Skills: Why They Work-Until They Don't
Princeton University（普林斯顿大学）；UC San Diego（加州大学圣迭戈分校）；Stanford University（斯坦福大学）；University of Southern California（南加利福尼亚大学）；Johns Hopkins University（约翰斯·霍普金斯大学）
