When Single-Agent with Skills Replace Multi-Agent Systems and When They Fail

Abstract

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.

Repository Summary

This paper studies when a multi-agent system can be “compiled” into a single agent with a skill library, showing competitive reasoning accuracy with lower token usage and latency but also identifying a phase transition where skill selection collapses beyond a critical library size.

Bibliographic Data

Title

When Single-Agent with Skills Replace Multi-Agent Systems and When They Fail

Authors

Xiaoxiao Li

Publication date

2026/01/08

Identifier

arXiv:2601.04748

DOI

10.48550/arXiv.2601.04748

PDF size

1.5 MB