AI agents are autonomous systems that can execute specific tasks based on predefined programming. Here, we present SkillFlow, a modular, technology-agnostic framework that allows agents to expand their functionality in an ad-hoc fashion by acquiring new skills from their environment or other agents. We present a theoretical model that examines under which conditions this framework would be beneficial, and we then explore SkillFlow's ability to accelerate task completion and lead to lower cumulative costs in a real-world application, namely scheduling agents for calendar events. We demonstrate that within a few iterations, SkillFlow leads to considerable (24.8%, p-value = ) gains in time and cost, especially when the communication cost is high. Finally, we draw analogies from well-studied biological systems and compare this framework to that of lateral gene transfer, a significant process of adaptation and evolution in novel environments.
View on arXiv@article{tagkopoulos2025_2504.06188,
title={ SkillFlow: Efficient Skill and Code Transfer Through Communication in Adapting AI Agents },
author={ Pagkratios Tagkopoulos and Fangzhou Li and Ilias Tagkopoulos },
journal={arXiv preprint arXiv:2504.06188},
year={ 2025 }
}