Nath, Saptarshi; Peridis, Christos; Benjamin, Eseoghene; Liu, Xinran; Kolouri, Soheil; Kinnell, Peter; Li, Zexin; Liu, Cong; Dora, Shirin; Soltoggio, Andrea (2026).听.听Proceedings of the AAAI Conference on Artificial Intelligence, 40(29), 24504鈥�24512.听
Agentic AI聽refers to systems that can set their own goals, adapt to new situations, and improve over time through experience. This study explores how such systems can learn more efficiently by sharing knowledge with one another, instead of learning everything from scratch. In particular, it looks at how an AI agent can decide聽what knowledge to reuse, which other agents to learn from, and how to incorporate that knowledge聽into its own decision-making process (often called a聽policy, or strategy for choosing actions).
The researchers introduce a new method called聽MOSAIC (Modular Sharing and Composition in Collective Learning). This approach allows agents to compare tasks using mathematical representations, select useful knowledge from others based on performance and similarity, and integrate it using flexible, modular neural network components. In simple terms, agents can 鈥渂orrow鈥� and adapt pieces of what others have already learned.
The results show that agents using MOSAIC learn faster and perform better than those learning alone or sharing information indiscriminately. In some cases, they can even solve problems that individual agents cannot. The study also finds that targeted, selective sharing reduces confusion between tasks and leads to a kind of聽self-organization, where agents working on easier problems help others tackle more complex ones. Overall, this work highlights the potential of collaborative learning strategies to make AI systems more efficient and adaptable.
