Automated Specialization of Stateful Agent Systems

Myan Vu, Harrish Ayyanar, PANG JIANG, Anwiketh Reddy, Mayank Goel, Kevin Zhu

Keywords: Multi-Agent Systems, Automated Agent Design, Agent Specialization, Stateful Agents, Reinforcement Learning, Large Language Models (LLMs), Agentic Workflows

Abstract: Current automated agent design frameworks produce either static workflows that lack adaptability or per-query optimizers that prevent the accumulation of deep, agent-level task expertise. We propose a new direction that reconciles these paradigms: creating stateful teams of specialist agents that accumulate knowledge over time and can be reconfigured for novel tasks entirely without human intervention. To this end, we introduce ASpec, a framework that manages this full agent lifecycle by first autonomously $\textbf{discovering}$ specialist archetypes via evolutionary search and then $\textbf{cultivating}$ their expertise through experience, mirroring how human experts learn through practice and reflection. We further introduce a lightweight hierarchical control policy, "retain-then-escalate," which governs when to leverage the established agent system versus when to adapt its structure. Through comprehensive experiments, we demonstrate that this approach leads to significant performance gains on expert-level scientific benchmarks like GPQA while matching the state-of-the-art on broader domain tasks, demonstrating a promising path toward agent systems that are simultaneously expert, adaptive, and efficient. We will release the code at https://github.com/myanvoos/ASpec.

Archival Option: The authors of this submission do *not* want it to appear in the archival proceedings.

Submission Number: 163