Automated Stateful Specialization for Adaptive Agent Systems

ICLR 2026 Conference Submission24986 Authors

Keywords: LLMs, Autonomous Agents, Agent Specialization

TL;DR: We introduce a framework that creates persistent, specialist agent teams through an offline lifecycle of discovery and cultivation, and deploys them with an online policy that efficiently adapts the team's structure for novel tasks.

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 \textsc{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.

Primary Area: foundation or frontier models, including LLMs

Submission Number: 24986