AI RESEARCH
Why Search When You Can Transfer? Amortized Agentic Workflow Design from Structural Priors
arXiv CS.LG
•
ArXi:2604.25012v1 Announce Type: new Automated agentic workflow design currently relies on per-task iterative search, which is computationally prohibitive and fails to reuse structural knowledge across tasks. We observe that optimized workflows converge to a small family of domain-specific topologies, suggesting that this combinatorial search is largely redundant. Building on this insight, we propose SWIFT (Synthesizing Workflows via Few-shot Transfer), a framework that amortizes workflow design into reusable structural priors.