Learning to Construct Practical Agentic Systems

ArXi:2606.00189v1 Announce Type: cross Automated design and optimization of agentic LLM-based systems leads to sophisticated systems that substantially improve result quality over off-the-shelf agentic patterns. However, studies of fielded agentic systems show that production systems focus much on issues such as simplicity, controllability, and predictability of inference costs. In this paper we propose principled approaches to designing and optimizing practical agentic systems.