CANTANTE: Optimizing Agentic Systems via Contrastive Credit Attribution

ArXi:2605.13295v1 Announce Type: cross LLM-based multi-agent systems have nstrated strong performance across complex real-world tasks, such as software engineering, predictive modeling, and retrieval-augmented generation. Yet automating their configuration remains a structural challenge, as scores are available only at the system level, whereas the parameters governing agent behavior are local. We argue that optimizing these systems is fundamentally a credit-assignment problem. We therefore.