PopPy: Opportunistically Exploiting Parallelism in Python Agentic Workflows

Excerpt

arXiv:2605.18697v2 Announce Type: replace-cross Abstract: Agentic workflows, which compose calls to ML models using a general-purpose programming language like Python, are widely used for a variety of user-facing tasks, from software engineering to enterprise automation, making their end-to-end latency a critical bottleneck. To improve their latency, developers can either manually parallelize them or use restricted agentic frameworks that cannot express or exploit all forms of parallelization. W