APWA: A Distributed Architecture for Parallelizable Agentic Workflows

ArXi:2605.15132v1 Announce Type: new Autonomous multi-agent systems based on large language models (LLMs) have nstrated remarkable abilities in independently solving complex tasks in a wide breadth of application domains. However, these systems hit critical reasoning, coordination, and computational scaling bottlenecks as the size and complexity of their tasks grow. These limitations hinder multi-agent systems from achieving high-throughput processing for highly parallelizable tasks, despite the availability of parallel computing and reasoning primitives in the underlying LLMs. We