基于大型语言模型(LLMs) 的自主多智能体系统在独立解决广泛应用领域中的复杂任务方面表现出了卓越的能力。然而，随着任务规模和复杂性的增长，, 这些系统遇到了关键推理, 协调, 和计算扩展瓶颈。尽管底层 LLM 中提供了并行计算和推理原语，但这些限制阻碍了多代理系统实现高度可并行任务, 的高吞吐量处理。我们引入代理并行工作负载架构(APWA),，这是一种分布式多代理系统架构，专为高效处理高度并行的代理工作负载而设计。 APWA 通过将工作流程分解为互不干扰的子问题来促进并行执行，这些子问题可以使用独立的资源进行处理，而无需交叉通信。它支持异构数据和并行处理模式,，并且可以容纳来自广泛领域的任务。在我们的评估,中，我们证明 APWA 可以动态地将复杂查询分解为可并行的工作流程，并在先前系统完全失败的情况下扩展更大的任务。
Autonomous multi-agent systems based on large language models (LLMs) have demonstrated 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 introduce the Agent-Parallel Workload Architecture (APWA), a distributed multi-agent system architecture designed for the efficient processing of heavily parallelizable agentic workloads. APWA facilitates parallel execution by decomposing workflows into non-interfering subproblems that can be processed using independent resources without cross-communication. It supports heterogeneous data and parallel processing patterns, and it accommodates tasks from a wide breadth of domains. In our evaluation, we demonstrate that APWA can dynamically decompose complex queries into parallelizable workflows and scales on larger tasks in settings where prior systems fail completely.
科目: 人工智能 (cs.AI); 分布式, 并行, 和集群计算 (cs.DC); 多代理系统 (cs.MA)
Subjects: Artificial Intelligence (cs.AI); Distributed, Parallel, and Cluster Computing (cs.DC); Multiagent Systems (cs.MA)