让大模型多智能体任务并行处理，突破效率瓶颈。
APWA: A Distributed Architecture for Parallelizable Agentic Workflows
- 将复杂任务拆解为无交互的子任务，实现资源独立并行处理。
- 在前人系统崩溃的场景下仍能动态分解任务并线性扩展性能。
- 适合需要高吞吐、可并行的任务，如数据处理与批量推理。
基于大语言模型（LLMs）的自主多智能体系统在广泛应用领域中展现出独立解决复杂任务的强大能力。然而，随着任务规模与复杂度增加，这些系统面临关键推理、协调和计算扩展性的瓶颈。尽管底层LLM具备并行计算与推理原语，现有系统仍难以实现高吞吐并行处理。我们提出代理并行工作负载架构（APWA），一种专为高效处理高度可并行化智能体工作负载而设计的分布式多智能体系统架构。APWA通过将工作流分解为互不干扰的子问题，使各任务可使用独立资源并行执行，无需跨通信。该架构支持异构数据与多种并行处理模式，适用于多领域任务。实验表明，APWA可在先前系统完全失效的场景中动态分解复杂查询，并在更大任务上实现有效扩展。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。