让多个AI团队并行试解复杂任务，提速近两倍且不丢准确率。
Optimizing Sequential Multi-Step Tasks with Parallel LLM Agents
- 多个AI团队并行探索不同解法路径，用异步通信高效协作。
- 早期终止可实现最高2.2倍加速，聚合结果提升任务完成率。
- 适合需要快速推理的高复杂度实际任务，如自动化决策系统。
基于大语言模型的多智能体系统通过将复杂任务分解为迭代规划、执行、观察与优化的子任务，展现出巨大潜力。然而，这类系统常因需多次推理循环导致延迟过高。为此，我们提出M1-Parallel框架，通过并行运行多个多智能体团队，同时探索不同解决方案路径。该框架采用事件驱动通信机制与异步消息传递，有效利用合法计划的多样性，从而降低端到端延迟或提升任务完成率。实验表明，在复杂任务上，启用早期终止的M1-Parallel可实现高达2.2倍的加速，同时保持准确性；而采用聚合策略则进一步提升了任务完成率。我们还研究了促进计划多样性的策略，但发现重复采样已足够，无额外收益。这些结果凸显了并行计划执行在优化真实世界高复杂度推理任务中的潜力。
原文摘要 · Abstract (English)
Large language model (LLM)-based multi-agent systems have demonstrated remarkable promise for tackling complex tasks by breaking them down into subtasks that are iteratively planned, executed, observed, and refined. Despite their effectiveness, these systems often incur high latency because real-world problems frequently demand multiple iterative cycles of reasoning steps. To address this challenge, we propose M1-Parallel, a framework that concurrently runs multiple multi-agent teams in parallel to uncover distinct solution paths. By leveraging an event-driven communication model with asynchronous messaging, M1-Parallel efficiently capitalizes on the inherent diversity of valid plans to either reduce end-to-end latency or boost task completion rates. Our experiments on complex tasks show that M1-Parallel with early termination achieves up to $2.2\times$ speedup while preserving accuracy, and that M1-Parallel with aggregation yields higher task completion rates. We further investigate strategies aimed at encouraging diverse execution plans but observe no additional performance gains over repeated sampling. Overall, these findings underscore the potential of parallel plan execution for optimizing multi-agent systems for real-world, high-complexity reasoning tasks.
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。