WorkflowOps：学习多智能体工作流编排的智能体协作先验

中文摘要 AI 辅助

多智能体系统越来越多地被部署用于复杂的知识工作，然而其编排层在很大程度上仍然是无记忆的：每个新任务都被从头开始分解、分配和执行，无法从先前成功的执行中获益。我们提出了WorkflowOps，一个多智能体工作流编排框架，它从历史工作流中学习智能体协作先验，并按需扩展其智能体池以覆盖新的能力需求。我们的方法引入了三种耦合机制。首先，转移概率矩阵从过去的工作流中捕获成对智能体协作频率，并在DAG工作流构建过程中通过层内排序优化、概率阈值边建议和传递约简以最大化并行性，将其作为软指导应用。其次，一个充分性驱动的智能体创建循环通过语义匹配分数检测能力缺口，通过LLM生成专门智能体，并同时将它们注入协作矩阵，使得新创建的智能体能够立即与预测的协作先验一起使用。第三，分层语义匹配策略使用预训练句子嵌入进行快速、确定性的能力匹配作为第一遍，仅对低置信度情况调用LLM验证，从而相比纯LLM方法减少了超过80%的LLM路由调用。在混合代码、数学和问答套件上的实验表明，WorkflowOps相比近期的工作流构建基线提高了端到端通过率，在结构化、可分解的任务上提升最大，这些任务中过去的智能体交接模式可以迁移。

英文摘要

Multi-agent systems are increasingly deployed for complex knowledge work, yet their orchestration layers remain largely memoryless: each new task is decomposed, assigned, and executed from scratch with no benefit from prior successful executions. We present WorkflowOps, a multi-agent workflow orchestration framework that learns agent collaboration priors from historical workflows and expands its agent pool on demand to cover new capability requirements. Our approach introduces three coupled mechanisms. First, a transition probability matrix captures pairwise agent collaboration frequencies from past workflows and applies them as soft guidance during DAG workflow construction through intra-layer ordering optimization, probability-thresholded edge suggestion, and transitive reduction for parallelism maximization. Second, a sufficiency-driven agent creation loop detects capability gaps via semantic matching scores, generates specialized agents through an LLM, and simultaneously injects them into the collaboration matrix, so that newly created agents are immediately usable with predicted collaboration priors. Third, a layered semantic matching strategy uses pre-trained sentence embeddings for fast, deterministic capability matching as a first pass, invoking LLM verification only for low-confidence cases, thereby reducing LLM routing calls by over 80\% compared to pure-LLM approaches. Experiments on mixed code, math, and question-answering suites show that WorkflowOps improves end-to-end pass rates over recent workflow-construction baselines, with the largest gains on structured, decomposable tasks where past agent handoff patterns transfer.

发表机构

• Rutgers University（罗格斯大学）
• University of Pittsburgh（匹兹堡大学）
• NEC Labs America（NEC美国实验室）

机构由 AI 辅助整理，请以论文原文为准。