arXiv cs.AI· Qi Cheng, Shengyu Chen, Wei Cheng, Yiqun Xie, Haoyu Wang, Haifeng Chen, Xiaowei Jia·· 10 天前AI 评分25
RA-MoWE：用工作流亲和度嵌入做查询聚类与智能体工作流生成
RA-MoWE: Workflow-Affinity Embeddings for Query Clustering and Agentic Workflow Generation
AI 导读
RA-MoWE 通过工作流亲和度嵌入对查询聚类，并据此生成可复用的专家工作流，每个嵌入记录一组固定参考工作流对查询的解决效果。在覆盖数学、科学、编程四个 benchmark 的 300 条查询测试集上，其平均任务得分比在参考工作流中选择高出 4.04 个百分点，推理时语言模型调用次数减少 27.7%。嵌入编码器可直接从查询文本预测该嵌入，使新查询无需先执行参考工作流即可选定专家。
正文 · 原文
Abstract:Agentic workflows enable large language models (LLMs) to solve complex tasks by coordinating reasoning, tool use, and verification. However, a workflow optimized for an entire task collection can overlook differences in the reasoning strategies that individual queries need, while searching for a new workflow for every query repeats costly optimization. To address this tradeoff, we introduce RA-MoWE, a framework that uses workflow-affinity embeddings to cluster queries and guide the generation of reusable expert workflows. Each embedding records how well a fixed set of reference workflows solves a query, revealing similarities in which reasoning strategies are effective. RA-MoWE uses each cluster's queries and average embedding to initialize and refine a specialized workflow through execution feedback. An embedding encoder predicts these embeddings from query text, allowing new queries to select a generated expert without first executing the reference workflows. On a 300-query test set drawn from four benchmarks spanning mathematics, science, and programming, RA-MoWE improves average task score by 4.04 percentage points over selecting among the reference workflows, while using 27.7% fewer language-model calls at inference.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.07851 [cs.AI] |
| (or arXiv:2610.07851v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.07851 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Qi Cheng [view email]
[v1]
Tue, 6 Oct 2026 06:58:16 UTC (147 KB)
来源：arXiv cs.AI · arxiv.org