提出无需每查询生成工作流，用少量任务级流程覆盖更多场景。
Do We Always Need Query-Level Workflows? Rethinking Agentic Workflow Generation for Multi-Agent Systems
- 用少量任务级工作流替代查询级生成，降低计算成本。
- 实验显示性能仅下降0.61%，但节省83%的令牌消耗。
- 适合追求高效多智能体系统部署的研究者与工程师。
基于大语言模型的多智能体系统通常通过工作流协调多个智能体解决复杂任务。现有方法在任务级或查询级生成工作流，但二者成本与收益尚不明确。经过重新思考与实证分析，我们发现查询级工作流生成并非总是必要，因为少量最优的任务级工作流已能覆盖等效甚至更多的查询。进一步发现，基于执行的全面任务级评估既消耗大量令牌又常不可靠。受自进化与生成式奖励建模启发，我们提出低代价任务级生成框架SCALE（Self prediction of the optimizer with few shot CALibration for Evaluation），以少量校准实现评估而非完整验证执行。大量实验表明，SCALE在多个数据集上性能仅平均下降0.61%，同时整体令牌使用量减少高达83%。
原文摘要 · Abstract (English)
Multi-Agent Systems (MAS) built on large language models typically solve complex tasks by coordinating multiple agents through workflows. Existing approaches generates workflows either at task level or query level, but their relative costs and benefits remain unclear. After rethinking and empirical analyses, we show that query-level workflow generation is not always necessary, since a small set of top-K best task-level workflows together already covers equivalent or even more queries. We further find that exhaustive execution-based task-level evaluation is both extremely token-costly and frequently unreliable. Inspired by the idea of self-evolution and generative reward modeling, we propose a low-cost task-level generation framework \textbf{SCALE}, which means \underline{\textbf{S}}elf prediction of the optimizer with few shot \underline{\textbf{CAL}}ibration for \underline{\textbf{E}}valuation instead of full validation execution. Extensive experiments demonstrate that \textbf{SCALE} maintains competitive performance, with an average degradation of just 0.61\% compared to existing approach across multiple datasets, while cutting overall token usage by up to 83\%.
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。