AI 中文总结
本文提出GRAFT方法，通过保留全局优化工作流并局部替换选定区域实现智能体工作流的实例级自适应，在多类任务上较MaAS平均提升3.85个百分点，且执行器升级无需重新优化全局工作流。
AI 中文摘要
智能体工作流优化的最新进展通过任务特定的工作流搜索或输入条件架构选择实现工作流设计自动化，但这些方法在执行前确定工作流，无法利用执行时无标签质量信号调整失败的工作流区域。若通过全工作流重新优化实现此类推理时自适应，计算成本将过高。为应对该挑战，本文提出GRAFT，该方法在保留全局优化工作流的同时，仅针对每个输入局部替换选定区域。无需参数训练，GRAFT利用无标签执行质量信号评估区域级备选方案，仅接受能提升局部质量且保持工作流级一致性的替换，从而实现实例级自适应而无需全工作流重新优化。GRAFT无需修改即可应用于数学推理、代码生成、多跳及知识密集型问答等一系列任务。在匹配优化器与执行器设置下，其较最强的现有工作流优化方法MaAS平均提升3.85个百分点；仅用更强模型替换执行器，无需重新优化全局工作流即可获得进一步提升。这表明优化后的工作流并非仅是静态优化产物，而是可随推理时反馈与更强执行器演化的自适应执行策略。
英文摘要
Recent advances in agentic workflow optimization automate workflow design through task-specific workflow search or input-conditioned architecture selection. However, they determine the workflow before execution and cannot adapt failed workflow regions using execution-time label-free quality signals. Naively enabling such inference-time adaptation through whole-workflow re-optimization would be computationally prohibitive. To tackle this challenge, we introduce GRAFT, which preserves a globally optimized workflow while locally replacing only selected regions for each input. Without parameter training, GRAFT evaluates region-level alternatives using label-free execution-quality signals and accepts only replacements that improve local quality while preserving workflow-level consistency, thereby enabling instance-wise adaptation without whole-workflow re-optimization. GRAFT applies without modification across a range of tasks spanning mathematical reasoning, code generation, and multi-hop and knowledge-intensive question answering. Under matched optimizer and executor settings, it improves over the strongest prior workflow-optimization method, MaAS, by 3.85 points on average. Replacing only the executor with a stronger model yields further gains without re-optimizing the global workflow. This suggests that an optimized workflow is not merely a static optimization artifact, but an adaptable execution policy that can evolve with inference-time feedback and stronger executors.
Comments9 pages, 3 figures, 4 tables
