用智能体系统自动把科研问题转成可执行工作流，提升效率与准确率。
From Research Question to Scientific Workflow: Leveraging Agentic AI for Science Automation
- 分三层架构：理解问题、生成流程、专家定义技能规则
- 技能库使意图匹配准确率从44%升至83%，数据传输减少92%
- 全程自动化，每查询耗时低于15秒，成本不到0.001美元
科学工作流系统能自动执行任务（如调度、容错、资源管理），但无法自动完成研究问题到工作流规范的语义转换。科学家仍需手动将研究问题转化为工作流，这需要领域知识和基础设施经验。本文提出一种智能体架构，通过三层实现闭环：大模型将自然语言转化为结构化意图（语义层）；经验证的生成器产出可复现的工作流有向无环图（确定性层）；领域专家编写‘技能’——以Markdown文档形式编码词汇映射、参数约束和优化策略（知识层）。该设计将大模型的不确定性仅限于意图提取：相同意图始终生成相同工作流。在1000 Genomes群体遗传学工作流及基于Kubernetes的Hyperflow WMS上实现并评估。对150个查询的消融实验显示，使用技能后全匹配意图准确率从44%提升至83%；基于技能的延迟生成使数据传输减少92%；端到端管道在Kubernetes上完成查询，大模型开销低于15秒，单次成本低于0.001美元。
原文摘要 · Abstract (English)
Scientific workflow systems automate execution -- scheduling, fault tolerance, resource management -- but not the semantic translation that precedes it. Scientists still manually convert research questions into workflow specifications, a task requiring both domain knowledge and infrastructure expertise. We propose an agentic architecture that closes this gap through three layers: an LLM interprets natural language into structured intents (semantic layer); validated generators produce reproducible workflow DAGs (deterministic layer); and domain experts author ``Skills'': markdown documents encoding vocabulary mappings, parameter constraints, and optimization strategies (knowledge layer). This decomposition confines LLM non-determinism to intent extraction: identical intents always yield identical workflows. We implement and evaluate the architecture on the 1000 Genomes population genetics workflow and Hyperflow WMS running on Kubernetes. In an ablation study on 150 queries, Skills raise full-match intent accuracy from 44% to 83%; skill-driven deferred workflow generation reduces data transfer by 92\%; and the end-to-end pipeline completes queries on Kubernetes with LLM overhead below 15 seconds and cost under $0.001 per query.
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。