发表机构
Peking University; Tsinghua University（北京大学; 清华大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
Vibe-FDTR是面向智能体的FDTR数据分析框架，结合领域代码包与智能体技能，在基准测试中表现优异，可降低计算成本与执行时间，助力低门槛可信热计量。
AI 中文摘要
频域热反射（FDTR）是一种广泛用于测量微纳尺度热特性的激光泵浦-探测技术，但它依赖的复杂数据分析流程需要深厚的领域专业知识，且易受细微人为误差影响。本文提出Vibe-FDTR，一种面向智能体的框架，支持大语言模型（LLM）智能体直接通过自然语言请求完成可靠、可复现的FDTR分析。该框架将配置驱动的FDTR代码包（确保物理与参数一致性）与程序性智能体技能（将用户意图转化为有条理、可验证的分析步骤）相结合。我们采用含两个级别的受控基准测试Vibe-FDTR：基于金涂层石墨样品测量的合成单步任务和真实数据多步任务。在两个级别中，使用Vibe-FDTR的智能体分别达到100%和98.9%的成功率；相比之下，移除技能（仅保留Code-agent）会使性能降至91.4%和36.7%，若同时省略领域代码包（仅保留Agent-only），性能进一步降至38.6%和0%。除成功率外，Vibe-FDTR相较于Code-agent变体降低了87.7%的计算成本，缩短了超60%的执行时间。最后，可选的专家模式支持通过自主灵敏度与不确定性评估进行实验规划，并为欠明确任务制定基于物理的建议。这些结果表明，将领域代码与专家知识封装进智能体技能，为实现低门槛、自主且可信的热计量提供了可行途径。
英文摘要
Frequency-domain thermoreflectance (FDTR) is a laser pump-probe technique widely used to measure thermal properties at the micro- and nanoscale; however, it relies on a complex data analysis procedure that demands substantial domain expertise and is susceptible to subtle human errors. Here, we present Vibe-FDTR, an agent-oriented framework that enables large language model (LLM) agents to perform reliable and reproducible FDTR analyses directly from natural language requests. This framework couples a configuration-driven FDTR code package, which enforces physical and parametric consistency, with procedural agent skills that translate user intentions into organized and verifiable analysis steps. We evaluate Vibe-FDTR using a controlled benchmark with two levels: synthetic single-step tasks and real-data multi-step tasks based on measurements of gold-coated graphite samples. Across the two levels, agents using Vibe-FDTR achieve success rates of 100% and 98.9%, respectively. In sharp contrast, ablating skills (Code-agent) reduces performance to 91.4% and 36.7%, which drops further to 38.6% and 0% when the domain package is also omitted (Agent-only). Beyond success rate, Vibe-FDTR also reduces computational cost by 87.7% relative to the Code-agent variant and cuts execution time by more than 60%. Finally, an optional expert mode supports experimental planning via autonomous sensitivity and uncertainty evaluations, and formulates physically grounded recommendations for underspecified tasks. These results demonstrate that encapsulating domain code and expert knowledge into agent skills offers a promising route toward low-barrier, autonomous, and trustworthy thermal metrology.
