评估自动化机器学习流水线中AI代理决策与结果的框架
A Framework for Assessing AI Agent Decisions and Outcomes in AutoML Pipelines
AI总结:
本文提出评估代理(EA)用于评估自动化机器学习代理的决策质量,通过四个维度检测决策错误、识别推理不一致并归因下游性能变化,提升自动化机器学习系统的可解释性和可控性。
摘要:
基于代理的自动化机器学习系统依赖大型语言模型在数据处理、模型选择和评估等多阶段决策中做出复杂决策。然而,现有的评估实践仍以结果为中心,主要关注最终任务性能。通过回顾先前工作,我们发现没有调查的代理自动化机器学习系统报告结构化、决策层面的评估指标,用于事后评估中间决策质量。为了解决这一限制,我们提出一个评估代理(EA),在不干扰其执行的情况下对自动化机器学习代理进行决策中心的评估。EA被设计为一个观察者,沿着四个维度评估中间决策:决策有效性、推理一致性、模型质量风险(超越准确性)以及反事实决策影响。在四个概念验证实验中,我们证明EA可以(i)用F1得分为0.919检测错误决策,(ii)独立于最终结果识别推理不一致,(iii)将下游性能变化归因于代理决策,揭示影响范围从-4.9%到+8.3%。这些结果展示了决策中心评估如何揭示对结果-only指标不可见的失败模式。我们的工作将自动化机器学习系统的评估从以结果为基础的视角转向审计代理决策,为可靠、可解释和可控的自主机器学习系统提供了基础。
英文摘要:
Agent-based AutoML systems rely on large language models to make complex, multi-stage decisions across data processing, model selection, and evaluation. However, existing evaluation practices remain outcome-centric, focusing primarily on final task performance. Through a review of prior work, we find that none of the surveyed agentic AutoML systems report structured, decision-level evaluation metrics intended for post-hoc assessment of intermediate decision quality. To address this limitation, we propose an Evaluation Agent (EA) that performs decision-centric assessment of AutoML agents without interfering with their execution. The EA is designed as an observer that evaluates intermediate decisions along four dimensions: decision validity, reasoning consistency, model quality risks beyond accuracy, and counterfactual decision impact. Across four proof-of-concept experiments, we demonstrate that the EA can (i) detect faulty decisions with an F1 score of 0.919, (ii) identify reasoning inconsistencies independent of final outcomes, and (iii) attribute downstream performance changes to agent decisions, revealing impacts ranging from -4.9% to +8.3% in final metrics. These results illustrate how decision-centric evaluation exposes failure modes that are invisible to outcome-only metrics. Our work reframes the evaluation of agentic AutoML systems from an outcome-based perspective to one that audits agent decisions, offering a foundation for reliable, interpretable, and governable autonomous ML systems.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。