Netflix 研究科学家分享主观任务 Agent 评测路线图

我刚刚发布了一份关于在高度主观任务上构建评测的路线图。以下是其中的关键步骤，以及一些用于减少噪声、提升置信度的实用技巧…… 博客在这里：https://t.co/uo0FsWtkYF 为什么这很难？评测智能体本就困难，原因在于其范围广泛、侧重昂贵且长周期的任务，以及非确定性。主观任务让这件事难上加难，因为我们无法确定性地验证解决方案，必须依赖人工判断（或 LLM 评判者）。这给本就困难的评测流程引入了额外的噪声。 评测路线图。我们可以使用一个可重复的框架来构建可靠的评测，该框架包含三个组成部分： - 人工评测：我们衡量质量的首要标准。在领域专家的帮助下制定清晰定义质量的质量准则，校准人工评测员以确保一致性，并持续监控评测质量。 - 离线评测：使用经过校准的 LLM 评判者或针对具体任务的评分细则，作为人工评测的高效替代。这使我们能够扩大实验规模，而不必为每个新模型都依赖昂贵的人工评测。 - 生产监控：追踪来自真实世界智能体使用情况的质量信号，并使用 A/B 测试在全面部署新智能体之前验证改进效果。 多阶段评测。这些组成部分构成一个分层评测流程： 离线评测 → 人工评测 → 生产 A/B 测试 → 全面部署 我们可以自动测试许多想法，将有希望的候选方案送去人工评测，并通过生产 A/B 测试验证改进效果。持续的生产监控随后让我们能够发现生产中的新用例/失败案例，并将其加入评测的早期阶段，从而形成反馈闭环。 采样有用的数据。评测质量在很大程度上取决于我们选择哪些任务。我们希望任务多样、真实、有难度、有区分度且准确。结构化任务分类体系、基于模型的难度过滤、项目反应理论（IRT）以及基于 LLM 的审计等技巧，有助于我们构建信息量更大的评测集。 处理噪声。我们应当在整个评测过程中运用统计学： - 功效分析：估算检测有意义的改进所需的评测样本数量。 - 置信区间：量化不确定性，并在评测结果旁提供清晰的置信信号。 - 重复采样：重复进行智能体/评判者评测，以减少任务内方差，并有可能收窄置信区间。 - 配对比较：在相同任务上评测模型，以更可靠地检测性能差异。 关键要点。基准分数的提升并不总是意味着我们的智能体能力更强。我们需要设计良好的评测任务、经过校准的人工/模型评测员以及统计置信信号，才能将有意义的能力提升与噪声区分开来（尤其是在主观任务上）。通过将这些技巧整合为一个可重复的评测流程/路线图，我们可以让评测套件的构建与维护更加系统化、可靠且可扩展。

查看原文

I just published my roadmap for building evals on highly subjective tasks. Here are the key steps involved and practical tricks for reducing noise / increasing confidence… Blog is here: https://t.co/uo0FsWtkYF Why is this difficult? Evaluating agents is already hard due to their broad scope, emphasis on expensive / long-horizon tasks, and non-determinism. Subjective tasks make this even harder because we cannot deterministically verify solutions and must rely on human judgments (or LLM judges). This introduces additional noise into an already difficult evaluation process. Evaluation roadmap. We can build reliable evaluations using a repeatable framework with three components: - Human evaluation: Our North Star for quality. Create quality guidelines that clearly define quality with the help of subject-matter experts, calibrate human evaluators to ensure agreement, and continually monitor evaluation quality. - Offline evaluation: Use calibrated LLM judges or task-specific rubrics as an efficient proxy for human evaluation. This allows us to scale experimentation without relying on expensive human evaluation for every new model. - Production monitoring: Track quality signals from real-world agent usage and use A/B testing to validate improvements before fully deploying a new agent. Multi-stage evaluation. These components form a tiered evaluation process: Offline evaluation → Human evaluation → Production A/B test → Full deployment We can test many ideas automatically, send promising candidates to human evaluation, and validate improvements through production A/B testing. Continual production monitoring then allows us to discover new use cases / failure cases in production that we can add into the earlier stages of evaluation to create a feedback loop. Sampling useful data. Evaluation quality depends heavily on which tasks we select. We want tasks that are diverse, realistic, difficult, discriminative, and accurate. Techniques like structured task taxonomies, model-based difficulty filtering, Item Response Theory (IRT), and LLM-based auditing help us construct more informative evaluation sets. Handling noise. We should leverage statistics throughout the evaluation process: - Power analysis: Estimate the number of evaluation samples needed to detect meaningful improvements. - Confidence intervals: Quantify uncertainty and provide clear confidence signals alongside evaluation results. - Re-sampling: Repeat agent / judge evaluations to reduce within-task variance and potentially tighten confidence intervals. - Paired comparisons: Evaluate models on the same tasks to more reliably detect performance differences. Key takeaway. An improved benchmark score does not always mean our agent is more capable. We need well-designed evaluation tasks, calibrated human / model evaluators, and statistical confidence signals to distinguish meaningful capability improvements from noise (especially on subjective tasks). By combining these techniques into a repeatable evaluation process / roadmap, we can make building and maintaining evaluation suites more systematic, reliable, and scalable.