AI 行为分析有了社会学老方法
研究 AI 智能体在长任务里到底在干什么，过去靠人看轨迹或预设分类器，又慢又容易漏。这篇把社会学用了六十年的「扎根理论」搬来：让 AI 自动对智能体的行为轨迹反复编码、归类，直到不再出现新模式为止，最后产出一套针对该任务的行为分类。在六套轨迹数据上，它找回了人类标注里 73% 到 91% 的失败模式，还发现了人类漏掉的规律。它不是你明天能拿来调模型的工具，但它是「AI 在无人监督时究竟怎么做事」这件事上，少有的系统化观察手段。
📄 原文摘要(英文)
Understanding agent behavior requires methods that scale to thousands of trajectories and surface new patterns in long, often unfamiliar tasks where pre-built classifiers fall short. We propose to bring grounded theory into agent trajectory analysis: a six-decade-old qualitative method from the social sciences, with a principled saturation criterion and an auditable trail from data to theory. We propose AutoTraceGT (Automated Trace analysis through Grounded Theory), the first multi-agent pipeline that automates grounded theory on agent trajectories. It iteratively performs open, axial, and theoretical coding until saturation, producing a behavioral taxonomy tailored to each task. Across six trajectory corpora, AutoTraceGT produces codebooks that recover 73-91 percent of the failure modes in human-annotated taxonomies and surface additional patterns that those taxonomies miss. The emergent theoretical narrative aligns with prior expert accounts. Used as a deductive feature space, the codebook outperforms zero-shot and few-shot LLM baselines on downstream failure prediction. These results suggest Grounded Theory offers a scalable analytic tool for ML researchers and agent developers studying what agents actually do.