用扎根理论自动化分析上千条智能体轨迹，发现新行为模式。
Using Grounded Theory for Agent Behavior Analysis at Scale
- 用扎根理论三阶段编码自动构建行为分类体系
- 在6个数据集上复现73%-91%的人工标注失败模式
- 适合研究智能体真实行为的机器学习与开发人员
理解智能体行为需要可扩展至数千条轨迹的方法，并能在长而陌生的任务中发现新规律，传统预设分类器难以胜任。本文将社会科学研究中的扎根理论引入智能体轨迹分析：一种六十年历史的定性方法，具备严谨的饱和标准和可追溯的数据到理论路径。提出AutoTraceGT（基于扎根理论的自动化轨迹分析），首个面向多智能体的自动化扎根理论分析流水线。它通过迭代执行开放编码、轴心编码和理论编码直至饱和，生成针对每个任务定制的行为分类体系。在六个轨迹数据集上，AutoTraceGT生成的代码本恢复了73%-91%人工标注分类体系中的失败模式，并揭示了原分类体系遗漏的新模式。生成的理论叙事与专家已有认知一致。作为归纳特征空间，该代码本在下游失败预测任务中优于零样本与少样本大模型基线。结果表明，扎根理论为研究智能体实际行为提供了可扩展的分析工具。
原文摘要 · Abstract (English)
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.
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。