Using Grounded Theory for Agent Behavior Analysis at Scale

2026-08-31

AI Summary

为解决大规模轨迹分析中行为模式识别问题，提出AutoTraceGT方法，通过自动化扎根理论进行多智能体行为分类，有效识别并预测行为失败模式。

Abstract

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.

Problem

• agent behavior
• trajectory analysis
• grounded theory

Innovation

• Grounded Theory
• Agent Trajectories
• Behavior Analysis
• Automated Coding
• Scalability