Using Grounded Theory for Agent Behavior Analysis at Scale
Summary
AutoTraceGT automates grounded theory analysis on agent trajectories to build behavioral taxonomies, effectively recovering human failure-mode annotations and improving downstream prediction tasks.
View Cached Full Text
Cached at: 09/04/26, 11:57 AM
Paper page - Using Grounded Theory for Agent Behavior Analysis at Scale
Source: https://huggingface.co/papers/2608.30391
Abstract
AutoTraceGT automates grounded theory coding on agent trajectories to build task-specific behavioral taxonomies that recover and extend human failure-mode annotations for downstream prediction.
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 bringgrounded theoryinto agent trajectory analysis: a six-decade-old qualitative method from the social sciences, with a principledsaturationcriterion and an auditable trail from data to theory. We proposeAutoTraceGT(Automated Trace analysis throughGrounded Theory), the first multi-agent pipeline that automatesgrounded theoryon agent trajectories. It iteratively performs open, axial, andtheoretical codinguntilsaturation, producing abehavioral taxonomytailored to each task. Across six trajectory corpora,AutoTraceGTproduces 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 adeductive feature space, the codebook outperforms zero-shot and few-shot LLM baselines on downstreamfailure prediction. These results suggestGrounded Theoryoffers a scalable analytic tool for ML researchers and agent developers studying what agents actually do.
View arXiv pageView PDFProject pageAdd to collection
Get this paper in your agent:
hf papers read 2608\.30391
Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash
Models citing this paper0
No model linking this paper
Cite arxiv.org/abs/2608.30391 in a model README.md to link it from this page.
Datasets citing this paper0
No dataset linking this paper
Cite arxiv.org/abs/2608.30391 in a dataset README.md to link it from this page.
Spaces citing this paper0
No Space linking this paper
Cite arxiv.org/abs/2608.30391 in a Space README.md to link it from this page.
Collections including this paper0
No Collection including this paper
Add this paper to acollectionto link it from this page.
Similar Articles
TraceGraph: Shared Decision Landscapes for Diagnosing and Improving Agent Trajectories
TraceGraph is a graph-based framework that constructs shared decision landscapes from multi-model agent trajectories, enabling diagnosis of failure regions and improvement via trap-aware recovery pipelines.
@omarsar0: NEW paper from Microsoft and colleagues. Debugging agent trajectories at scale is challenging. This is a clever approac…
This paper introduces OAT, a lightweight failure attribution tool for LLM-based agentic systems that trains only on successful trajectories and uses neural controlled differential equations to detect error steps, outperforming expensive baselines by orders of magnitude in speed and accuracy.
TrajGenAgent: A Hierarchical LLM Agent for Human Mobility Trajectory Generation
TrajGenAgent proposes a hierarchical LLM agent framework that decouples macro-level activity planning from micro-level spatiotemporal instantiation for realistic human mobility trajectory generation without fine-tuning. It also introduces an anomaly-detection-based evaluation for behavioral fidelity.
From Noisy Traces to Root Causes: Structural Trajectory Analysis and Causal Extraction for Agent Optimization
Introduces STRACE, a framework that performs structural trajectory analysis and causal extraction to construct high signal-to-noise optimization contexts for improving long-horizon agents, outperforming baselines on a formal verification task.
Lost in Recovery: Demystifying Recovery Behavior of Computer-Use Agents via Goal-Oriented Action Replay
ReTrace is a scalable evaluation framework for systematically studying recovery behavior in computer-use agents, formalizing Transition-Consistent Recovery via goal-oriented action replay after controlled error injection. The study finds that ideal recovery unlocks latent task completion capabilities, current agents fail to exploit their recovery potential, and accurate model-based recovery yields measurable end-to-end gains.