# Using Grounded Theory for Agent Behavior Analysis at Scale

arXiv: https://arxiv.org/abs/2608.30391 · HTML: https://mlsanity.com/paper/2608.30391/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 25 of its 36 references that are in the map.
- First posted on arXiv 31 Aug 2026.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 25 of 25)

- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [WebArena: A Realistic Web Environment for Building Autonomous Agents](https://mlsanity.com/paper/2307.13854/) (2023)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains](https://mlsanity.com/paper/2406.12045/) (2024)
- [WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents](https://mlsanity.com/paper/2207.01206/) (2022)
- [Mind2Web: Towards a Generalist Agent for the Web](https://mlsanity.com/paper/2306.06070/) (2023)
- [ALFWorld: Aligning Text and Embodied Environments for Interactive Learning](https://mlsanity.com/paper/2010.03768/) (2020)
- [OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments](https://mlsanity.com/paper/2404.07972/) (2024)
- [GAIA: a benchmark for General AI Assistants](https://mlsanity.com/paper/2311.12983/) (2023)
- [Why Do Multi-Agent LLM Systems Fail?](https://mlsanity.com/paper/2503.13657/) (2025)
- [Rewarding Progress: Scaling Automated Process Verifiers for LLM Reasoning](https://mlsanity.com/paper/2410.08146/) (2024)
- [Where LLM Agents Fail and How They can Learn From Failures](https://mlsanity.com/paper/2509.25370/) (2025)
- [FLAML: A Fast and Lightweight AutoML Library](https://mlsanity.com/paper/1911.04706/) (2019)
- [Supporting Qualitative Analysis with Large Language Models: Combining Codebook with GPT-3 for Deductive Coding](https://mlsanity.com/paper/2304.10548/) (2023)
- [CollabCoder: A Lower-barrier, Rigorous Workflow for Inductive Collaborative Qualitative Analysis with Large Language Models](https://mlsanity.com/paper/2304.07366/) (2023)
- [Go-Browse: Training Web Agents with Structured Exploration](https://mlsanity.com/paper/2506.03533/) (2025)
- [Agentic Rubrics as Contextual Verifiers for SWE Agents](https://mlsanity.com/paper/2601.04171/) (2026)
- [Butterfly Effects in Toolchains: A Comprehensive Analysis of Failed Parameter Filling in LLM Tool-Agent Systems](https://mlsanity.com/paper/2507.15296/) (2025)
- [HICode: Hierarchical Inductive Coding with LLMs](https://mlsanity.com/paper/2509.17946/) (2025)
- [How to Interpret Agent Behavior](https://mlsanity.com/paper/2605.13625/) (2026)
- [Auto-TA: Towards Scalable Automated Thematic Analysis (TA) via Multi-Agent Large Language Models with Reinforcement Learning](https://mlsanity.com/paper/2506.23998/) (2025)
- [LOGOS: LLM-driven End-to-End Grounded Theory Development and Schema Induction for Qualitative Research](https://mlsanity.com/paper/2509.24294/) (2025)
- [AcademiaOS: Automating Grounded Theory Development in Qualitative Research with Large Language Models](https://mlsanity.com/paper/2403.08844/) (2024)
- [Human-LLM Collaborative Feature Engineering for Tabular Data](https://mlsanity.com/paper/2601.21060/) (2026)
- [Agent-as-Peer-Debriefer: A Multi-Agent Framework with Perspective-Based Refinement for Qualitative Analysis](https://mlsanity.com/paper/2605.24600/) (2026)

## Abstract (arXiv)

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.