Agent-as-Peer-Debriefer: A Multi-Agent Framework with Perspective-Based Refinement for Qualitative Analysis

The paper introduces Agent-as-Peer-Debriefing, a multi‑agent framework that incorporates peer debriefing into qualitative data analysis with large language models. A Hierarchical Coding Agent generates codes and reflections, which are then refined by three Peer‑Debriefing Agents applying Theory‑Driven, Data‑Driven, or Applied perspectives. Experiments on three datasets show that perspective‑based refinement aligns more closely with human codes than a single‑LLM baseline, and that the choice of perspective offers meaningful trade‑offs.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• llms
• agents
• benchmarks