An Agentic Approach to Generating XAI-Narratives

ArXi:2603.20003v1 Announce Type: new Explainable AI (XAI) research has experienced substantial growth in recent years. Existing XAI methods, however, have been criticized for being technical and expert-oriented, motivating the development of interpretable and accessible explanations. In response, large language model (LLM)-generated XAI narratives have been proposed as a promising approach for translating post-hoc explanations into accessible, natural-language explanations. In this work, we propose a multi-agent framework for XAI narrative generation and refinement.