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 more 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 more accessible, natural-language explanations. In this work, we propose a multi-agent framework for XAI narrative generation and refinement. The framework comprises the Narrator, which generates and revises narratives based on feedback from multiple Critic Agents on faithfulness and coherence metrics, thereby enabling narrative improvement through iteration. We design five agentic systems (Basic Design, Critic Design, Critic-Rule Design, Coherent Design, and Coherent-Rule Design) and systematically evaluate their effectiveness across five LLMs on five tabular datasets. Results validate that the Basic Design, the Critic Design, and the Critic-Rule Design are effective in improving the faithfulness of narratives across all LLMs. Claude-4.5-Sonnet on Basic Design performs best, reducing the number of unfaithful narratives by 90% after three rounds of iteration. To address recurrent issues, we further introduce an ensemble strategy based on majority voting. This approach consistently enhances performance for four LLMs, except for DeepSeek-V3.2-Exp. These findings highlight the potential of agentic systems to produce faithful and coherent XAI narratives.
DataNarrative: Automated Data-Driven Storytelling with Visualizations and Texts
York University（约克大学）；Qatar Computing Research Institute (QCRI)（卡塔尔计算研究所）；Nanyang Technological University（南洋理工大学）；Dialpad Inc.（Dialpad公司）；Salesforce AI（Salesforce人工智能部门）
Good quality explanations of artificial intelligence (XAI) reasoning must be written (and evaluated) for an explanatory purpose, targeted towards their readers, have a good narrative and causal structure, and highlight where uncertainty and data quality affect the AI output. I discuss these challenges from a Natural Language Generation (NLG) perspective, and highlight four specific NLG for XAI research challenges.
Knowledge-Grounded Agentic Large Language Models for Multi-Hazard Understanding from Reconnaissance Reports
organization= Department One , addressline= Address One , city= City One , postcode= 00000 , state= State One , country= Country One；organization= Department Two , addressline= Address Two , city= City Two , postcode= 22222 , state= State Two , country= Country Two；organization= Zachry Department of Civil \& Environmental Engineering, Texas A\&M University , addressline= 3136 TAMU , city= College Station , postcode= 77843 , state= TX , country= USA；organization= Department of Engineering Technology；Industrial Distribution, Texas A\&M University , city= College Station , postcode= 77843 , state= TX , country= USA；organization= Department of Civil；Environmental Engineering, University of Illinois Urbana-Champaign , city= Urbana , postcode= 61801 , state= IL , country= USA
Prompt, Plan, Extract: Zero-Shot Agentic LLMs Workflows for Lung Pathology Extraction from Clinical Narratives
Department of Health Outcomes and Biomedical Informatics, College of Medicine, University of Florida（健康结果与生物医学信息学系，医学院，佛罗里达大学）；Division of Pulmonary, Critical Care and Sleep Medicine, Department of Medicine, College of Medicine, University of Florida（呼吸科、重症医学科和睡眠医学科，医学系，医学院，佛罗里达大学）；College of Nursing, Florida State University（护理学院，佛罗里达州立大学）
Explanations of Large Language Models Explain Language Representations in the Brain
Iran University of Science and Technology（伊朗科学技术大学）；University of Tehran（德黑兰大学）；Institute for Research in Fundamental Sciences（基础科学研究所）；Khatam University（哈塔姆大学）
