Agentic Explainable Artificial Intelligence (Agentic XAI) Approach To Explore Better Explanation

Explainable Artificial Intelligence (XAI) is vital for trust and transparency in AI systems, especially in high-stakes applications. This study introduces an Agentic XAI approach that utilizes the iterative refinement capabilities of Large Language Models (LLMs) to generate more comprehensive and contextually relevant explanations. The framework integrates SHAP-based explainability with multimodal LLM-driven iterative refinement to enhance AI prediction interpretability. Applied to an agricultural recommendation system using rice yield data in Japan, the Agentic XAI framework successfully enhanced recommendation quality by 30-33% from the baseline, demonstrating its potential for making complex AI decisions more understandable for human users and fostering better real-world decision-making.