Agentic Explainable Artificial Intelligence (Agentic XAI) Approach To Explore Better Explanation
Tomoaki Yamaguchi, Yutong Zhou, Masahiro Ryo, Keisuke Katsura

TL;DR
This paper introduces an agentic XAI framework that combines SHAP explainability with multimodal LLM-driven iterative refinement, improving explanations in an agricultural setting and revealing the importance of early stopping for optimal utility.
Contribution
It presents a novel integration of agentic LLMs with XAI, demonstrating iterative refinement improves explanations but requires strategic early stopping to prevent quality decline.
Findings
Explanations improved by 30-33% over initial rounds
Excessive refinement reduces explanation quality
Early stopping enhances practical utility
Abstract
Explainable artificial intelligence (XAI) enables data-driven understanding of factor associations with response variables, yet communicating XAI outputs to laypersons remains challenging, hindering trust in AI-based predictions. Large language models (LLMs) have emerged as promising tools for translating technical explanations into accessible narratives, yet the integration of agentic AI, where LLMs operate as autonomous agents through iterative refinement, with XAI remains unexplored. This study proposes an agentic XAI framework combining SHAP-based explainability with multimodal LLM-driven iterative refinement to generate progressively enhanced explanations. As a use case, we tested this framework as an agricultural recommendation system using rice yield data from 26 fields in Japan. The Agentic XAI initially provided a SHAP result and explored how to improve the explanation through…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsExplainable Artificial Intelligence (XAI) · Smart Agriculture and AI · Agriculture Sustainability and Environmental Impact
