代理可解释人工智能（代理XAI）方法探索更好的解释
Agentic Explainable Artificial Intelligence (Agentic XAI) Approach To Explore Better Explanation: A Case Study in Decision Support for Rice Cultivation in Japan
AI总结：
本文提出一种结合SHAP解释性和多模态LLM迭代细化的代理XAI框架，通过农业推荐系统验证，发现早期停止可提升推荐质量，但过度细化导致性能下降，揭示了偏差-方差权衡。
摘要：
可解释人工智能（XAI）使数据驱动地理解因素与响应变量之间的关联，但将XAI输出传达给普通公众仍具有挑战性，阻碍了对基于AI的预测的信任。大型语言模型（LLMs）已出现作为将技术解释转化为可访问叙述的有希望的工具，但将代理AI（LLMs通过迭代细化作为自主代理）与XAI的整合仍处于未探索的领域。本研究提出了一种结合SHAP基于可解释性与多模态LLM驱动的迭代细化的代理XAI框架，以生成逐步增强的解释。作为用例，我们测试了该框架作为农业推荐系统，使用日本26个田地的水稻产量数据。代理XAI最初提供了SHAP结果，并通过额外分析在11次细化轮次（第0-10轮）中逐步改进解释。解释通过人类专家（作物科学家）（n=12）和LLM（n=14）根据七个指标进行评估：特异性、清晰度、简洁性、实用性、上下文相关性、成本考虑和作物科学可信度。两个评估组均确认该框架成功提升了推荐质量，从第0轮平均得分增加了30-33%，在第3-4轮达到峰值。然而，过度细化导致推荐质量显著下降，表明了偏差-方差权衡，其中早期轮次缺乏解释深度（偏差），而过度迭代引入了冗长和无根据的抽象（方差），这通过指标特定分析揭示出来。这些发现表明，需要战略性早期停止（正则化）以优化实用价值，挑战了关于单调改进的假设，并为代理XAI系统提供了基于证据的设计原则。
英文摘要：
Explainable artificial intelligence (XAI) reveals how explanatory variables relate to a response variable, yet communicating XAI outputs to laypersons remains difficult, limiting trust in AI-based predictions. Large language models (LLMs) can translate technical explanations into accessible narratives, but iterative refinement of XAI explanations by an autonomous LLM agent remains unexplored. This study proposes an agentic XAI framework that combines SHapley Additive exPlanations (SHAP) with iterative refinement by a multimodal LLM and tests it as an agricultural recommendation system on rice yield data from 28 fields in Japan. From a SHAP result, the agent explored additional analyses across 11 refinement rounds (Rounds 0-10). Crop scientists (n = 12) and LLM judges (n = 14) scored every round on seven criteria: Specificity, Clarity, Conciseness, Practicality, Contextual Relevance, Cost Consideration, and Crop Science Credibility. Both groups found that refinement raised the average score by 30-33% over Round 0, peaking at Rounds 3-4, after which quality declined, below the starting point for crop scientists. Refinement therefore requires strategic early stopping, which challenges assumptions of monotonic improvement. Criterion-level trajectories indicate a bias-variance trade-off. Early rounds lacked Specificity (bias), whereas excessive iteration eroded Conciseness and raised Cost Consideration through ungrounded economic reasoning (variance). The LLM judges overscored every criterion by 1.4-2.3 points but largely preserved the experts' ranking of rounds (Spearman $ρ$ = 0.58-0.90), so screened LLM judges can flag the quality peak despite unreliable absolute scores. Trustworthy agentic XAI also needs expert-anchored screening of LLM judges and transparent, verifiable refinement records.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
