AI explanation methods often assume a static user model, producing non-adaptive explanations regardless of expert goals, reasoning strategies, or decision contexts. Knowledge graph-based explanations, despite their capacity for grounded, path-based reasoning, inherit this limitation. In complex domains such as scientific discovery, this assumption fails to capture the diversity of cognitive strategies and epistemic stances among experts, preventing explanations that foster deeper understanding and informed decision-making. However, the scarcity of human experts limits the use of direct human feedback to produce adaptive explanations. We present a reinforcement learning approach for scientific explanation generation that incorporates agentic personas, structured representations of expert reasoning strategies, that guide the explanation agent towards specific epistemic preferences. In an evaluation of knowledge graph-based explanations for drug discovery, we tested two personas that capture distinct epistemic stances derived from expert feedback. Results show that persona-driven explanations match state-of-the-art predictive performance while persona preferences closely align with those of their corresponding experts. Adaptive explanations were consistently preferred over non-adaptive baselines (n = 22), and persona-based training reduces feedback requirements by two orders of magnitude. These findings demonstrate how agentic personas enable scalable adaptive explainability for AI systems in complex and high-stakes domains.

翻译：AI解释方法通常假设用户模型是静态的，无论专家目标、推理策略或决策背景如何，都生成非自适应的解释。基于知识图谱的解释尽管具备基于路径的可靠推理能力，但仍继承了这一局限。在科学发现等复杂领域中，这一假设无法捕捉专家在认知策略和认知立场上的多样性，从而阻碍了能够促进深度理解和明智决策的解释生成。然而，人类专家的稀缺性限制了直接利用人类反馈来生成自适应解释的可能性。我们提出了一种基于强化学习的科学解释生成方法，该方法引入了智能体角色——即专家推理策略的结构化表征——以引导解释智能体朝着特定的认知偏好方向进行推理。在针对药物发现的知识图谱解释评估中，我们测试了两种捕捉源自专家反馈的不同认知立场的角色。结果表明，角色驱动的解释在保持与现有最优方法相当的预测性能的同时，其角色偏好与对应专家的偏好高度一致。自适应解释相较于非自适应基线（n=22）得到了持续性的偏好选择，而基于角色的训练将反馈需求降低了两个数量级。这些发现论证了智能体角色如何使AI系统在复杂且高风险领域实现可扩展的自适应可解释性。