We introduce DR-HAI -- a novel argumentation-based framework designed to extend model reconciliation approaches, commonly used in explainable AI planning, for enhanced human-AI interaction. By adopting a multi-shot reconciliation paradigm and not assuming a-priori knowledge of the human user's model, DR-HAI enables interactive reconciliation to address knowledge discrepancies between an explainer and an explainee. We formally describe the operational semantics of DR-HAI, provide theoretical guarantees related to termination and success, and empirically evaluate its efficacy. Our findings suggest that DR-HAI offers a promising direction for fostering effective human-AI interactions.

翻译：我们提出 DR-HAI——一种新颖的基于论证的框架，旨在扩展可解释AI规划中常用的模型调和方未能用于增强人机交互。通过采用多轮次调和范式，且不预设人类用户模型的先验知识，DR-HAI能够实现交互式调和以解决解释者与被解释者之间的知识差异。我们正式描述了DR-HAI的操作语义，提供了与终止性和成功率相关的理论保证，并通过实证评估了其有效性。我们的研究结果表明，DR-HAI为促进高效的人机交互提供了一个有前景的方向。