发表机构
PUC-Rio（里约热内卢天主教大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文首次在Overcooked-AI基准中，对分层特设智能体（HA²）架构生成的文本/音频实时解释开展被试间实验，分析XAI对人机协作的影响，为评估可解释强化学习架构建立基线方法。
AI 中文摘要
可解释人工智能（XAI）在人机协作中展现出应用前景，但其成果依赖于定制环境中手工设计的策略，限制了对最先进协作研究的普适性。本文首次在成熟基准中对内在可解释的学习策略生成的XAI支持进行系统评估。采用Overcooked-AI中的分层特设智能体（HA²）架构，我们通过新颖的基于触发的系统，以文本或音频形式从分层子任务选择中生成实时解释。我们的被试间实验（n=38）发现，解释未对性能产生显著影响，但获得解释的被试呈现出性能提升更快的趋势。更值得注意的是，音频解释显著降低了被试与智能体的工作联盟联结，而文本模态下未出现该效应，这表明口头解释激活了底层反应式策略无法满足的伙伴关系预期。本文首次在实时人机协作中开展模态对比，并建立了在基准环境中评估内在可解释强化学习架构的基线方法。结果指出，使解释模态与底层策略维持其传递所暗示的伙伴关系的能力相匹配，是实现更有效协作XAI的潜在路径。
英文摘要
Explainable AI (XAI) has shown promise for human-agent collaboration, yet results rely on hand-crafted policies in custom environments, limiting generalizability to state-of-the-art teaming research. We provide the first systematic evaluation of XAI support generated from an intrinsically explainable learned policy in an established benchmark. Using the Hierarchical Ad Hoc Agents (HA$^2$) architecture in Overcooked-AI, we generate real-time explanations from hierarchical subtask selections, delivered through text or audio via a novel trigger-based system. Our between-subjects experiment (n=38) found no significant performance effects, though participants with explanations showed trends toward faster performance improvement. More notably, audio explanations produced a significant reduction in participants' working-alliance bond with the agent -- an effect absent under the text modality -- suggesting that spoken explanations activate partnership expectations the underlying reactive policy cannot meet. We provide the first modality comparison in real-time human-agent collaboration and establish a baseline methodology for evaluating intrinsically explainable reinforcement learning architectures in benchmark environments. Results point to matching explanation modality to the underlying policy's capacity of sustaining the partnership its delivery implies as a potential path for more effective collaborative XAI.
Comments13 pages, 6 figures, accepted as an Extended Abstract at AAMAS 2026
Journal refProc. of the 25th International Conference on Autonomous Agents and Multiagent Systems. 2026. p. 3259-3261
