返回全部动态
多智能体序贯决策中的责任归因：人类判断与形式化模型的比较
原标题：Responsibility in Multi-Agent Sequential Decision-Making: Comparing Human Judgments to Formal Models of Causal Attribution
AI 摘要
该研究通过大规模调查，比较了多智能体序贯决策中人类对责任判断与基于实际因果性的形式化责任归因模型的一致性。研究发现，没有任何单一的责任归因方法能始终与人类判断一致，但识别出影响人类责任判断的关键因素，包括智能体特定偏见和决策时可用信息量。
以上摘要由 AI 生成，可能存在误差。事实请以原文为准。
正文节选
Computer Science > Multiagent Systems Title:Responsibility in Multi-Agent Sequential Decision-Making: Comparing Human Judgments to Formal Models of Causal Attribution View PDF HTML (experimental) Abstract:With the growing adoption of artificial intelligence in high-stakes decision-making, identifying the causes of outcomes--particularly failures--and determining who is responsible has become a critical concern. In this work, we examine how well formal definitions of \textit{responsib
发布时间：2026-08-06 12:00
抓取时间：2026-08-06 21:18
来源机构：arXiv