English(EN) Structured Machine Theory of Mind from Agent Trajectories

新的SMToM框架通过显式信念和欲望实现可解释AI

作者 PulseAugur 编辑部 · [1 个来源] · 2026-11-06 05:00

研究人员开发了一个名为结构化心智理论（SMToM）的新框架，以创建更具可解释性的AI模型。SMToM在信念-欲望-意图（BDI）结构中显式地对智能体的信念和欲望进行建模，从而能够进行原则性的干预和反事实分析。当应用于行人导航领域时，由此产生的模型BDIBottleneck展示了改进的归因准确性以及根据改变的心智状态连贯地转移预测行为的能力。 AI

影响通过对智能体心智状态进行显式建模，增强了AI的可解释性，以便于理解和干预。

排序理由这是一篇详细介绍AI可解释性新框架和模型的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.LG 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 17 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 这是一篇详细介绍AI可解释性新框架和模型的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, model release; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.LG TIER_1 English(EN) · Nigel F. Doering, Rahath Malladi, Arshia Sangwan, M Tanjid Hasan Tonmoy, Jacob Doan, David Danks, Tauhidur Rahman · 2026-11-06 05:00

基于智能体轨迹的结构化心智理论

arXiv:2611.07208v1 Announce Type: new Abstract: Predictive models of human behavior trained on large-scale trajectory data optimize for statistical accuracy without representing the mental states that causally generate behavior. Such models support prediction but not principled i…

本文如何被排名

报道来源 [1]

基于智能体轨迹的结构化心智理论

相关实体

相关话题