English(EN) From Belief Inference to Task Action: A Multi-Level Evaluation of Theory of Mind on Verifiable Tasks

新评估将人工智能心智理论与任务表现联系起来

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-27 04:00

引入了一个新的评估框架，用于评估语言模型的心智理论（ToM），该框架超越了简单的推理问题，转向可验证的任务。该框架测试了模型在协作场景中利用推断出的信念来做出决策和执行行动的能力。对 Claude 和 Qwen-27B 等模型的实验揭示了信念推理能力与实际任务表现之间的差异，突显了需要进行能够将心智状态理解与切实成果联系起来的评估。 AI

影响这项研究提出了一种更强大的方法来评估人工智能理解和基于推断出的信念采取行动的能力，这对于未来协作式人工智能系统至关重要。

排序理由学术论文，介绍了一种新的人工智能评估方法。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CL 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: 10 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 学术论文，介绍了一种新的人工智能评估方法。[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, safety; 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: Same-day; Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.CL TIER_1 English(EN) · Zhenshuai Yin, Yongxin Guo, Mingda Zhang, Zhongze Luo, Haoyue Liu, Lianmin Zhang, Xiaoying Tang · 2026-10-27 04:00

从信念推理到任务行动：可验证任务上心智理论的多层次评估

arXiv:2610.34759v1 Announce Type: new Abstract: Effective collaboration requires language models to understand what others know and believe, and to act accordingly. Models that assume others share their information may omit necessary communication and undermine coordination. Many…

本文如何被排名

报道来源 [1]

从信念推理到任务行动：可验证任务上心智理论的多层次评估

相关实体

相关话题