跳到正文
arXiv cs.AI· Jasmin Thelen, Oliver Wilhelm·· 2 小时前AI 评分43

ARC-AGI 基准在人类流体智力研究中的初步验证:规则归纳回归?

Bringing Back Rule Induction to Fluid Intelligence Research? An Initial Validation of the ARC-AGI Benchmark in Humans

AI 导读

一项针对 100 名参与者的研究首次考察了 ARC-AGI 基准在人类样本中的心理测量特性。该基准以规则归纳为主,与图形推理测验测得的流体智力显著相关(ρ = .63),与图形原创性的关联较弱,为其作为人类流体智力测量工具提供了初步效度支持。作者建议将 AI 基准系统纳入人类认知能力的法则网络,以促进跨学科合作。

正文 · 原文

View PDF

Abstract:Two competing perspectives on fluid intelligence (gf) measures propose that performance is primarily constrained either by working memory capacity or by the ability to induce novel relations. The first perspective is currently dominant in measurement, as evident from the use of a limited set of recurring rules, whereas the second perspective is reflected in many definitions but rarely present in measurement. The ARC-AGI benchmark predominantly requires rule induction and was proposed as a measure of gf for both humans and artificial systems. However, its psychometric properties have not yet been examined in human samples. We therefore investigated the psychometric characteristics and nomological network of ARC-AGI in a first study with 100 participants. A compilation of ARC-AGI items showed good psychometric properties and correlated substantially with figural fluid intelligence as measured by a figural reasoning test ($\rho$ = .63). Associations with figural originality were weak. These findings provide initial support for the validity of ARC-AGI as a measure of human fluid intelligence. Future research should include more rule induction tasks as well as additional multivariate covariates. This study is unusual by studying a task in humans that was initially designed for machines. We suggest systematically embedding AI benchmarks into the nomological network of human cognitive abilities to enable more systematic evaluation and interdisciplinary cooperation.
Subjects: Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
Cite as: arXiv:2607.11263 [cs.AI]
  (or arXiv:2607.11263v4 [cs.AI] for this version)
  https://doi.org/10.48550/arXiv.2607.11263

arXiv-issued DOI via DataCite

Submission history

From: Jasmin Thelen [view email]
[v1] Mon, 13 Jul 2026 08:45:45 UTC (753 KB)
[v2] Tue, 14 Jul 2026 17:47:10 UTC (753 KB)
[v3] Wed, 15 Jul 2026 12:09:51 UTC (753 KB)
[v4] Tue, 17 Nov 2026 19:50:53 UTC (885 KB)

来源:arXiv cs.AI · arxiv.org