Human-Like Attention? A Psychophysical Comparison of Visual Search in Humans and MLLMs

Renchi Zhang; Joost C. F. de Winter; Dimitra Dodou; Harleigh C. Seyffert; Yke Bauke Eisma

cs.HCOct 4, 2026

Human-Like Attention? A Psychophysical Comparison of Visual Search in Humans and MLLMs

Authors: Renchi Zhang, Joost C. F. de Winter, Dimitra Dodou, Harleigh C. Seyffert, Yke Bauke Eisma

Organizations: Faculty of Mechanical Engineering, Delft University of Technology, Delft, The Netherlands

Abstract

Visual search is a fundamental cognitive ability. This study investigates whether Multimodal Large Language Models (MLLMs) exhibit human-like difficulty signatures in visual search tasks. We compared search performance of humans (n = 1,250) and MLLMs using identical 2D and 3D stimuli across different set sizes. Both groups showed efficient performance in feature searches, most clearly when the target had a unique color, but performance degradation in conjunction searches as set sizes increased. Additionally, we found strong correlations between human and MLLM error rates ( $ρ= 0.82$ ), which suggests that MLLMs are sensitive to similar objective complexities, such as stimulus heterogeneity. However, differences were found as well: whereas humans invested extra search time to respond accurately on target-absent trials, MLLMs exhibited extreme present/absent response biases in complex searches. We conclude that MLLMs replicate high-level human performance signatures, yet their underlying computations differ significantly.

Explore similar work

Do vision-language models search like humans? Reasoning tokens as a reaction-time analog in classic visual-search paradigms
Jun 23, 2026Farahnaz WickMultiple Vision Tasks Visual Perception
1Independent Researcher
BabyVision: Visual Reasoning Beyond Language
Jan 10, 2026Liang Chen, Weichu Xie, Yiyan Liang +27Recent Vision-Language Models Visual Reasoning
1UniPat AI · 6Peking University · 3Alibaba Group +8
VisLens: Single-Pass Interpretable Visual Search for Multimodal LLMs
Aug 31, 2026Jingyi He, Sanghwan Kim, Zeynep AkataMultiple Vision Tasks Recent Vision-Language Models
Technical University of Munich · Helmholtz Munich · Munich Center for Machine Learning

Jun 23, 2026, cs.AIJ/K move · Enter open · S save

Do vision-language models search like humans? Reasoning tokens as a reaction-time analog in classic visual-search paradigms

Farahnaz Wick

1Independent Researcher

Multiple Vision Tasks Visual Perception Psychology Asymmetry

Open paper AskPDF arXiv

Visual search has been one of the most productive paradigms in the study of visual attention: the way reaction time scales with the number of items distinguishes parallel, "pop-out" search from serial, attention-demanding search. I ask whether vision-language models (VLMs) exhibit the same behavioral signatures. I adapt four classic paradigms: feature versus conjunction search, spatial-configuration (T-vs-L) search, enumeration, and the tilted/vertical search asymmetry; and present them to current frontier and mid-tier models. Because a single model call has no reaction time, I use the number of reasoning ("thinking") tokens a model spends per trial as a within-model analog of search effort, and I compare against a large public human benchmark (Wolfe et al., 2010). The models reproduce several human signatures: feature search costs flat effort while conjunction effort climbs with set size; frontier models hold accuracy where mid-tier models collapse to chance; and a resolution control shows the conjunction cost is genuine search rather than difficulty resolving small shapes. They also diverge from humans in informative ways. The target-present effort slope exceeds the target-absent slope, reversing the human ordering; enumeration remains accurate where humans would lose count; and a reasoning model with adaptive deliberation declines to deliberate on detection tasks altogether, so that a single search expresses itself as an effort gradient in one model and as an accuracy cliff in another. I argue that psychophysical paradigms, applied behaviorally, are a sharp and inexpensive probe of machine visual cognition, and that the points of divergence are as informative as the points of agreement.

Abstract

Explore similar work

Do vision-language models search like humans? Reasoning tokens as a reaction-time analog in classic visual-search paradigms

BabyVision: Visual Reasoning Beyond Language

VisLens: Single-Pass Interpretable Visual Search for Multimodal LLMs