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

arXiv: https://arxiv.org/abs/2610.05463 · HTML: https://mlsanity.com/paper/2610.05463/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 68 references that are in the map.
- First posted on arXiv 4 Oct 2026.

## Builds on (most cited first, 27 of 27)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning](https://mlsanity.com/paper/1612.06890/) (2016)
- [A Survey on Multimodal Large Language Models](https://mlsanity.com/paper/2306.13549/) (2023)
- [Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting](https://mlsanity.com/paper/2310.11324/) (2023)
- [V*: Guided Visual Search as a Core Mechanism in Multimodal LLMs](https://mlsanity.com/paper/2312.14135/) (2023)
- [More Agents Is All You Need](https://mlsanity.com/paper/2402.05120/) (2024)
- [An Introduction to Vision-Language Modeling](https://mlsanity.com/paper/2405.17247/) (2024)
- [Vision language models are blind: Failing to translate detailed visual features into words](https://mlsanity.com/paper/2407.06581/) (2024)
- [The Butterfly Effect of Altering Prompts: How Small Changes and Jailbreaks Affect Large Language Model Performance](https://mlsanity.com/paper/2401.03729/) (2024)
- [Understanding the Limits of Vision Language Models Through the Lens of the Binding Problem](https://mlsanity.com/paper/2411.00238/) (2024)
- [Interleaved-Modal Chain-of-Thought](https://mlsanity.com/paper/2411.19488/) (2024)
- [Blending Is All You Need: Cheaper, Better Alternative to Trillion-Parameters LLM](https://mlsanity.com/paper/2401.02994/) (2024)
- [Exploring Perceptual Limitation of Multimodal Large Language Models](https://mlsanity.com/paper/2402.07384/) (2024)
- [KiVA: Kid-inspired Visual Analogies for Testing Large Multimodal Models](https://mlsanity.com/paper/2407.17773/) (2024)
- [Self-attention in Vision Transformers Performs Perceptual Grouping, Not Attention](https://mlsanity.com/paper/2303.01542/) (2023)
- [Vision-Language Models Struggle to Align Entities across Modalities](https://mlsanity.com/paper/2503.03854/) (2025)
- [Human Cognitive Benchmarks Reveal Foundational Visual Gaps in MLLMs](https://mlsanity.com/paper/2502.16435/) (2025)
- [Mixed Evidence for Gestalt Grouping in Deep Neural Networks](https://mlsanity.com/paper/2203.07302/) (2022)
- [Weaving Context Across Images: Improving Vision-Language Models through Focus-Centric Visual Chains](https://mlsanity.com/paper/2504.20199/) (2025)
- [The Geometry of Representational Failures in Vision Language Models](https://mlsanity.com/paper/2602.07025/) (2026)
- [Visual Language Models show widespread visual deficits on neuropsychological tests](https://mlsanity.com/paper/2504.10786/) (2025)
- [I Spy With My Model's Eye: Visual Search as a Behavioural Test for MLLMs](https://mlsanity.com/paper/2510.19678/) (2025)
- [Attention Alignment Between Humans and Vision-Language Models](https://mlsanity.com/paper/2606.17410/) (2026)
- [Do vision-language models search like humans? Reasoning tokens as a reaction-time analog in classic visual-search paradigms](https://mlsanity.com/paper/2606.25066/) (2026)

## Abstract (arXiv)

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.