# Visual Persuasion: What Influences Decisions of Vision-Language Models?

arXiv: https://arxiv.org/abs/2602.15278 · HTML: https://mlsanity.com/paper/2602.15278/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in VLM benchmarks and visual reasoning, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 33 of its 48 references that are in the map.
- First posted on arXiv 17 Feb 2026.

## Placed in

- Multimodal LLMs / vision-language models / [VLM benchmarks and visual reasoning](https://mlsanity.com/mllm/vlm-benchmarks-and-visual-reasoning/)

## Builds on (most cited first, 30 of 33)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [WebArena: A Realistic Web Environment for Building Autonomous Agents](https://mlsanity.com/paper/2307.13854/) (2023)
- [WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents](https://mlsanity.com/paper/2207.01206/) (2022)
- [Qwen-Image Technical Report](https://mlsanity.com/paper/2508.02324/) (2025)
- [Discovering Language Model Behaviors with Model-Written Evaluations](https://mlsanity.com/paper/2212.09251/) (2022)
- [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)
- [Automatic Prompt Optimization with "Gradient Descent" and Beam Search](https://mlsanity.com/paper/2305.03495/) (2023)
- [GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning](https://mlsanity.com/paper/2507.19457/) (2025)
- [U2-Net: Going Deeper with Nested U-Structure for Salient Object Detection](https://mlsanity.com/paper/2005.09007/) (2020)
- [ABO: Dataset and Benchmarks for Real-World 3D Object Understanding](https://mlsanity.com/paper/2110.06199/) (2021)
- [Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning](https://mlsanity.com/paper/2405.10292/) (2024)
- [StyleGAN-Human: A Data-Centric Odyssey of Human Generation](https://mlsanity.com/paper/2204.11823/) (2022)
- [Automatically Interpreting Millions of Features in Large Language Models](https://mlsanity.com/paper/2410.13928/) (2024)
- [Improving Text-to-Image Consistency via Automatic Prompt Optimization](https://mlsanity.com/paper/2403.17804/) (2024)
- [Understanding the Limits of Vision Language Models Through the Lens of the Binding Problem](https://mlsanity.com/paper/2411.00238/) (2024)
- [Adversarial Demonstration Attacks on Large Language Models](https://mlsanity.com/paper/2305.14950/) (2023)
- [VHELM: A Holistic Evaluation of Vision Language Models](https://mlsanity.com/paper/2410.07112/) (2024)
- [Feedback Descent: Open-Ended Text Optimization via Pairwise Comparison](https://mlsanity.com/paper/2511.07919/) (2025)
- [Bayesian Preference Elicitation with Language Models](https://mlsanity.com/paper/2403.05534/) (2024)
- [Can We Talk Models Into Seeing the World Differently?](https://mlsanity.com/paper/2403.09193/) (2024)
- [AI Hiring with LLMs: A Context-Aware and Explainable Multi-Agent Framework for Resume Screening](https://mlsanity.com/paper/2504.02870/) (2025)
- [Maestro: Self-Improving Text-to-Image Generation via Agent Orchestration](https://mlsanity.com/paper/2509.10704/) (2025)
- [House price estimation from visual and textual features](https://mlsanity.com/paper/1609.08399/) (2016)
- [How to Distinguish AI-Generated Images from Authentic Photographs](https://mlsanity.com/paper/2406.08651/) (2024)
- [A Framework for Studying AI Agent Behavior: Evidence from Consumer Choice Experiments](https://mlsanity.com/paper/2509.25609/) (2025)
- [Multimodal Prompt Optimization: Why Not Leverage Multiple Modalities for MLLMs](https://mlsanity.com/paper/2510.09201/) (2025)
- [Visual serial processing deficits explain divergences in human and VLM reasoning](https://mlsanity.com/paper/2509.25142/) (2025)

## Built on by (most cited first, 1 of 1)

- [Probing Perceptual Priors of MLLMs via Gibbs Sampling with Interpretable Generative Controls](https://mlsanity.com/paper/2608.27727/) (2026)

## Abstract (arXiv)

The web is littered with images, once created for human consumption and now increasingly interpreted by agents using vision-language models (VLMs). These agents make visual decisions at scale, deciding what to click, recommend, or buy. Yet, we know little about the structure of their visual preferences. We introduce a framework for studying this by placing VLMs in controlled image-based choice tasks and systematically perturbing their inputs. Our key idea is to treat the agent's decision function as a latent visual utility that can be inferred through revealed preference: choices between systematically edited images. Starting from common images, such as product photos, we propose methods for visual prompt optimization, adapting text optimization methods to iteratively propose and apply visually plausible modifications using an image generation model (such as in composition, lighting, or background). We then evaluate which edits increase selection probability. Through large-scale experiments on frontier VLMs, we demonstrate that optimized edits significantly shift choice probabilities in head-to-head comparisons. We develop an automatic interpretability pipeline to explain these preferences, identifying consistent visual themes that drive selection. We argue that this approach offers a practical and efficient way to surface visual vulnerabilities, safety concerns that might otherwise be discovered implicitly in the wild, supporting more proactive auditing and governance of image-based AI agents.