DeepPHY: Benchmarking Agentic VLMs on Physical Reasoning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xu, Xinrun, Bu, Pi, Wang, Ye, Karlsson, Börje F., Wang, Ziming, Song, Tengtao, Zhu, Qi, Song, Jun, Ding, Zhiming, Zheng, Bo
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918117247025152
author Xu, Xinrun
Bu, Pi
Wang, Ye
Karlsson, Börje F.
Wang, Ziming
Song, Tengtao
Zhu, Qi
Song, Jun
Ding, Zhiming
Zheng, Bo
author_facet Xu, Xinrun
Bu, Pi
Wang, Ye
Karlsson, Börje F.
Wang, Ziming
Song, Tengtao
Zhu, Qi
Song, Jun
Ding, Zhiming
Zheng, Bo
contents Although Vision Language Models (VLMs) exhibit strong perceptual abilities and impressive visual reasoning, they struggle with attention to detail and precise action planning in complex, dynamic environments, leading to subpar performance. Real-world tasks typically require complex interactions, advanced spatial reasoning, long-term planning, and continuous strategy refinement, usually necessitating understanding the physics rules of the target scenario. However, evaluating these capabilities in real-world scenarios is often prohibitively expensive. To bridge this gap, we introduce DeepPHY, a novel benchmark framework designed to systematically evaluate VLMs' understanding and reasoning about fundamental physical principles through a series of challenging simulated environments. DeepPHY integrates multiple physical reasoning environments of varying difficulty levels and incorporates fine-grained evaluation metrics. Our evaluation finds that even state-of-the-art VLMs struggle to translate descriptive physical knowledge into precise, predictive control.
format Preprint
id arxiv_https___arxiv_org_abs_2508_05405
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DeepPHY: Benchmarking Agentic VLMs on Physical Reasoning
Xu, Xinrun
Bu, Pi
Wang, Ye
Karlsson, Börje F.
Wang, Ziming
Song, Tengtao
Zhu, Qi
Song, Jun
Ding, Zhiming
Zheng, Bo
Artificial Intelligence
Although Vision Language Models (VLMs) exhibit strong perceptual abilities and impressive visual reasoning, they struggle with attention to detail and precise action planning in complex, dynamic environments, leading to subpar performance. Real-world tasks typically require complex interactions, advanced spatial reasoning, long-term planning, and continuous strategy refinement, usually necessitating understanding the physics rules of the target scenario. However, evaluating these capabilities in real-world scenarios is often prohibitively expensive. To bridge this gap, we introduce DeepPHY, a novel benchmark framework designed to systematically evaluate VLMs' understanding and reasoning about fundamental physical principles through a series of challenging simulated environments. DeepPHY integrates multiple physical reasoning environments of varying difficulty levels and incorporates fine-grained evaluation metrics. Our evaluation finds that even state-of-the-art VLMs struggle to translate descriptive physical knowledge into precise, predictive control.
title DeepPHY: Benchmarking Agentic VLMs on Physical Reasoning
topic Artificial Intelligence
url https://arxiv.org/abs/2508.05405