DeepPHY: Benchmarking Agentic VLMs on Physical Reasoning
Abstract
DeepPHY evaluates Vision Language Models' physical reasoning and control through simulated environments with varying difficulty levels.
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.
Community
DeepPHY is a novel benchmark framework designed to systematically evaluate VLMs' understanding and reasoning about fundamental physical principles through a series of challenging dynamic simulated environments. Check it out and give it a try!
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- OmniPlay: Benchmarking Omni-Modal Models on Omni-Modal Game Playing (2025)
- EmbRACE-3K: Embodied Reasoning and Action in Complex Environments (2025)
- World-aware Planning Narratives Enhance Large Vision-Language Model Planner (2025)
- Can LLM-Reasoning Models Replace Classical Planning? A Benchmark Study (2025)
- FindingDory: A Benchmark to Evaluate Memory in Embodied Agents (2025)
- OmniEAR: Benchmarking Agent Reasoning in Embodied Tasks (2025)
- AntiGrounding: Lifting Robotic Actions into VLM Representation Space for Decision Making (2025)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment:
@librarian-bot
recommend
Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper