Pith

open record

sign in

arxiv: 2508.05405 · v1 · pith:YW4VTQRL · submitted 2025-08-07 · cs.AI

DeepPHY: Benchmarking Agentic VLMs on Physical Reasoning

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:YW4VTQRLrecord.jsonopen to challenge →

classification cs.AI
keywords reasoningphysicalvlmsdeepphyenvironmentscomplexevaluationplanning
0
0 comments X
read the original abstract

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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Bridging Physical Reasoning and Task Generalization via Visual Action Outcome Reasoning Alignment

    cs.AI 2026-07 conditional novelty 6.0

    VAORA aligns VLM chain-of-thought reasoning with visual scene observations and post-action outcomes via structured symbolic rewards, achieving cross-task and cross-environment generalization on physical reasoning benchmarks.

  2. Agentic Physical AI toward a Domain-Specific Foundation Model for Nuclear Reactor Control

    cs.AI 2025-12 unverdicted novelty 5.0

    A compact language model trained on scaled synthetic nuclear reactor control data exhibits variance collapse and emergent concentration on a single actuation strategy driven by physical execution success.