cs.AINov 17, 2026

PhysScope: Agentic Multimodal Physics Reasoning with Grounded Visual Memory

Authors: Haoyang Liu, Kecheng Liang, Xinyu Li, Weixing Chen, Yang Liu

Abstract

Vision-language models (VLMs) can correctly interpret physics diagrams yet apply constraints outside the states or conditions in which they hold, causing premise errors to propagate through subsequent calculations. We introduce PhysScope, an inference-time visual harness that supports self-correction of these scope mismatches without updating model weights. PhysScope enables the model to link physical scopes directly to its visual observations and explicitly constructs derived views to support reasoning. The harness imposes explicit constraints on state distinctions, conditions, and physical scopes during model reasoning, and checks agent-proposed revisions against sources and scopes. Accepted revisions invalidate registered dependents, thereby maintaining scope-aware working memory. On PhysAlign, PhysScope achieves higher solving scores than direct solving across all six evaluated VLMs. With Gemini-3.8-flash, it outperforms Canvas-CoT by 9.34 percentage points and substantially improves solving accuracy on the out-of-distribution (OOD) PhysUniBench benchmark. Ablation studies support explicit scope management and dependency maintenance as design principles for multimodal physics reasoning agents.

Figures & tables

Appendix figures & tables14 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Decoupled Physical Modeling and Execution for Physics Reasoning

    Aug 22, 2026Ye Zhang, Xuehang Guo, Rui Pan +4Physical ReasoningVLM Reasoning

  2. PhysNote: Self-Knowledge Notes for Evolvable Physical Reasoning in Vision-Language Model

    Apr 27, 2026Sinin Zhang, Yunfei Xie, Yuxuan Cheng +2Vision-Language ModelsVLM Reasoning

  3. PhysMind: From Video to Executable Worlds for Training-Free Physical Reasoning

    Aug 5, 2026Chen Yang, Shenxiang Zeng, Haoyang Zhao +6Counterfactual ReasoningPhysical Reasoning in Video