PhysicsSolutionAgent: Towards Multimodal Explanations for Numerical Physics Problem Solving

TL;DR

PhysicsSolutionAgent (PSA) is an autonomous system that generates multimodal physics explanations through videos, using automated evaluation and iterative feedback to improve visual reasoning for complex physics problems.

Contribution

This work introduces PSA, a novel agent that creates physics explanation videos with automated quality assessment and feedback, advancing multimodal reasoning in physics education.

Findings

PSA achieves 100% video completion rate.

Automated scores average 3.8/5, indicating room for improvement.

Identifies key challenges in visual content generation and evaluation.

Abstract

Explaining numerical physics problems often requires more than text-based solutions; clear visual reasoning can substantially improve conceptual understanding. While large language models (LLMs) demonstrate strong performance on many physics questions in textual form, their ability to generate long, high-quality visual explanations remains insufficiently explored. In this work, we introduce PhysicsSolutionAgent (PSA), an autonomous agent that generates physics-problem explanation videos of up to six minutes using Manim animations. To evaluate the generated videos, we design an assessment pipeline that performs automated checks across 15 quantitative parameters and incorporates feedback from a vision-language model (VLM) to iteratively improve video quality. We evaluate PSA on 32 videos spanning numerical and theoretical physics problems. Our results reveal systematic differences in video quality depending on problem difficulty and whether the task is numerical or theoretical. Using GPT-5-mini, PSA achieves a 100% video-completion rate with an average automated score of 3.8/5. However, qualitative analysis and human inspection uncover both minor and major issues, including visual layout inconsistencies and errors in how visual content is interpreted during feedback. These findings expose key limitations in reliable Manim code generation and highlight broader challenges in multimodal reasoning and evaluation for visual explanations of numerical physics problems. Our work underscores the need for improved visual understanding, verification, and evaluation frameworks in future multimodal educational systems