PhysCodeBench: Benchmarking Physics-Aware Symbolic Simulation of 3D Scenes via Self-Corrective Multi-Agent Refinement

• URL: http://arxiv.org/abs/2604.23580v1
• Date: Sun, 26 Apr 2026 07:37:20 GMT
• Title: PhysCodeBench: Benchmarking Physics-Aware Symbolic Simulation of 3D Scenes via Self-Corrective Multi-Agent Refinement
• Abstract summary: Physics-aware symbolic simulation of 3D scenes is critical for robotics, embodied AI, and scientific computing.<n>We introduce PhysCodeBench, the first comprehensive benchmark for evaluating physics-aware symbolic simulation.<n>Our evaluation framework measures both code executability and physical accuracy through automated and visual assessment.
• Score: 35.63080643326192
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Physics-aware symbolic simulation of 3D scenes is critical for robotics, embodied AI, and scientific computing, requiring models to understand natural language descriptions of physical phenomena and translate them into executable simulation environments. While large language models (LLMs) excel at general code generation, they struggle with the semantic gap between physical descriptions and simulation implementation. We introduce PhysCodeBench, the first comprehensive benchmark for evaluating physics-aware symbolic simulation, comprising 700 manually-crafted diverse samples across mechanics, fluid dynamics, and soft-body physics with expert annotations. Our evaluation framework measures both code executability and physical accuracy through automated and visual assessment. Building on this, we propose a Self-Corrective Multi-Agent Refinement Framework (SMRF) with three specialized agents (simulation generator, error corrector, and simulation refiner) that collaborate iteratively with domain-specific validation to produce physically accurate simulations. SMRF achieves 67.7 points overall performance compared to 36.3 points for the best baseline among evaluated SOTA models, representing a 31.4-point improvement. Our analysis demonstrates that error correction is critical for accurate physics-aware symbolic simulation and that specialized multi-agent approaches significantly outperform single-agent methods across the tested physical domains.

Related papers

• GAUGE: A Measurement-Grounded Benchmark for Physical Fidelity in Simulation Engines and Video World Models [66.77745044586173]
  GAUGE is a real-world-grounded diagnostic benchmark for evaluating how numerical simulators and generative video world models reproduce or deviate from real-world physics.<n>We benchmark Isaac Sim, Genesis, and Newton on 14 task families using generalized trajectory errors, and evaluate 6 image-to-video models on 5 rigid-body tasks.<n>Our results reveal no uniformly faithful physics engine, with the largest discrepancies arising in impulsive contact, rapid textile motion, and volumetric deformation.
  arXiv  Detail & Related papers  (2026-08-06T12:19:38Z)
• PhysAgent: Reflective Agentic Physics Control for Physically Plausible Video Generation [68.13035350819901]
  PhysAgent is a framework that closes the loop among physical program generation, physics simulation, stage-specific verification, and targeted program repair.<n>Our framework produces more physically plausible videos, achieves better prompt alignment, and generalizes more effectively across diverse physical scenarios.
  arXiv  Detail & Related papers  (2026-07-17T08:55:09Z)
• Coding Agent Is Good As World Simulator [5.161736405778465]
  We present an agentic framework constructing physics-based world models through executable simulation code.<n>The framework coordinates planning, code generation, visual review, and physics analysis agents.<n> Experimental results show that our framework outperforms advanced video-based models in physical accuracy, instruction fidelity and visual quality.
  arXiv  Detail & Related papers  (2026-05-14T05:33:41Z)
• PhyCo: Learning Controllable Physical Priors for Generative Motion [55.59209981836171]
  We present PhyCo, a framework that introduces continuous, interpretable, and physically grounded control into video generation.<n>Our approach integrates three key components: (i) a large-scale dataset of over 100K photorealistic simulation videos where friction, restitution, deformation, and force are systematically varied across diverse scenarios; (ii) physics-supervised fine-tuning of a pretrained diffusion model using a ControlNet conditioned on pixel-aligned physical property maps; and (iii) VLM-guided reward optimization, where a fine-tuned vision-language model evaluates generated videos with targeted physics queries and provides differentiable feedback.
  arXiv  Detail & Related papers  (2026-04-30T17:53:03Z)
• Perceptual Self-Reflection in Agentic Physics Simulation Code Generation [0.0]
  We present a framework for generating physics simulation code from natural language descriptions.<n>Key innovation is perceptual validation, which analyzes rendered animation frames using a vision-capable language model.<n>We evaluate the system across seven domains including classical mechanics, fluid dynamics, thermodynamics, electromagnetics, wave physics, reaction-diffusion systems, and non-physics data visualization.
  arXiv  Detail & Related papers  (2026-02-12T15:48:33Z)
• SimuScene: Training and Benchmarking Code Generation to Simulate Physical Scenarios [71.65387146697319]
  Large language models (LLMs) have been extensively studied for tasks like math competitions, complex coding, and scientific reasoning.<n>We propose SimuScene, the first systematic study that trains and evaluates LLMs on simulating physical scenarios.<n>We build an automatic pipeline to collect data, with human verification to ensure quality.
  arXiv  Detail & Related papers  (2026-02-11T13:26:02Z)
• URDF-Anything: Constructing Articulated Objects with 3D Multimodal Language Model [76.08429266631823]
  We propose an end-to-end automatic reconstruction framework based on a 3D multimodal large language model (MLLM)<n>URDF-Anything utilizes an autoregressive prediction framework based on point-cloud and text multimodal input to jointly optimize geometric segmentation and kinematic parameter prediction.<n> Experiments on both simulated and real-world datasets demonstrate that our method significantly outperforms existing approaches.
  arXiv  Detail & Related papers  (2025-11-02T13:45:51Z)
• Scan, Materialize, Simulate: A Generalizable Framework for Physically Grounded Robot Planning [16.193477346643295]
  Scan, Materialize, Simulate (SMS) is a unified framework that combines 3D Gaussian Splatting for accurate scene reconstruction, visual foundation models for semantic segmentation, vision-language models for material property inference, and physics simulation for reliable prediction of action outcomes.<n>Our results highlight the potential of bridging differentiable rendering for scene reconstruction, foundation models for semantic understanding, and physics-based simulation to achieve physically grounded robot planning across diverse settings.
  arXiv  Detail & Related papers  (2025-05-20T21:55:01Z)
• GausSim: Foreseeing Reality by Gaussian Simulator for Elastic Objects [55.02281855589641]
  GausSim is a novel neural network-based simulator designed to capture the dynamic behaviors of real-world elastic objects represented through Gaussian kernels.<n>We leverage continuum mechanics and treat each kernel as a Center of Mass System (CMS) that represents continuous piece of matter.<n>In addition, GausSim incorporates explicit physics constraints, such as mass and momentum conservation, ensuring interpretable results and robust, physically plausible simulations.
  arXiv  Detail & Related papers  (2024-12-23T18:58:17Z)
• GaussianProperty: Integrating Physical Properties to 3D Gaussians with LMMs [21.3615403516602]
  Estimating physical properties for visual data is a crucial task in computer vision, graphics, and robotics.<n>We introduce GaussianProperty, a training-free framework that assigns physical properties of materials to 3D Gaussians.<n>We demonstrate that 3D Gaussians with physical property annotations enable applications in physics-based dynamic simulation and robotic grasping.
  arXiv  Detail & Related papers  (2024-12-15T17:44:10Z)
• Efficient Physics Simulation for 3D Scenes via MLLM-Guided Gaussian Splatting [32.846428862045634]
  We present Sim Anything, a physics-based approach that endows static 3D objects with interactive dynamics.<n>Inspired by human visual reasoning, we propose MLLM-based Physical Property Perception.<n>We also simulate objects in an open-world scene with particles sampled via the Physical-Geometric Adaptive Sampling.
  arXiv  Detail & Related papers  (2024-11-19T12:52:21Z)
• DeepSimHO: Stable Pose Estimation for Hand-Object Interaction via Physics Simulation [81.11585774044848]
  We present DeepSimHO, a novel deep-learning pipeline that combines forward physics simulation and backward gradient approximation with a neural network. Our method noticeably improves the stability of the estimation and achieves superior efficiency over test-time optimization.
  arXiv  Detail & Related papers  (2023-10-11T05:34:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.