Agentic Real2Sim: Physics-based World Modeling with Vision-Language Agents

• URL: http://arxiv.org/abs/2607.19190v3
• Date: Fri, 24 Jul 2026 08:16:46 GMT
• Title: Agentic Real2Sim: Physics-based World Modeling with Vision-Language Agents
• Abstract summary: We introduce textitAgentic Real2Sim, a framework for generalized physical world modeling with vision-language agents.<n>We evaluate Agentic Real2Sim on rigid-object manipulation, deformable-object interaction, and humanoid motion scenes.<n>The framework's agentic decisions can be driven by an open-weight VLM backend at a small fraction of the cost of frontier models.
• Score: 42.18672329354181
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Real-to-sim conversion for robotic interaction with objects remains labor-intensive because it requires more than visual reconstruction: a streamlined real2sim process must recover scene geometries and object states, infer physical parameters, and assemble actors, objects, cameras, poses, and trajectories into a runnable physical simulation. Today this process still depends on manual tuning of visual foundation models, mesh cleanup, coordinate-frame alignment, and brittle workflow glue across visual perception tools and simulators. We introduce \textit{Agentic Real2Sim}, a framework for generalized physical world modeling with vision-language agents, converting a real-world recording of object-robot interaction into a simulatable episodic twin which preserves observations, geometries, robot interactions, and object states. We evaluate Agentic Real2Sim on rigid-object manipulation, deformable-object interaction, and humanoid motion scenes, spanning domains that are usually handled by separate Real2Sim pipelines, marking a first step toward scalable conversion. The framework's agentic decisions can be driven by an open-weight VLM backend at a small fraction of the cost of frontier models, while attaining comparable conversion success rate. We aim to use the resulting real-world-aligned twins for downstream robotics tasks, specifically policy learning and evaluation. The project site is available at https://agentic-real2sim.github.io/.

Related papers

• RoboSnap: One-Shot Real-to-Sim Scene Generation for Generalizable Robot Learning and Evaluation [55.07260698542592]
  We present RoboSnap, a real-to-sim framework that turns a single RGB image into a simulation-ready scene.<n>Experiments on DROID scenes and real-robot tasks show that RoboSnap achieves reliable trajectory replay in the recovered scenes.<n>To further support real-to-sim research, we introduce DROID-Sim, a real-to-sim companion dataset constructed from 564 real-world scenes in DROID.
  arXiv  Detail & Related papers  (2026-07-07T18:19:10Z)
• ArtiTwinSplat: Interactable Digital Twin Reconstruction via Gaussian Splatting from RGB-D videos [47.4010297818512]
  ArtiTwinSplat is a framework that automatically constructs articulated, photo-realistic digital twins of objects from RGB-D videos.<n>Our method is built on 3D Gaussian Splatting that preserve geometric fidelity and photometric realism.
  arXiv  Detail & Related papers  (2026-06-23T14:24:07Z)
• GenHOI: Contact-Aware Humanoid-Object Interaction by Imitating Generated Videos without Task-Specific Training [20.414478780328437]
  Existing methods often require time-consuming task-specific policy training or rely on rigid trajectory replay.<n>We present textitGenHOI, a framework that enables humanoid robots to perform diverse object-interaction tasks in a zero-shot manner.<n>We validate the proposed framework in extensive simulation and real-world experiments across diverse object-interaction tasks.
  arXiv  Detail & Related papers  (2026-06-11T07:31:05Z)
• OASIS: From Simulation Data Collection to Real-World Humanoid Loco-Manipulation [51.37436817948304]
  OASIS is a simulation-data-driven framework for humanoid loco-manipulation.<n>It reconstructs realistic object assets from real-world images using a 3D generative model.<n>Under zero-shot deployment, it achieves higher success rates on most tasks than that trained on real-robot teleoperation data.
  arXiv  Detail & Related papers  (2026-06-07T10:01:53Z)
• GRAIL: Generating Humanoid Loco-Manipulation from 3D Assets and Video Priors [113.71148915419246]
  We present GRAIL, a digital generation pipeline that composes 3D assets, simulator-ready scenes, and priors from video foundation models (VFMs) to synthesize interactions without rebuilding physical environments or teleoperating the robot.<n>GRAIL starts from fully specified 3D configurations in which object geometry, camera parameters, metric scale, environment depth, and a robot-proportioned character are known before video generation and reused during reconstruction.<n>We retarget the recovered motions to a humanoid robot and train complementary task-general morphology trackers.<n>GRAIL produces over 20,000 sequences spanning pick-up, object manipulation, sitting
  arXiv  Detail & Related papers  (2026-06-03T17:57:45Z)
• URDF-Anything+: Autoregressive Articulated 3D Models Generation for Physical Simulation [45.4820195450296]
  We present an end-to-end autoregressive framework that directly generates executable articulated object models from visual observations.<n>Building on this capability, we enable a new Real-Follow-Sim paradigm, where high-fidelity digital twins constructed from visual observations allow policies trained in simulation to transfer to real robots without online adaptation.
  arXiv  Detail & Related papers  (2026-03-14T16:23:44Z)
• SAGE: Scalable Agentic 3D Scene Generation for Embodied AI [67.43935343696982]
  Existing scene-generation systems often rely on rule-based or task-specific pipelines, yielding artifacts and physically invalid scenes.<n>We present SAGE, an agentic framework that, given a user-specified embodied task, understands the intent and automatically generates simulation-ready environments at scale.<n>The resulting environments are realistic, diverse, and directly deployable in modern simulators for policy training.
  arXiv  Detail & Related papers  (2026-02-10T18:59:55Z)
• Mirage2Matter: A Physically Grounded Gaussian World Model from Video [87.9732484393686]
  We present Simulate Anything, a graphics-driven world modeling and simulation framework.<n>Our approach reconstructs real-world environments into a photorealistic scene representation using 3D Gaussian Splatting (3DGS)<n>We then leverage generative models to recover a physically realistic representation and integrate it into a simulation environment via a precision calibration target.
  arXiv  Detail & Related papers  (2026-01-24T07:43:57Z)
• Real2Sim based on Active Perception with automatically VLM-generated Behavior Trees [41.21672421530866]
  This paper presents a Real2Sim framework that autonomously generates and executes Behavior Trees for task-specific physical interactions.<n>Given a high-level user request, an incomplete simulation description, and an RGB observation of the scene, a vision-language model performs multi-modal reasoning to identify relevant objects.<n>The resulting behavior is executed on a torque-controlled Franka Emika Panda, enabling compliant, contact-rich interactions for parameter estimation.
  arXiv  Detail & Related papers  (2026-01-13T11:28:46Z)
• Real-to-Sim Robot Policy Evaluation with Gaussian Splatting Simulation of Soft-Body Interactions [27.247431258140463]
  We present a real-to-sim policy evaluation framework that constructs soft-body digital twins from real-world videos.<n>We validate our approach on representative deformable manipulation tasks, including plush toy packing, rope routing, and T-block pushing.
  arXiv  Detail & Related papers  (2025-11-06T18:52:08Z)
• One-Shot Real-to-Sim via End-to-End Differentiable Simulation and Rendering [20.919046758279205]
  We introduce a novel rigid object representation that allows the joint identification of properties.<n>Our method employs a novel differentiable point-based geometry representation coupled with a grid-based appearance field.<n>We show that our method can learn both simulation- and rendering-ready world models from only one robot action sequence.
  arXiv  Detail & Related papers  (2024-11-29T21:02:02Z)
• GeoSim: Photorealistic Image Simulation with Geometry-Aware Composition [81.24107630746508]
  We present GeoSim, a geometry-aware image composition process that synthesizes novel urban driving scenes. We first build a diverse bank of 3D objects with both realistic geometry and appearance from sensor data. The resulting synthetic images are photorealistic, traffic-aware, and geometrically consistent, allowing image simulation to scale to complex use cases.
  arXiv  Detail & Related papers  (2021-01-16T23:00:33Z)

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.