# RoboGaze: Evaluating Robot World Models via Structured Vision-Language Analysis

arXiv: https://arxiv.org/abs/2606.28385 · HTML: https://mlsanity.com/paper/2606.28385/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Embodied and robot world models, one of 11 directions in World models.
- Builds on 30 of its 49 references that are in the map.
- First posted on arXiv 22 Jun 2026.

## Placed in

- World models / [Embodied and robot world models](https://mlsanity.com/wm/embodied-and-robot-world-models/)

## Builds on (most cited first, 30 of 30)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency](https://mlsanity.com/paper/2508.18265/) (2025)
- [Towards Accurate Generative Models of Video: A New Metric & Challenges](https://mlsanity.com/paper/1812.01717/) (2018)
- [OpenAI GPT-5 System Card](https://mlsanity.com/paper/2601.03267/) (2025)
- [Gemma: Open Models Based on Gemini Research and Technology](https://mlsanity.com/paper/2403.08295/) (2024)
- [WorldSimBench: Towards Video Generation Models as World Simulators](https://mlsanity.com/paper/2410.18072/) (2024)
- [Gemini: A Family of Highly Capable Multimodal Models](https://mlsanity.com/paper/2312.11805/) (2023)
- [DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset](https://mlsanity.com/paper/2403.12945/) (2024)
- [GAIA-1: A Generative World Model for Autonomous Driving](https://mlsanity.com/paper/2309.17080/) (2023)
- [VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness](https://mlsanity.com/paper/2503.21755/) (2025)
- [World Simulation with Video Foundation Models for Physical AI](https://mlsanity.com/paper/2511.00062/) (2025)
- [Ctrl-World: A Controllable Generative World Model for Robot Manipulation](https://mlsanity.com/paper/2510.10125/) (2025)
- [Cosmos 3: Omnimodal World Models for Physical AI](https://mlsanity.com/paper/2606.02800/) (2026)
- [DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos](https://mlsanity.com/paper/2602.06949/) (2026)
- [Evaluating Newtonian Mechanics in Video Generative Models with Real Physical Systems](https://mlsanity.com/paper/2504.02918/) (2025)
- [VCR-Bench: A Comprehensive Evaluation Framework for Video Chain-of-Thought Reasoning](https://mlsanity.com/paper/2504.07956/) (2025)
- [VideoScore2: Think before You Score in Generative Video Evaluation](https://mlsanity.com/paper/2509.22799/) (2025)
- [World-VLA-Loop: Closed-Loop Learning of Video World Model and VLA Policy](https://mlsanity.com/paper/2602.06508/) (2026)
- [PAI-Bench: A Comprehensive Benchmark For Physical AI](https://mlsanity.com/paper/2512.01989/) (2025)
- [Rethinking Video Generation Model for the Embodied World](https://mlsanity.com/paper/2601.15282/) (2026)
- [VideoGen-Eval: Agent-based System for Video Generation Evaluation](https://mlsanity.com/paper/2503.23452/) (2025)
- [RoboWM-Bench: A Benchmark for Evaluating World Models in Robotic Manipulation](https://mlsanity.com/paper/2604.19092/) (2026)
- [Physion-Eval: Evaluating Physical Realism in Generated Video via Human Reasoning](https://mlsanity.com/paper/2603.19607/) (2026)
- [Clutter-Robust Vision-Language-Action Models through Object-Centric and Geometry Grounding](https://mlsanity.com/paper/2512.22519/) (2025)
- [WorldJen: An End-to-End Multi-Dimensional Benchmark for Generative Video Models](https://mlsanity.com/paper/2605.03475/) (2026)
- [Open-Ended Video Game Glitch Detection with Agentic Reasoning and Temporal Grounding](https://mlsanity.com/paper/2604.07818/) (2026)
- [Self-Improving VLA Policies: Selected Diffusion Noise for Spurious-Robust Action Smoothing](https://mlsanity.com/paper/2606.14084/) (2026)

## Built on by (most cited first, 1 of 1)

- [PhysicsLENS: Diagnosing Physical Property Blindness in Video Generation Models](https://mlsanity.com/paper/2610.01162/) (2026)

## Abstract (arXiv)

Robot world models now generate synthetic manipulation videos, but evaluating them is hard: realistic-looking outputs often violate physical laws, temporal consistency or task logic, while conventional metrics and monolithic Vision-Language Model (VLM) judges return scores that do not say what failed. We present RoboGaze, a training-free multi-agent VLM evaluator that grounds the task and scene, routes each subtask to dimension-specific specialists and verifies their findings with a critic, producing temporally localized diagnostic reports that state what failed, when, why and how severely, under a schema of 6 dimensions and 30 failure types whose annotation reliability and coverage we measure. To benchmark it, we introduce RoboGazeBench, 914 human-annotated clips from five generators, conditioned on simulated and real-world data and running from 4.9 to 148.9 s. Across eight open-source and proprietary VLM backbones, RoboGaze outperforms every baseline; even a published agentic detector given the same schema and a slightly larger inference budget trails it by 10.1-12.3 description-F1 points, a margin that blinded human raters confirm. On the strongest backbone it closes 83% of the gap between chain-of-thought prompting and human agreement, and its critic curbs the "cry-wolf" false positives of standard VLMs, lifting mean clean-clip accuracy from 17% to 85%. The advantage is largest on held-out generators and long clips, and carries over to selecting generated demonstrations (80% vs. 71% precision).