WorldAuditBench: Interactive 3D World Auditing with Multimodal Agents
cs.AI
Submitted: 2026-09-30
Updated: 2026-09-30
Code: https://github.com/anomalyco/opencode
Project page: https://glitchbench.github.io
Sources
- Deriving and Evaluating a Detailed Taxonomy of Game Bugs
- AI2-THOR: An Interactive 3D Environment for Visual AI
- PAT3D: Physics-Augmented Text-to-3D Scene Generation
- VisualAgentBench: Towards Large Multimodal Models as Visual Foundation Agents
- FlySearch: Exploring how vision-language models explore
- UnrealCV: Connecting Computer Vision to Unreal Engine
- SimWorld: An Open-ended Realistic Simulator for Autonomous Agents in Physical and Social Worlds
- Habitat: A Platform for Embodied AI Research
- VideoGameQA-Bench: Evaluating Vision-Language Models for Video Game Quality Assurance
- We'll Fix It in Post: What Do Bug Fixes in Video Game Update Notes Tell Us?
- EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents
- Scaling Behavior Cloning Improves Causal Reasoning: An Open Model for Real-Time Video Game Playing
- Open-Ended Video Game Glitch Detection with Agentic Reasoning and Temporal Grounding
- UnrealZoo: Enriching Photo-realistic Virtual Worlds for Embodied AI
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems