GameWorld: Towards Standardized and Verifiable Evaluation of Multimodal Game Agents
- 15 September 2026
- book chapter
- Published by Springer Nature
- p. 41-59
Abstract
No abstract availableKeywords
All Related Versions
This publication has 15 references indexed in Scilit:
- V-MAGE: A Game Evaluation Framework for Assessing Vision-Centric Capabilities in Multimodal Large Language Models2026
- ShowUI: One Vision-Language-Action Model for GUI Visual Agent2025
- FlashAdventure: A Benchmark for GUI Agents Solving Full Story Arcs in Diverse Adventure Games2025
- Collab-Overcooked: Benchmarking and Evaluating Large Language Models as Collaborative Agents2025
- JARVIS-VLA: Post-Training Large-Scale Vision Language Models to Play Visual Games with Keyboards and Mouse2025
- AssistGUI: Task-Oriented PC Graphical User Interface Automation2024
- Human-level play in the game ofDiplomacyby combining language models with strategic reasoningScience, 2022
- MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge2022
- Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos2022
- TextWorld: A Learning Environment for Text-Based Games2019