Summary of Can Vlms Play Action Role-playing Games? Take Black Myth Wukong As a Study Case, by Peng Chen et al.
Can VLMs Play Action Role-Playing Games? Take Black Myth Wukong as a Study Case
by Peng Chen, Pi Bu, Jun Song, Yuan Gao, Bo Zheng
First submitted to arxiv on: 19 Sep 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: None
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper presents a novel approach to applying vision language models (VLMs) in action role-playing games (ARPGs), focusing on combat scenarios. The researchers select the game “Black Myth: Wukong” as a research platform and define 12 tasks within it, with 75% focused on combat. They incorporate several state-of-the-art VLMs into this benchmark and propose a novel framework called VARP, which consists of an action planning system and a visual trajectory system. The framework demonstrates the ability to perform basic tasks and succeed in 90% of easy and medium-level combat scenarios. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The researchers use large language models (LLMs) based agents to interact with video games using only visual inputs. They select “Black Myth: Wukong” as a research platform and define 12 tasks within it, including mouse and keyboard actions. The paper proposes a novel framework called VARP, which demonstrates the ability to perform basic tasks and succeed in combat scenarios. |
