Summary of Wis Platform: Enhancing Evaluation Of Llm-based Multi-agent Systems Through Game-based Analysis, by Chengwei Hu et al.
WiS Platform: Enhancing Evaluation of LLM-Based Multi-Agent Systems Through Game-Based Analysis
by Chengwei Hu, Jianhui Zheng, Yancheng He, Hangyu Guo, Junguang Jiang, Han Zhu, Kai Sun, Yuning Jiang, Wenbo Su, Bo Zheng
First submitted to arxiv on: 4 Dec 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 This paper introduces an open, scalable, and real-time updated platform for evaluating and analyzing large language model (LLM)-based autonomous multi-agent systems (MAS). The platform, called Who is Spy?” (WiS), features a unified model evaluation interface that supports models available on Hugging Face, a real-time updated leaderboard for model evaluation, and comprehensive evaluations covering game-winning rates, attacking and defense strategies, and reasoning of LLMs. The authors conduct extensive experiments with various open- and closed-source LLMs, demonstrating the effectiveness and efficiency of their platform in evaluating LLM-based MAS. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper makes a special platform for testing big computer models that can work together to play games. These computer models are called “large language models” or LLMs. The platform is very useful because it helps us see how well these LLMs do when working together. It also shows which strategies they use to win or lose in the game. By using this platform, researchers can test different LLMs and learn more about what makes them good at playing games. |
Keywords
» Artificial intelligence » Large language model
