Summary of Enhance Reasoning For Large Language Models in the Game Werewolf, by Shuang Wu et al.
Enhance Reasoning for Large Language Models in the Game Werewolf
by Shuang Wu, Liwen Zhu, Tao Yang, Shiwei Xu, Qiang Fu, Yang Wei, Haobo Fu
First submitted to arxiv on: 4 Feb 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: Computation and Language (cs.CL)
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 proposed framework combines Large Language Models (LLMs) with an external Thinker module to improve the reasoning capabilities of LLM-based agents. The Thinker module utilizes knowledge from databases and optimization techniques, whereas LLMs handle natural language processing tasks. The framework is demonstrated through a 9-player Werewolf game that requires dual-system reasoning. The Thinker module is trained using data from human sessions and reinforcement learning. Experiments show the effectiveness of the framework in deductive reasoning, speech generation, and online game evaluation. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper shows how to make computers think better by combining two types of artificial intelligence: Large Language Models (LLMs) and a special module called Thinker. The Thinker uses information from databases and gets smarter over time. This combination allows the computer to do tasks that require complex thinking, like playing games or generating speech. The researchers tested this idea with a game called Werewolf and showed it works well. They also trained a large language model to outperform another popular AI model. |
Keywords
* Artificial intelligence * Large language model * Natural language processing * Optimization * Reinforcement learning
