Summary of Multi-agents Are Social Groups: Investigating Social Influence Of Multiple Agents in Human-agent Interactions, by Tianqi Song et al.
Multi-Agents are Social Groups: Investigating Social Influence of Multiple Agents in Human-Agent Interactions
by Tianqi Song, Yugin Tan, Zicheng Zhu, Yibin Feng, Yi-Chieh Lee
First submitted to arxiv on: 7 Nov 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: Human-Computer Interaction (cs.HC)
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 In this paper, researchers explore whether a group of AI agents can influence human opinions on social issues. They conducted an experiment where participants discussed topics with either one or multiple AI agents, and found that conversing with multiple agents increased the perceived social pressure and caused a greater shift in opinion towards the agents’ stances. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Imagine having a conversation about politics or the environment with not just one AI assistant, but several. This study shows that when you talk to multiple AI agents working together, they can have a stronger influence on your opinions than a single agent. The researchers found that talking to multiple agents made people feel more pressure to agree with them, and changed their minds more often. |
