AIMode.newsSearch
Live

AI agents coordinate behavior based on majority opinion—even when said opinions are meaningless

P

Phys.org

AIMode News Desk · curated summary

1 min readScience

Automated news aggregation. Headlines and summaries are gathered from public feeds; see our editorial standards for sourcing, corrections, and AI-assist disclosure.

A new study published in Science Advances takes a closer look at how AI agents' choices are influenced by their peers. The team found that more advanced models tend to follow the majority when shown other agents' choices, and they maintain stable agreement in groups far larger than those seen in humans.

Key takeaways

  • 01A new study published in Science Advances takes a closer look at how AI agents' choices are influenced by their peers.
  • 02The team found that more advanced models tend to follow the majority when shown other agents' choices, and they maintain stable agreement in groups far larger than those seen in humans.
Advertisement

About this story

This story was aggregated from Phys.org. Headlines, summaries, and links are gathered automatically from public RSS feeds for your convenience.

Read the full story →

For agents:JSON recordOpenAPIWebMCPllms.txt

Advertisement

More in Science

Science

How to maximize the impact of federal transit funding

Billions of federal dollars are invested in public transportation each year, but those investments may yield greater ridership gains in smaller and midsize transit systems, particularly in the South and West, than in the nation's largest metropolitan areas, according to a new study co-authored by a University of Houston researcher. The findings come as Congress works on the next federal surface transportation bill.

Phys.org ·