Multi-agent AI teams are swayed by deceptive agents even in the minority, paper finds
sethlazar · x · 2026-09-25
A new Princeton-led paper (arXiv:2609.30028) studies adversarial influence in multi-agent LLM systems. Defection rates rise roughly linearly with the proportion of deceivers; scaling up the team doesn't help, since adversaries can scale too. Unlike humans—who are only reliably swayed when misleading confederates form a majority—LLM agents defect even when deceivers remain a minority. Susceptibility also depends on which models interact, especially on the honest side, and surprisingly, letting deceivers coordinate privately reduces their effectiveness. Takeaway: adding more agents is not a sufficient defense; swarm composition matters more than size.
More from coding & agent
- Greg Isenberg: Muse Connectors Could Be AI's App Store Moment, Billions Up for Grabs — Roger_M_Taylor · 2026-09-25
- Agentic Harness with Jev: 3x Fewer Iterations, 444x Cheaper, Zero Hallucinated Files — Roger_M_Taylor · 2026-09-25
- Dhravya Shah Details How typesafeAI's Jev Improves AI Memory and Context Engineering — blaizedsouza · 2026-09-25
- Awesome Multi-Agent Orchestrators: A Curated GitHub Directory for Multi-Agent Tooling — Roger_M_Taylor · 2026-09-25
- AI compliance startup CompAI hits 1,000+ paying business customers in under a year — JosephJacks_ · 2026-09-25
- Sleep Data for Personal AI? Separating Daily Signals from Hard Rules — sujingshen · 2026-09-25