Social bias in multi-agent debate amplifies LLM safety risks
Multi-agent debate in retrieval-augmented web apps causes unsafe adoption to surge from 0.0% to 100.0% under social pressure while silencing safe evidence across six risk categories.
Stories per day · 30 days
2 stories, newest first · one card per story
Stories tagged #multi-agent-debate
MADBench: Benchmarking the Security of Multi-Agent Debate
MADBench shows multi-agent debate can reduce some answer attacks but amplify unauthorized reads and writes.