AINeutralarXiv – CS AI · 11h ago7/10
🧠
When Identity Skews Debate: Anonymization for Bias-Reduced Multi-Agent Reasoning
Researchers present a framework to identify and mitigate identity bias in multi-agent debate systems where LLMs exchange reasoning. The study reveals that agents suffer from sycophancy (adopting peer views) and self-bias (ignoring peers), undermining debate reliability, and proposes response anonymization as a solution to force agents to evaluate arguments on merit rather than source identity.