RedDebate: Safer Responses through Multi-Agent Red Teaming Debates

Ali Asad, Stephen Obadinma, Radin Shayanfar, Xiaodan Zhu — 2025-06-04 — arXiv

Summary

Introduces RedDebate, a fully automated multi-agent debate framework that uses collaborative argumentation among LLMs with memory modules to identify and mitigate unsafe behaviors through red-teaming, demonstrating substantial reductions in unsafe outputs on safety benchmarks.

Key Result

RedDebate substantially reduces unsafe outputs across diverse models, with memory integration yielding further significant safety improvements beyond debate alone.

Source