AIFIRST multi-agent-debate: configurable N-agent debate system with an impartial LLM judge
The brief
multi-agent-debate is an open-source framework where any number of LLM agents argue opposing positions on a topic, with a separate impartial judge agent producing a structured, scored verdict.
Key points
- The system is provider-agnostic and supports any LLM backend via a configurable adapter.
Sources
- GitHubgithub.com
- Source codegithub.com