Multi Agent Evolve

Enables LLM self-improvement without external verification through multi-agent co-evolution. Proposer generates questions, Solver attempts solutions, Judge evaluates both. All agents evolve together via RL, achieving 4.54% improvement on reasoning benchmarks without human supervision.

adu2021 Updated 7 repo stars

File contents

adu2021/skillxiv commit 0c4bba52f1

Frequently asked questions

npx get-skill add adu2021/multi-agent-evolve