Machine Heart
Jun 8, 2026 · Artificial Intelligence
Unlocking New Potential in Agent Swarms: OpenJiuwen’s MANGO Multi‑Agent Flow Network
The MANGO framework integrates reinforcement learning, text‑gradient updates, and a node‑skipping mechanism to jointly optimize workflow structure and execution policy in multi‑agent systems, achieving superior accuracy and dramatically lower compute costs across seven benchmark datasets.
GPT-4o-miniMANGOReinforcement Learning
0 likes · 10 min read