Wide Seek Multi Agent Scaling

Dynamically fork sub-agents at any step based on task requirements instead of using fixed agent counts. Linearize hierarchical trajectories into unified sequences for GRPO training. Demonstrates 6.36x more sub-agents than baselines via learned orchestration.

adu2021 Updated 7 repo stars

File contents

adu2021/skillxiv commit 8d1e4931ed

Frequently asked questions

npx get-skill add adu2021/wide-seek-multi-agent-scaling