Multi-agent RL recipe turns pass@k into pass@1 with role-free Inkling 2 Small teams

keirp1 · x · 2026-11-18

Researcher @jaswwei shares a multi-agent RL result: a team of Inkling 2 Small agents learns to collaborate, communicate and delegate on hard chess puzzles — with no predefined roles.

The key finding: a simple multi-agent RL recipe converts pass@k into pass@1, meaning solutions that previously required many samples are found on a single try. Thread with collaborators @emilianogl and @GabeVisotsky.

Original post →

More from coding & agent

coding & agent channel →