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.
More from coding & agent
- Just Screenshot the Bug: Skipping Copy-Paste When Tasking Coding Agents — fhinkel · 2026-11-18
- Free browser arcade golf game Fairway Fever built entirely with ChatGPT + Codex — ZabblesMarshmelon · 2026-11-18
- Dev builds Kasane Valley with Blender + three.js, showcasing 'GPT 6.2 Astra Ultra' workflow — OpenAIDevs · 2026-11-18
- 3 Weeks with GPT-6.2 Astra Internal Checkpoint: Less Lazy, Less Coding Slop — SIGKITTEN · 2026-11-18
- User files a Chase complaint addressed to the bank's AI agent, with a full image transcript — AaronBergman18 · 2026-11-18
- Anthropic on agent memory: scaling 'dreaming' to 128 sessions lifts score from 13% to 48% — dl_weekly · 2026-11-18