Multi-turn agent RL training at scale on HF Hub: 9,523 sandboxes in 14h, zero crashes
vanstriendaniel · x · 2026-09-16
First multi-turn agent harness RL training with sandboxing running at scale on the Hugging Face Hub: 9,523 sandboxes spawned in 14 hours, full-parameter training of Qwen3-Coder-30B-A3B (30B MoE) with FSDP2 + expert parallel, all on HF Jobs with no Slurm and zero crashes.
More from coding & agent
- Microsoft's MemSteer turns unlabeled user histories into agent memory supervision — MicrosoftResearch · 2026-11-02
- She fired herself from her own Instagram: AI agent runs the account, views up 82.3% — heyshrutimishra · 2026-11-02
- Sourcegraph: AI writes code faster than teams can review it, driving more outages — AI Engineer · 2026-11-02
- Tsinghua & Microsoft's HarnessMM cuts agent token use by up to 87.93% while raising success rate — rohanpaul_ai · 2026-11-02
- GitHub launches Agent HQ: Anthropic, OpenAI, Google coding agents in Copilot — emmanuelvivier · 2026-11-02
- DeepSeek open-sources Super-Agent, a coding agent that reads team chats to minimize human input — emmanuelvivier · 2026-11-02