Open source #Open models Nov 9, 2026 · Originally published Nov 6

Ai2 opens ToyBlocks, a robot learning framework: 85,336 long-horizon demonstrations, about 1,600 hours of data, and up to 24x real-time generation on one GPU

A controlled tabletop world of blocks for generating tasks and training and evaluating robots, which also exposes where frontier models acting as agents fall short in planning and perception.

Image: Ai2 on the Hugging Face blog
Primary source Ai2 on the Hugging Face blog · huggingface.co Read the original ↗

// Key points

  • Released: simulation assets, task and demonstration generators, training and evaluation code, validation sets, and two models, Molmo2-4B-tb and maniflow-tb; the data has 85,336 long-horizon demonstrations and about 144 million frames
  • With Claude Opus 5.5 as the agent, 63% of search-and-spell tasks were solved or correctly declared infeasible; learned skill descriptions raised success from 24% to 63%, versus 36% for expert-written ones
  • Adding 100 world-model rollouts raised a policy's success in an unseen region from 19% to 78%; ManiFlow's atomic skills scored 80.0% in simulation and 81.1% on a real robot
  • The authors say action models still generalize poorly to new spatial layouts and frontier models still misread letter orientation; a larger second release is planned within weeks

Builder's takeI don't build robots, but the finding that learned skill descriptions beat expert-written ones matters to anyone writing tool descriptions for agents: let the model rewrite them from real call results, then compare on an eval set. I would try one round on PandaClaws' tool descriptions.

// Background · from #Open models

Full timeline →
  1. Nov 8 Kimi K3.1 Pro (Highspeed) arrives on Amazon Bedrock: open-weight, natively multimodal, a 1-million-token context, and explicit prompt caching
  2. Nov 8 NVIDIA open-sources the Reshard collective, making RL post-training weight refit 2.7x to 5.7x faster than gather-and-broadcast
  3. Nov 8 Gradium releases Phonon for on-device speech: from about 65 MB, 28 ms p95 time to first audio on CPU streaming, and an Apache 2.0 English model

Every Monday, the week in AI in one email

Every Monday morning: the 6 AI stories that mattered most in the past seven days, with my take, in your inbox.

Your email is only used to send the weekly and is never shared. Every email has a one-click unsubscribe link. See the latest issue →