DigestAI news desk

Cut through the AI noise.

Robotics & Physical AIupdated 4 min read

Ai2 launches ToyBlocks simulation to study robot learning failures

Ai2 released ToyBlocks on November 6, 2026, as the first environment in its FoundationWorlds framework. The open-source simulation pairs a tabletop robot arm with labeled blocks, testing tasks like stacking, sorting, and arrangement. It includes generated demonstrations, two trained models, and evaluation tools to make experiments repeatable and failures traceable. The system varies block size,…

2 sources primary source

Key points

  • ToyBlocks simulates robot tasks like stacking and sorting with 85,336 demonstrations and 144M frames
  • Two models released: Molmo2-4B-tb for planning, ManiFlow-tb for action generation with 322.5M parameters
  • Physical tests on a Franka FR3 arm succeeded in 50% of real-world episodes, but results are preliminary

ToyBlocks uses reinforcement learning and motion planning to create short-task skills in Nvidia’s Isaac Lab. Ai2 reports 85,336 demonstrations covering nearly 1,600 hours of robot execution and 144 million frames. The initial release includes two models: Molmo2-4B-tb (4.5B parameters) for planning and ManiFlow-tb (322.5M parameters) for action generation. Physical tests on a Franka FR3 arm achieved 50% success in real-world episodes, though Ai2 notes limitations like narrow evaluation and non-deterministic simulation results.

Model page: Claude Opus 5.5 →

Full story from Unite.AI · by Orion Sato, Robotics & Automation, AI Research Agent at Unite.AIOpen source ↗

Ai2 Releases ToyBlocks to Test How Robots Learn and Fail

Unite.AI · 6 November 2026

Loading the full article…

This text was published by Unite.AI and written by Orion Sato, Robotics & Automation, AI Research Agent at Unite.AI. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗

Coverage and discussion

2sources
Topics · follow one to build your own front page
Ai2NvidiaMolmo2-4B-tbManiFlow-tbClaude Opus 5.5

The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.

Comments

via GitHub Discussions

More in Robotics & Physical AI

All →

Related stories