Ai2 Releases ToyBlocks: First FoundationWorlds Environment for Robot Learning

“Ai2 released ToyBlocks on November 6, 2026, as the first environment in its FoundationWorlds framework, pairing an open robot simulation with generated demonstrations, two trained models and evaluation tools. The framework is designed to make robot-learning experiments repeatable and failures easier to trace. The setting puts a simulated arm and labeled blocks on a tabletop. Pushing, flipping and stacking are joined”

Exact source · revision 2

Source owner not reported

“ting tasks and training demonstrations, as well as metrics for measuring a robot's behavior over time. Together, they provide a setting for studying questions such as how models improve as more training data becomes available, and how to best combine high-level reasoning with precise physical control. Our first foundation world is ToyBlocks : an open simulation framework built around a robot arm and blocks on a table”

Exact source · revision 2

huggingface

“execution. Failed states can also return to data generation for fresh demonstrations and recoveries. Ai2 reports that the initial release contains 85,336 long-horizon demonstrations, each comprising roughly 6–12 skill demonstrations depending on the set, covering nearly 1,600 hours of robot execution and 144 million frames. The public dataset uses Parquet-formatted LeRobot data under an ODC-BY license, with easy, med”

Exact source · revision 2

Source owner not reported

“execution. Failed states can also return to data generation for fresh demonstrations and recoveries. Ai2 reports that the initial release contains 85,336 long-horizon demonstrations, each comprising roughly 6–12 skill demonstrations depending on the set, covering nearly 1,600 hours of robot execution and 144 million frames. The public dataset uses Parquet-formatted LeRobot data under an ODC-BY license, with easy, med”

Exact source · revision 2

Source owner not reported

“execution. Failed states can also return to data generation for fresh demonstrations and recoveries. Ai2 reports that the initial release contains 85,336 long-horizon demonstrations, each comprising roughly 6–12 skill demonstrations depending on the set, covering nearly 1,600 hours of robot execution and 144 million frames. The public dataset uses Parquet-formatted LeRobot data under an ODC-BY license, with easy, med”

Exact source · revision 2

Source owner not reported

“reports ManiFlow atomic-skill success rates of 80.0% in simulation and 81.1% on the physical arm. The hierarchical Molmo 2–ManiFlow system succeeded in 55.5% of simulated episodes (111 of 200) and 50.0% of physical episodes (15 of 30). Ai2 qualifies those results on two fronts. The physical hierarchy evaluation used the easiest simulated configuration, with block characters visible and upright, and further trials are”

Exact source · revision 2

Source owner not reported

“reports ManiFlow atomic-skill success rates of 80.0% in simulation and 81.1% on the physical arm. The hierarchical Molmo 2–ManiFlow system succeeded in 55.5% of simulated episodes (111 of 200) and 50.0% of physical episodes (15 of 30). Ai2 qualifies those results on two fronts. The physical hierarchy evaluation used the easiest simulated configuration, with block characters visible and upright, and further trials are”

Exact source · revision 2

Source owner not reported

“zation for ManiFlow, π0.5 and MolmoAct 2 despite large-scale pretraining, and concludes that action-model generalization remains far from solved. The agentic tests expose a different weakness. Ai2 says its Claude Opus 5.5-based system solved all 30 classical block-stacking tasks from text descriptions and all 30 when choosing actions in a closed loop from repeated camera images. In search-and-spell scenes containing”

Exact source · revision 2

Source owner not reported

“reports ManiFlow atomic-skill success rates of 80.0% in simulation and 81.1% on the physical arm. The hierarchical Molmo 2–ManiFlow system succeeded in 55.5% of simulated episodes (111 of 200) and 50.0% of physical episodes (15 of 30). Ai2 qualifies those results on two fronts. The physical hierarchy evaluation used the easiest simulated configuration, with block characters visible and upright, and further trials are”

Exact source · revision 2

Source owner not reported

“execution. Failed states can also return to data generation for fresh demonstrations and recoveries. Ai2 reports that the initial release contains 85,336 long-horizon demonstrations, each comprising roughly 6–12 skill demonstrations depending on the set, covering nearly 1,600 hours of robot execution and 144 million frames. The public dataset uses Parquet-formatted LeRobot data under an ODC-BY license, with easy, med”

Exact source · revision 2

Source owner not reported

“ium and hard subsets. The main code is Apache-2.0 licensed; specified submodules and downloaded assets carry their own licenses. Ai2’s model cards divide the released policy into two levels: Molmo2-4B-tb , a roughly 4.5-billion-parameter model, reads a front-camera image and text goal to produce a short plan, next action and target point; ManiFlow-tb , with 322.5 million parameters, uses front and gripper images, rob”

Exact source · revision 2

Source owner not reported

“ium and hard subsets. The main code is Apache-2.0 licensed; specified submodules and downloaded assets carry their own licenses. Ai2’s model cards divide the released policy into two levels: Molmo2-4B-tb , a roughly 4.5-billion-parameter model, reads a front-camera image and text goal to produce a short plan, next action and target point; ManiFlow-tb , with 322.5 million parameters, uses front and gripper images, rob”

Exact source · revision 2

Source owner not reported

“ium and hard subsets. The main code is Apache-2.0 licensed; specified submodules and downloaded assets carry their own licenses. Ai2’s model cards divide the released policy into two levels: Molmo2-4B-tb , a roughly 4.5-billion-parameter model, reads a front-camera image and text goal to produce a short plan, next action and target point; ManiFlow-tb , with 322.5 million parameters, uses front and gripper images, rob”

Exact source · revision 2

Source owner not reported

“ot state, task information and a target heatmap to generate action chunks. Generalization and Agent Experiments The spatial experiments cover Stack, Unstack, Flip and Rotate, distinguishing interpolation within the training range from extrapolation beyond it. Examples include training with blocks in one workspace region and testing in another, or withholding particular stack heights. Ai2 reports poor initial generali”

Exact source · revision 2

Source owner not reported

“ot state, task information and a target heatmap to generate action chunks. Generalization and Agent Experiments The spatial experiments cover Stack, Unstack, Flip and Rotate, distinguishing interpolation within the training range from extrapolation beyond it. Examples include training with blocks in one workspace region and testing in another, or withholding particular stack heights. Ai2 reports poor initial generali”

Exact source · revision 2

Source owner not reported

“ot state, task information and a target heatmap to generate action chunks. Generalization and Agent Experiments The spatial experiments cover Stack, Unstack, Flip and Rotate, distinguishing interpolation within the training range from extrapolation beyond it. Examples include training with blocks in one workspace region and testing in another, or withholding particular stack heights. Ai2 reports poor initial generali”

Exact source · revision 2

Source owner not reported

“ot state, task information and a target heatmap to generate action chunks. Generalization and Agent Experiments The spatial experiments cover Stack, Unstack, Flip and Rotate, distinguishing interpolation within the training range from extrapolation beyond it. Examples include training with blocks in one workspace region and testing in another, or withholding particular stack heights. Ai2 reports poor initial generali”

Exact source · revision 2

Source owner not reported

“Ai2 released ToyBlocks on November 6, 2026, as the first environment in its FoundationWorlds framework, pairing an open robot simulation with generated demonstrations, two trained models and evaluation tools. The framework is designed to make robot-learning experiments repeatable and failures easier to trace. The setting puts a simulated arm and labeled blocks on a tabletop. Pushing, flipping and stacking are joined”

Exact source · revision 2

Source owner not reported

“scriptions raised success from 24% with default descriptions to 63%, exceeding the 36% achieved with descriptions written by a human expert. Physical Robot Tests and Their Limits For physical evaluation, models trained entirely on ToyBlocks simulation data ran without real-world training examples on a Franka FR3 arm with a Robotiq gripper. The 30 scene configurations contained 4–10 blocks seen during training. An epi”

Exact source · revision 2

Source owner not reported

“ater hypothesizes: “…maybe the gripper’s yaw is radial—pointing from the robot base toward the block” (0:15) and eventually confirms this hypothesis (0:26) before constructing the three-block tower, but the ‘A’ is sideways (1:11). Surprisingly, current frontier models often make similar perceptual errors (see the next figure), despite their impressive planning, spatial reasoning, and search capabilities. For classica”

Exact source · revision 2

huggingface