# MolmoSpaces: A Large-Scale Open Ecosystem for Robot Navigation and Manipulation

arXiv: https://arxiv.org/abs/2602.11337 · HTML: https://mlsanity.com/paper/2602.11337/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Feb 2026.

## Built on by (most cited first, 14 of 14)

- [Cosmos 3: Omnimodal World Models for Physical AI](https://mlsanity.com/paper/2606.02800/) (2026)
- [MolmoAct2: Action Reasoning Models for Real-world Deployment](https://mlsanity.com/paper/2605.02881/) (2026)
- [Playful Agentic Robot Learning](https://mlsanity.com/paper/2606.19419/) (2026)
- [Guava: Distilling Frontier VLMs into a Compact Agent through a Robotic Manipulation Harness](https://mlsanity.com/paper/2606.18363/) (2026)
- [MolmoMotion: Forecasting Point Trajectories in 3D with Language Instruction](https://mlsanity.com/paper/2606.18558/) (2026)
- [RoboWorld: Fast and Reliable Neural Simulators for Generalist Robot Policy Evaluation](https://mlsanity.com/paper/2607.01060/) (2026)
- [Visual Verification Enables Inference-time Steering and Autonomous Policy Improvement](https://mlsanity.com/paper/2606.18247/) (2026)
- [Image2Sim: Scaling Embodied Navigation via Generative Neural Simulator](https://mlsanity.com/paper/2607.05765/) (2026)
- [Is Success All You Need? Investigating the Impact of Input Perturbations on VLA Behaviour in Tabletop Manipulation Tasks](https://mlsanity.com/paper/2610.01351/) (2026)
- [I2CD: Direct Image-to-Convex Decomposition for Simulation-Ready Collision Geometry](https://mlsanity.com/paper/2610.03453/) (2026)
- [GATOR: Generative and Agentic 3D Object Reconstruction From Casual Images](https://mlsanity.com/paper/2610.11215/) (2026)
- [ARC: A Reasoning Recipe for Robot Foundation Models](https://mlsanity.com/paper/2610.12386/) (2026)
- [Interactive Navigation Beyond Reachability: Benchmark and Agentic Framework](https://mlsanity.com/paper/2610.17089/) (2026)
- [FoveaVLA: Foveation Actions Replace the Wrist Camera in VLAs](https://mlsanity.com/paper/2610.20064/) (2026)

## Abstract (arXiv)

Deploying robots at scale demands robustness to the long tail of everyday situations. The countless variations in scene layout, object geometry, and task specifications that characterize real environments are vast and underrepresented in existing robot benchmarks. Measuring this level of generalization requires infrastructure at a scale and diversity that physical evaluation alone cannot provide. We introduce MolmoSpaces, a fully open ecosystem to support large-scale benchmarking of robot policies. MolmoSpaces consists of over 230k diverse indoor environments, ranging from handcrafted household scenes to procedurally generated multiroom houses, populated with 130k richly annotated object assets, including 48k manipulable objects with 42M stable grasps. Crucially, these environments are simulator-agnostic, supporting popular options such as MuJoCo, Isaac, and ManiSkill. The ecosystem supports the full spectrum of embodied tasks: static and mobile manipulation, navigation, and multiroom long-horizon tasks requiring coordinated perception, planning, and interaction across entire indoor environments. We also design MolmoSpaces-Bench, a benchmark suite of 8 tasks in which robots interact with our diverse scenes and richly annotated objects. Our experiments show MolmoSpaces-Bench exhibits strong sim-to-real correlation (R = 0.96, rho = 0.98), confirm newer and stronger zero-shot policies outperform earlier versions in our benchmarks, and identify key sensitivities to prompt phrasing, initial joint positions, and camera occlusion. Through MolmoSpaces and its open-source assets and tooling, we provide a foundation for scalable data generation, policy training, and benchmark creation for robot learning research.