Paper page - SO-101 Bench: Accessible Spatial Manipulation

Source: https://huggingface.co/papers/2610.36420

Abstract

A simulated benchmark for language-conditioned spatial manipulation on low-cost robot arms reveals that hybrid LLM agents outperform learned vision-language-action policies, with ranking consistency between simulation and real hardware.

Low-cost arms such as the SO-101 have become the most common entry point to robot learning, yet no released policy performs spatially constrained, language-conditioned tasks on them out of the box, and existingSO-101 benchmarks run only on physical hardware with simple tasks and few held-out objects. We introduceSO-101 Bench, a simulated benchmark for language-conditionedspatial manipulationbuilt on anIsaac Labdigital twinof a real SO-101 setup. It has four tasks scored as five families, 138 objects in seen, unseen-instance and unseen-class splits, 916 evaluation episodes with subsets for held-out appearances,rotate-to-fit planningandocclusion memory, and 3,629 simulated demonstrations on which every learned policy is fine-tuned under an equal compute budget. The twin ranks policies as the real robot does: five policies trained without real data, fourVLAsand anLLM agent, keep their exact ranking when the same weights run on the physical arm in an unseen environment with unseen objects (Spearman rho = 1.00, MMRV = 0.000), although simulation overestimates success. Across nineVLAsandworld-action models, the best learned policies score near 61%, with spatial placement, unseen object classes androtate-to-fit planningremaining open. AnLLM agentthat writes code and hands grasping to a learned policy scores 83.2%, and an ablation shows that this lead comes from the choice of harness and the choice of language model.

View arXiv pageView PDFProject pageGitHub28Add to collection

Get this paper in your agent:

hf papers read 2610\.36420

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2610.36420 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2610.36420 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2610.36420 in a Space README.md to link it from this page.

Collections including this paper1