cs.RONov 12, 2026

Reins: Frontier Multimodal Models Driving Real Robot Arms on Long-Horizon Tasks, Zero-Shot

Authors: Pengfei Ye, Zhiyang Dou, Yuxiang Ma, Haonan Chen, Heng Yang, Edward H. Adelson

Organizations: MIT CSAIL · Harvard University

Abstract

Frontier models such as GPT-6.1 Sol, GPT-6 Astra and Claude Opus 5.5 can now plan and call tools, yet they still struggle to drive real robots through long-horizon, contact-rich manipulation, blind while the arm moves and while they think. We present Reins, a harness in which an off-the-shelf model operates a dual-arm robot with 3D perception tools and atomic actions that report contact and grip. The model chains actions in one call, each with a condition that must hold, stopping at the first that fails; a second instance, the narrator, watches the cameras continuously and reports what changed with every result. From images, Reins also builds a simulation-ready twin of the scene for continual policy learning. With natural-language prompts and no task-specific code, GPT-6.1 Sol succeeds in 88% of real episodes on five tasks; without the harness, it fails every shell game, taking 8 times as long. Three frontier models perform alike but differ in tracking a scene that changes while the actor thinks. Code will be released upon publication.

Figures & tables

Appendix figures & tables5 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. DreamFAR: Real-Time and Long-Horizon Interaction with Diverse Objects

    Nov 16, 2026Yiming Dou, Botao He, Antonio Loquercio +4World Models for RoboticsLong-Horizon Robotic Manipulation

  2. ForceHarness: Turning Force into Action and Physics for Frozen Frontier Models

    Nov 16, 2026Ke Sun, Kevin Yuchen Ma, Yike Zhang +2Robotic ManipulationForce-Controlled Robotic Manipulation

  3. JustRUA: A Controlled Study of GPT-6 Robot-Use Agents

    Nov 11, 2026Zefan Wang, Yufan Dang, Xuanwei Shi +9Robotic ControlRobotic Manipulation