# ReSteer: Quantifying and Refining the Steerability of Multitask Robot Policies

arXiv: https://arxiv.org/abs/2603.17300 · HTML: https://mlsanity.com/paper/2603.17300/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Mar 2026.

## Built on by (most cited first, 7 of 7)

- [Learning What to Say to Your VLA: Mostly Harmless Vision Language Action Model Steering](https://mlsanity.com/paper/2606.12299/) (2026)
- [See Less, Specify More: Visual Evidence Budgets for Generalizable VLAs](https://mlsanity.com/paper/2606.02735/) (2026)
- [In-Context Learning for Robots: Methods and Applications](https://mlsanity.com/paper/2609.36012/) (2026)
- [Flow Control: Steering Vision-Language-Action Models with Simple Real-Time Inputs](https://mlsanity.com/paper/2606.10180/) (2026)
- [Causeway: Restoring Task Accessibility for Instruction Switching in VLA Policies](https://mlsanity.com/paper/2609.30913/) (2026)
- [GT-VLA: Target-Conditioned Trace Guidance for Generalizable Robotic Manipulation](https://mlsanity.com/paper/2609.31904/) (2026)
- [Same Scene, Different Task: Skill Alignment for Compositional Generalization in VLAs](https://mlsanity.com/paper/2610.00524/) (2026)

## Abstract (arXiv)

Despite strong multi-task pretraining, existing policies often exhibit poor task steerability. For example, a robot may fail to respond to a new instruction ``put the bowl in the sink" when moving towards the oven, executing ``close the oven", even though it can complete both tasks when executed separately. We propose ReSteer, a framework to quantify and improve task steerability in multitask robot policies. We conduct an exhaustive evaluation of state-of-the-art policies, revealing a common lack of steerability. We find that steerability is associated with limited overlap among training task trajectory distributions, and introduce a proxy metric to measure this overlap from policy behavior. Building on this insight, ReSteer improves steerability via three components: (i) a steerability estimator that identifies low-steerability states without full-rollout evaluation, (ii) a steerable data generator that synthesizes motion segments from these states, and (iii) a self-refinement pipeline that improves policy steerability using the generated data. In simulation on LIBERO, ReSteer improves steerability by 11% over 18k rollouts. In real-world experiments, we show that improved steerability is critical for interactive use, enabling users to instruct robots to perform any task at any time. We hope this work motivates further study on quantifying steerability and data collection strategies for large robot policies.