# Steerable Vision-Language-Action Policies for Embodied Reasoning and Hierarchical Control

arXiv: https://arxiv.org/abs/2602.13193 · HTML: https://mlsanity.com/paper/2602.13193/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 38 of its 76 references that are in the map.
- First posted on arXiv 13 Feb 2026.

## Placed in

- LLM reasoning / [Spatial and embodied reasoning](https://mlsanity.com/lr/spatial-and-embodied-reasoning/)
- Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/)
- Vision-language-action models / [Reasoning and chain-of-thought in VLA](https://mlsanity.com/vla/reasoning-and-chain-of-thought-in-vla/)

## Builds on (most cited first, 30 of 38)

- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [π0: A Vision-Language-Action Flow Model for General Robot Control](https://mlsanity.com/paper/2410.24164/) (2024)
- [LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning](https://mlsanity.com/paper/2306.03310/) (2023)
- [Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents](https://mlsanity.com/paper/2201.07207/) (2022)
- [Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success](https://mlsanity.com/paper/2502.19645/) (2025)
- [PaliGemma: A versatile 3B VLM for transfer](https://mlsanity.com/paper/2407.07726/) (2024)
- [FAST: Efficient Action Tokenization for Vision-Language-Action Models](https://mlsanity.com/paper/2501.09747/) (2025)
- [LM-Nav: Robotic Navigation with Large Pre-Trained Models of Language, Vision, and Action](https://mlsanity.com/paper/2207.04429/) (2022)
- [Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models](https://mlsanity.com/paper/2409.17146/) (2024)
- [TraceVLA: Visual Trace Prompting Enhances Spatial-Temporal Awareness for Generalist Robotic Policies](https://mlsanity.com/paper/2412.10345/) (2024)
- [EMMA: End-to-End Multimodal Model for Autonomous Driving](https://mlsanity.com/paper/2410.23262/) (2024)
- [Hi Robot: Open-Ended Instruction Following with Hierarchical Vision-Language-Action Models](https://mlsanity.com/paper/2502.19417/) (2025)
- [MolmoAct: Action Reasoning Models that can Reason in Space](https://mlsanity.com/paper/2508.07917/) (2025)
- [LIBERO-PRO: Towards Robust and Fair Evaluation of Vision-Language-Action Models Beyond Memorization](https://mlsanity.com/paper/2510.03827/) (2025)
- [Steering Your Diffusion Policy with Latent Space Reinforcement Learning](https://mlsanity.com/paper/2506.15799/) (2025)
- [Knowledge Insulating Vision-Language-Action Models: Train Fast, Run Fast, Generalize Better](https://mlsanity.com/paper/2505.23705/) (2025)
- [RT-Trajectory: Robotic Task Generalization via Hindsight Trajectory Sketches](https://mlsanity.com/paper/2311.01977/) (2023)
- [HAMSTER: Hierarchical Action Models For Open-World Robot Manipulation](https://mlsanity.com/paper/2502.05485/) (2025)
- [Galaxea Open-World Dataset and G0 Dual-System VLA Model](https://mlsanity.com/paper/2509.00576/) (2025)
- [Bootstrap Your Own Skills: Learning to Solve New Tasks with Large Language Model Guidance](https://mlsanity.com/paper/2310.10021/) (2023)
- [Gemini Robotics: Bringing AI into the Physical World](https://mlsanity.com/paper/2503.20020/) (2025)
- [In-Context Imitation Learning via Next-Token Prediction](https://mlsanity.com/paper/2408.15980/) (2024)
- [RoboMonkey: Scaling Test-Time Sampling and Verification for Vision-Language-Action Models](https://mlsanity.com/paper/2506.17811/) (2025)
- [Diffusion Guidance Is a Controllable Policy Improvement Operator](https://mlsanity.com/paper/2505.23458/) (2025)
- [From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment](https://mlsanity.com/paper/2502.01828/) (2025)
- [OmniVLA: An Omni-Modal Vision-Language-Action Model for Robot Navigation](https://mlsanity.com/paper/2509.19480/) (2025)
- [Interactive Task Planning with Language Models](https://mlsanity.com/paper/2310.10645/) (2023)

## Built on by (most cited first, 20 of 20)

- [What Matters in Orchestrating Robot Policies: A Systematic Study of Hierarchical VLA Agents](https://mlsanity.com/paper/2606.10267/) (2026)
- [Addressing the Orchestration Gap in Generalist Robots via Physical Agency](https://mlsanity.com/paper/2607.21725/) (2026)
- [Flex-π: A Multi-Stream World-Action Model with Compute Flexibility](https://mlsanity.com/paper/2608.10860/) (2026)
- [Breaking Lock-In: Preserving Steerability under Low-Data VLA Post-Training](https://mlsanity.com/paper/2604.23121/) (2026)
- [Improving Robotic Generalist Policies via Flow Reversal Steering](https://mlsanity.com/paper/2606.13675/) (2026)
- [ICLR: In-Context Imitation Learning with Visual Reasoning](https://mlsanity.com/paper/2603.07530/) (2026)
- [Learning What to Say to Your VLA: Mostly Harmless Vision Language Action Model Steering](https://mlsanity.com/paper/2606.12299/) (2026)
- [StellaVLA: In-Context Structured Demonstration for Generalizable Vision-Language-Action Models](https://mlsanity.com/paper/2608.11671/) (2026)
- [Contrastive Conceptor Activation Steering (COAST): Unlocking Vision-Language-Action Models through Hidden States](https://mlsanity.com/paper/2605.17144/) (2026)
- [Adapting Generalist Robot Policies with Semantic Reinforcement Learning](https://mlsanity.com/paper/2606.31958/) (2026)
- [A Few Words Go a Long Way: Language Guided Robot Policy Synthesis](https://mlsanity.com/paper/2607.23784/) (2026)
- [InSight: Self-Guided Skill Acquisition via Steerable VLAs](https://mlsanity.com/paper/2606.24884/) (2026)
- [Direct Action-Head Injection of A Grounded 3D Point Unlocks Spatial and Task Generalization](https://mlsanity.com/paper/2606.27663/) (2026)
- [2AM: Grounding Agent-Side Memory as Guidance for Steerable Action Models in Long-Horizon Manipulation](https://mlsanity.com/paper/2609.11308/) (2026)
- [See Less, Specify More: Visual Evidence Budgets for Generalizable VLAs](https://mlsanity.com/paper/2606.02735/) (2026)
- [Decoupling the Declarative from the Procedural in Vision-Language-Action Models](https://mlsanity.com/paper/2606.21496/) (2026)
- [PonderPounce: A Pretrained MLLM as an Episode Context Engine for Robot Control](https://mlsanity.com/paper/2608.24115/) (2026)
- [In-Context Learning for Robots: Methods and Applications](https://mlsanity.com/paper/2609.36012/) (2026)
- [Act, Think or Abstain: Complexity-Aware Adaptive Inference for Vision-Language-Action Models](https://mlsanity.com/paper/2603.05147/) (2026)
- [ARC: A Reasoning Recipe for Robot Foundation Models](https://mlsanity.com/paper/2610.12386/) (2026)

## Abstract (arXiv)

Pretrained vision-language models (VLMs) can make semantic and visual inferences across diverse settings, providing valuable common-sense priors for robotic control. However, effectively grounding this knowledge in robot behaviors remains an open challenge. Prior methods often employ a hierarchical approach where VLMs reason over high-level commands to be executed by separate low-level policies, e.g., vision-language-action models (VLAs). The interface between VLMs and VLAs is usually natural language task instructions, which fundamentally limits how much VLM reasoning can steer low-level behavior. We thus introduce Steerable Policies: VLAs trained on rich synthetic commands at various levels of abstraction, like subtasks, motions, and grounded pixel coordinates. By improving low-level controllability, Steerable Policies can unlock pretrained knowledge in VLMs, enabling improved task generalization. We demonstrate this benefit by controlling our Steerable Policies with both a learned high-level embodied reasoner and an off-the-shelf VLM prompted to reason over command abstractions via in-context learning. Across extensive real-world manipulation experiments, these two novel methods outperform prior embodied reasoning VLAs and VLM-based hierarchical baselines, including on challenging generalization and long-horizon tasks. Website: steerable-policies.github.io