# How Should Vision-Language-Action Models Use Proprioceptive State?

arXiv: https://arxiv.org/abs/2608.03052 · HTML: https://mlsanity.com/paper/2608.03052/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Generalist VLA models and benchmarks, one of 13 directions in Vision-language-action models.
- Builds on 27 of its 30 references that are in the map.
- First posted on arXiv 4 Aug 2026.

## Placed in

- Vision-language-action models / [Generalist VLA models and benchmarks](https://mlsanity.com/vla/generalist-vla-models-and-benchmarks/)

## Builds on (most cited first, 27 of 27)

- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [π0: A Vision-Language-Action Flow Model for General Robot Control](https://mlsanity.com/paper/2410.24164/) (2024)
- [π0.5: a Vision-Language-Action Model with Open-World Generalization](https://mlsanity.com/paper/2504.16054/) (2025)
- [Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware](https://mlsanity.com/paper/2304.13705/) (2023)
- [GR00T N1: An Open Foundation Model for Generalist Humanoid Robots](https://mlsanity.com/paper/2503.14734/) (2025)
- [Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success](https://mlsanity.com/paper/2502.19645/) (2025)
- [Causal Confusion in Imitation Learning](https://mlsanity.com/paper/1905.11979/) (2019)
- [Recurrent Memory Transformer](https://mlsanity.com/paper/2207.06881/) (2022)
- [MemoryVLA: Perceptual-Cognitive Memory in Vision-Language-Action Models for Robotic Manipulation](https://mlsanity.com/paper/2508.19236/) (2025)
- [RoboCasa365: A Large-Scale Simulation Framework for Training and Benchmarking Generalist Robots](https://mlsanity.com/paper/2603.04356/) (2026)
- [Fighting Copycat Agents in Behavioral Cloning from Observation Histories](https://mlsanity.com/paper/2010.14876/) (2020)
- [RoboMME: Benchmarking and Understanding Memory for Robotic Generalist Policies](https://mlsanity.com/paper/2603.04639/) (2026)
- [CLAP: Contrastive Latent Action Pretraining for Learning Vision-Language-Action Models from Human Videos](https://mlsanity.com/paper/2601.04061/) (2026)
- [Contrastive Representation Regularization for Vision-Language-Action Models](https://mlsanity.com/paper/2510.01711/) (2025)
- [TwinBrainVLA: Unleashing the Potential of Generalist VLMs for Embodied Tasks via Asymmetric Mixture-of-Transformers](https://mlsanity.com/paper/2601.14133/) (2026)
- [HEX: Humanoid-Aligned Experts for Cross-Embodiment Whole-Body Manipulation](https://mlsanity.com/paper/2604.07993/) (2026)
- [LoLA: Long Horizon Latent Action Learning for General Robot Manipulation](https://mlsanity.com/paper/2512.20166/) (2025)
- [When would Vision-Proprioception Policies Fail in Robotic Manipulation?](https://mlsanity.com/paper/2602.12032/) (2026)
- [ROSA: Harnessing Robot States for Vision-Language and Action Alignment](https://mlsanity.com/paper/2506.13679/) (2025)
- [NeuroVLA: A Brain-inspired Embodied Intelligence for Fluid and Fast Reflexive Robotics Control](https://mlsanity.com/paper/2601.14628/) (2026)
- [ReViP: Mitigating False Completion in Vision-Language-Action Models with Vision-Proprioception Rebalance](https://mlsanity.com/paper/2601.16667/) (2026)
- [From Pixels to Tokens: A Systematic Study of Latent Action Supervision for Vision-Language-Action Models](https://mlsanity.com/paper/2605.04678/) (2026)
- [Spatial Memory for Out-of-Vision Manipulation in Vision-Language-Action](https://mlsanity.com/paper/2605.22283/) (2026)
- [Understanding the Impact of Geometric Foundation Models on Vision-Language-Action Models](https://mlsanity.com/paper/2605.24642/) (2026)
- [Tenma: Robust Cross-Embodiment Robot Manipulation with Diffusion Transformer](https://mlsanity.com/paper/2509.11865/) (2025)
- [Continuous Vision-Language-Action Co-Learning with Semantic-Physical Alignment for Behavioral Cloning](https://mlsanity.com/paper/2511.14396/) (2025)

## Built on by (most cited first, 1 of 1)

- [FAN: Foresight Action Normalization for Continual Adaptation of Vision-Language-Action Models](https://mlsanity.com/paper/2609.21358/) (2026)

## Abstract (arXiv)

Recent Vision-Language-Action (VLA) models almost universally take robot proprioceptive state as input, yet wire it in incompatible ways -- serialized into text prompts, projected into the vision-language prefix, or fed directly to the action expert -- and almost always as a single current frame. Three questions remain open: (1) whether, and on which tasks, current state actually improves closed-loop control; (2) how much state history helps, and whether its benefit reflects genuine temporal variation rather than added conditioning capacity; and (3) where state should enter the model -- the vision-language backbone or the action-generation module. We answer these questions through controlled experiments on a flow-matching VLA, fixing the backbone, training data, action representation, and evaluation protocol throughout. We implement five representative interfaces -- discrete state prompt, VLM prefix, action prefix, state expert, and feature modulation -- under matched implementation details, and evaluate them on 45 atomic tasks spanning three task families plus 20 composite tasks; we then sweep the state-history length from 1 to 96 frames to examine how historical state information affects model performance. The experiments yield systematic answers to all three questions, distilled into testable design principles for state-aware VLAs.