# VLA Grounder: Language-Conditioning Space Optimization for Black-Box VLA Models

arXiv: https://arxiv.org/abs/2607.04517 · HTML: https://mlsanity.com/paper/2607.04517/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Reinforcement learning and post-training, one of 13 directions in Vision-language-action models.
- Builds on 20 of its 28 references that are in the map.
- First posted on arXiv 5 Jul 2026.

## Placed in

- Vision-language-action models / [Reinforcement learning and post-training](https://mlsanity.com/vla/reinforcement-learning-and-post-training/)

## Builds on (most cited first, 20 of 20)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [π0: A Vision-Language-Action Flow Model for General Robot Control](https://mlsanity.com/paper/2410.24164/) (2024)
- [Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware](https://mlsanity.com/paper/2304.13705/) (2023)
- [BridgeData V2: A Dataset for Robot Learning at Scale](https://mlsanity.com/paper/2308.12952/) (2023)
- [GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning](https://mlsanity.com/paper/2507.19457/) (2025)
- [π*0.6: a VLA That Learns From Experience](https://mlsanity.com/paper/2511.14759/) (2025)
- [ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL](https://mlsanity.com/paper/2402.19446/) (2024)
- [What Can RL Bring to VLA Generalization? An Empirical Study](https://mlsanity.com/paper/2505.19789/) (2025)
- [A Survey on Vision-Language-Action Models: An Action Tokenization Perspective](https://mlsanity.com/paper/2507.01925/) (2025)
- [MolmoAct2: Action Reasoning Models for Real-world Deployment](https://mlsanity.com/paper/2605.02881/) (2026)
- [PRewrite: Prompt Rewriting with Reinforcement Learning](https://mlsanity.com/paper/2401.08189/) (2024)
- [Don't Blind Your VLA: Aligning Visual Representations for OOD Generalization](https://mlsanity.com/paper/2510.25616/) (2025)
- [Stable Language Guidance for Vision-Language-Action Models](https://mlsanity.com/paper/2601.04052/) (2026)
- [Limited Linguistic Diversity in Embodied AI Datasets](https://mlsanity.com/paper/2601.03136/) (2026)
- [Experiences from Benchmarking Vision-Language-Action Models for Robotic Manipulation](https://mlsanity.com/paper/2511.11298/) (2025)
- [Bring the Apple, Not the Sofa: Impact of Irrelevant Context in Embodied AI Commands on VLA Models](https://mlsanity.com/paper/2510.07067/) (2025)
- [SPARTA: Evaluating Reasoning Segmentation Robustness through Black-Box Adversarial Paraphrasing in Text Autoencoder Latent Space](https://mlsanity.com/paper/2510.24446/) (2025)

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

- [Rephrase Before You Act: Characterizing and Mitigating Language Sensitivity in Vision-Language-Action Models](https://mlsanity.com/paper/2610.10526/) (2026)

## Abstract (arXiv)

Vision-Language-Action (VLA) models are commonly treated as end-to-end action policies conditioned on natural-language task descriptions. In practice, however, their behavior often depends sharply on how the instruction is phrased, suggesting that language is not merely a task label but an optimizable conditioning input. We study whether frozen VLA policies can be improved by optimizing language space rather than updating action weights. Our method introduces a language-conditioning space policy that translates a human instruction into a short VLA-grounded command using object appearance, spatial relations, and target-grounding cues. The language-conditioning space policy is optimized with reinforcement learning from sparse task-completion rewards, while the downstream VLA remains fully frozen. Experiments on RL4VLA and VL-Think show that language-conditioning space optimization improves success on instruction-sensitive, symbolic, and multi-object manipulation tasks, demonstrating that language can serve as an optimizable variable for robot foundation models. Website: https://cognitiveaisystems.github.io/VLA-Grounder/