{"ID":5937810,"CreatedAt":"2026-07-07T03:14:33.014478982Z","UpdatedAt":"2026-07-08T21:35:32.327944328Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.04517","arxiv_id":"2607.04517","title":"VLA Grounder: Language-Conditioning Space Optimization for Black-Box VLA Models","abstract":"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 initialized with a failure-derived command-space prior and optimized with reinforcement learning from sparse task-completion rewards, while the downstream VLA remains fully frozen. This yields language-conditioning space optimization: RL discovers which VLA-grounded commands best elicit successful behavior from the frozen action policy. 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 a robot foundation models. Website: https://tttonyalpha.github.io/vla_grounder","short_abstract":"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 inpu...","url_abs":"https://arxiv.org/abs/2607.04517","url_pdf":"https://arxiv.org/pdf/2607.04517v1","authors":"[\"Damir Shodiev\",\"Aleksei Staroverov\",\"Nikita Kachaev\",\"Alexey K. Kovalev\",\"Aleksandr I. Panov\"]","published":"2026-07-05T21:41:25Z","proceeding":"cs.AI","tasks":"[\"cs.AI\"]","methods":"[\"Reinforcement Learning\"]","has_code":false}