CAST: Counterfactual Labels Improve Instruction Following in Vision-Language-Action Models

Published June 10, 2026 · Category: Robotics

Overview

arXiv:2508.13446v2 Announce Type: replace Abstract: Generalist robots should be able to understand and follow user instructions. Despite providing a powerful architecture for mapping open-vocabulary language instructions to robot actions, current vision-language-action (VLA) models struggle to follow fine-grained commands. One cause for this is a lack of semantic diversity and language grounding in existing robot datasets and, specifically, a lack of fine-grained task diversity for similar observations. To address this, we present a novel method to augment existing robot datasets by leveraging vision-language models to create counterfactual labels. By augmenting existing datasets with these labels, we increase the diversity and granularity of language grounding for robot datasets, ultimately improving the language-following capabilities of VLAs. We evaluate the resulting model's ability to follow language instructions, ranging from simple object-centric commands to complex referential tasks, by conducting vision-language navigation experiments in 3 different indoor and outdoor environments. Our experiments show that counterfactual relabeling (without additional data collection) significantly improves instruction-following in VLA policies, outperforming state-of-the-art methods and doubling the success rate compared to VLAs trained on unaugmented data. We also evaluate our method for manipulation VLAs and find a similar gain in performance on tasks with distractors.

Source

Originally published at arxiv.org.

Related Articles

• AgenticNav: Zero-Shot Vision-and-Language Navigation as a Tool-Calling Harness
• Act on What You See: Unlocking Safe Social Navigation in Vision-Language-Action Models
• Dexterous Point Policy: Learning Point-based Dexterous Hand Policies from Human Demonstrations