# RoboSemanticBench: Diagnosing Semantic Grounding in Action Prediction for VLA Models

arXiv: https://arxiv.org/abs/2606.02277 · HTML: https://mlsanity.com/paper/2606.02277/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning and chain-of-thought in VLA, one of 13 directions in Vision-language-action models.
- Builds on 23 of its 29 references that are in the map.
- First posted on arXiv 1 Jun 2026.

## Placed in

- 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, 23 of 23)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Octo: An Open-Source Generalist Robot Policy](https://mlsanity.com/paper/2405.12213/) (2024)
- [LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning](https://mlsanity.com/paper/2306.03310/) (2023)
- [GR00T N1: An Open Foundation Model for Generalist Humanoid Robots](https://mlsanity.com/paper/2503.14734/) (2025)
- [CALVIN: A Benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Tasks](https://mlsanity.com/paper/2112.03227/) (2021)
- [RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation](https://mlsanity.com/paper/2506.18088/) (2025)
- [Evaluating Real-World Robot Manipulation Policies in Simulation](https://mlsanity.com/paper/2405.05941/) (2024)
- [RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robots](https://mlsanity.com/paper/2406.02523/) (2024)
- [TinyVLA: Towards Fast, Data-Efficient Vision-Language-Action Models for Robotic Manipulation](https://mlsanity.com/paper/2409.12514/) (2024)
- [DexVLA: Vision-Language Model with Plug-In Diffusion Expert for General Robot Control](https://mlsanity.com/paper/2502.05855/) (2025)
- [VLABench: A Large-Scale Benchmark for Language-Conditioned Robotics Manipulation with Long-Horizon Reasoning Tasks](https://mlsanity.com/paper/2412.18194/) (2024)
- [ChatVLA: Unified Multimodal Understanding and Robot Control with Vision-Language-Action Model](https://mlsanity.com/paper/2502.14420/) (2025)
- [StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developing](https://mlsanity.com/paper/2604.05014/) (2026)
- [Actions as Language: Fine-Tuning VLMs into VLAs Without Catastrophic Forgetting](https://mlsanity.com/paper/2509.22195/) (2025)
- [When Vision Overrides Language: Evaluating and Mitigating Counterfactual Failures in VLAs](https://mlsanity.com/paper/2602.17659/) (2026)
- [LangForce: Bayesian Decomposition of Vision Language Action Models via Latent Action Queries](https://mlsanity.com/paper/2601.15197/) (2026)
- [TwinBrainVLA: Unleashing the Potential of Generalist VLMs for Embodied Tasks via Asymmetric Mixture-of-Transformers](https://mlsanity.com/paper/2601.14133/) (2026)
- [Restoring Linguistic Grounding in VLA Models via Train-Free Attention Recalibration](https://mlsanity.com/paper/2603.06001/) (2026)
- [vla-eval: A Unified Evaluation Harness for Vision-Language-Action Models](https://mlsanity.com/paper/2603.13966/) (2026)
- [How Do VLAs Effectively Inherit from VLMs?](https://mlsanity.com/paper/2511.06619/) (2025)
- [Limited Linguistic Diversity in Embodied AI Datasets](https://mlsanity.com/paper/2601.03136/) (2026)
- [UAM: A Dual-Stream Perspective on Forgetting in VLA Training](https://mlsanity.com/paper/2605.15735/) (2026)

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

- [In-Context Learning for Robots: Methods and Applications](https://mlsanity.com/paper/2609.36012/) (2026)

## Abstract (arXiv)

Vision-language-action (VLA) models are built on the premise that semantic understanding from pretrained language or vision-language backbones should guide robot action prediction. Yet robot fine-tuning is optimized as imitation over task-specific action distributions, and many evaluations can be solved through visual or instruction-action shortcuts. We introduce RoboSemanticBench (RSB), an embodied benchmark for diagnosing semantic grounding in action prediction: whether post-trained VLA models can use complex instruction semantics to select and manipulate the correct physical target. In each episode, a robot receives a multiple-choice math or general-knowledge question, observes candidate answer blocks, and must grasp the block corresponding to the correct answer. RSB covers controlled arithmetic, grade-school mathematical understanding, and commonsense or factual understanding under four-choice and ten-choice suites. Across representative VLA models, we find that many policies learn to grasp candidate blocks but select the semantically correct block at near-random or below-random rates after controlling for grasp success, revealing a persistent gap between backbone-level semantic competence and action prediction.