# RADAR: Benchmarking Vision-Language-Action Generalization via Real-World Dynamics, Spatial-Physical Intelligence, and Autonomous Evaluation

arXiv: https://arxiv.org/abs/2602.10980 · HTML: https://mlsanity.com/paper/2602.10980/

## Key facts

- Cited by 4 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 12 of its 20 references that are in the map.
- First posted on arXiv 11 Feb 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, 12 of 12)

- [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)
- [LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning](https://mlsanity.com/paper/2306.03310/) (2023)
- [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)
- [LIBERO-Plus: In-depth Robustness Analysis of Vision-Language-Action Models](https://mlsanity.com/paper/2510.13626/) (2025)
- [ManiSkill3: GPU Parallelized Robotics Simulation and Rendering for Generalizable Embodied AI](https://mlsanity.com/paper/2410.00425/) (2024)
- [GELLO: A General, Low-Cost, and Intuitive Teleoperation Framework for Robot Manipulators](https://mlsanity.com/paper/2309.13037/) (2023)
- [VLABench: A Large-Scale Benchmark for Language-Conditioned Robotics Manipulation with Long-Horizon Reasoning Tasks](https://mlsanity.com/paper/2412.18194/) (2024)
- [RoboTwin: Dual-Arm Robot Benchmark with Generative Digital Twins](https://mlsanity.com/paper/2504.13059/) (2025)
- [AutoEval: Autonomous Evaluation of Generalist Robot Manipulation Policies in the Real World](https://mlsanity.com/paper/2503.24278/) (2025)
- [VLA Models Are More Generalizable Than You Think: Revisiting Physical and Spatial Modeling](https://mlsanity.com/paper/2512.02902/) (2025)
- [SIRI-Bench: Challenging VLMs' Spatial Intelligence through Complex Reasoning Tasks](https://mlsanity.com/paper/2506.14512/) (2025)

## Built on by (most cited first, 4 of 4)

- [TAG: Target-Agnostic Guidance for Stable Object-Centric Inference in Vision-Language-Action Models](https://mlsanity.com/paper/2603.24584/) (2026)
- [EgoDyn-Bench: Evaluating Ego-Motion Understanding in Vision-Centric Foundation Models for Autonomous Driving](https://mlsanity.com/paper/2604.22851/) (2026)
- [The Moving Eye: Enhancing VLA Spatial Generalization via Hybrid Dynamic Data Collection](https://mlsanity.com/paper/2607.02322/) (2026)
- [RawVLA: Embodied Neural Image Signal Processor For Robotic Manipulation](https://mlsanity.com/paper/2609.37530/) (2026)

## Abstract (arXiv)

VLA models have achieved remarkable progress in embodied intelligence; however, their evaluation remains largely confined to simulations or highly constrained real-world settings. This mismatch creates a substantial reality gap, where strong benchmark performance often masks poor generalization in diverse physical environments. We identify three systemic shortcomings in current benchmarking practices that hinder fair and reliable model comparison. (1) Existing benchmarks fail to model real-world dynamics, overlooking critical factors such as dynamic object configurations, robot initial states, lighting changes, and sensor noise. (2) Current protocols neglect spatial--physical intelligence, reducing evaluation to rote manipulation tasks that do not probe geometric reasoning. (3) The field lacks scalable fully autonomous evaluation, instead relying on simplistic 2D metrics that miss 3D spatial structure or on human-in-the-loop systems that are costly, biased, and unscalable. To address these limitations, we introduce RADAR (Real-world Autonomous Dynamics And Reasoning), a benchmark designed to systematically evaluate VLA generalization under realistic conditions. RADAR integrates three core components: (1) a principled suite of physical dynamics; (2) dedicated tasks that explicitly test spatial reasoning and physical understanding; and (3) a fully autonomous evaluation pipeline based on 3D metrics, eliminating the need for human supervision. We apply RADAR to audit multiple state-of-the-art VLA models and uncover severe fragility beneath their apparent competence. Performance drops precipitously under modest physical dynamics, with the expectation of 3D IoU declining from 0.261 to 0.068 under sensor noise. Moreover, models exhibit limited spatial reasoning capability. These findings position RADAR as a necessary bench toward reliable and generalizable real-world evaluation of VLA models.