# Flow-Support-Weighted Proposals for Test-Time Verified VLA Policies

arXiv: https://arxiv.org/abs/2610.14588 · HTML: https://mlsanity.com/paper/2610.14588/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Reinforcement learning and post-training, one of 13 directions in Vision-language-action models.
- Builds on 28 of its 33 references that are in the map.
- First posted on arXiv 10 Oct 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, 28 of 28)

- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Neural Ordinary Differential Equations](https://mlsanity.com/paper/1806.07366/) (2018)
- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [π0: A Vision-Language-Action Flow Model for General Robot Control](https://mlsanity.com/paper/2410.24164/) (2024)
- [LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning](https://mlsanity.com/paper/2306.03310/) (2023)
- [Improving and generalizing flow-based generative models with minibatch optimal transport](https://mlsanity.com/paper/2302.00482/) (2023)
- [FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Models](https://mlsanity.com/paper/1810.01367/) (2018)
- [RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robots](https://mlsanity.com/paper/2406.02523/) (2024)
- [LIBERO-Plus: In-depth Robustness Analysis of Vision-Language-Action Models](https://mlsanity.com/paper/2510.13626/) (2025)
- [HybridVLA: Collaborative Diffusion and Autoregression in a Unified Vision-Language-Action Model](https://mlsanity.com/paper/2503.10631/) (2025)
- [StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developing](https://mlsanity.com/paper/2604.05014/) (2026)
- [Learning Sampling Distributions for Robot Motion Planning](https://mlsanity.com/paper/1709.05448/) (2017)
- [Sampling-Efficient Test-Time Scaling: Self-Estimating the Best-of-N Sampling in Early Decoding](https://mlsanity.com/paper/2503.01422/) (2025)
- [RoboMonkey: Scaling Test-Time Sampling and Verification for Vision-Language-Action Models](https://mlsanity.com/paper/2506.17811/) (2025)
- [Verifier-free Test-Time Sampling for Vision-Language-Action Models](https://mlsanity.com/paper/2510.05681/) (2025)
- [Sample, Don't Search: Rethinking Test-Time Alignment for Language Models](https://mlsanity.com/paper/2504.03790/) (2025)
- [EVOLVE-VLA: Test-Time Training from Environment Feedback for Vision-Language-Action Models](https://mlsanity.com/paper/2512.14666/) (2025)
- [Scaling Verification Can Be More Effective than Scaling Policy Learning for Vision-Language-Action Alignment](https://mlsanity.com/paper/2602.12281/) (2026)
- [RoVer: Robot Reward Model as Test-Time Verifier for Vision-Language-Action Model](https://mlsanity.com/paper/2510.10975/) (2025)
- [LIBERO-Para: A Diagnostic Benchmark and Metrics for Paraphrase Robustness in VLA Models](https://mlsanity.com/paper/2603.28301/) (2026)
- [TTT-VLA: Test-Time Latent Prompt Optimization for Vision-Language-Action Models](https://mlsanity.com/paper/2606.03127/) (2026)
- [Training Vision-Language-Action Models with Dense Embodied Chain-of-Thought Supervision](https://mlsanity.com/paper/2606.30552/) (2026)
- [Shifting Uncertainty to Critical Moments: Towards Reliable Uncertainty Quantification for VLA Model](https://mlsanity.com/paper/2603.18342/) (2026)
- [Pre-VLA: Preemptive Runtime Verification for Reliable Vision-Language-Action and World-Model Rollouts](https://mlsanity.com/paper/2605.22446/) (2026)
- [EVE: A Generator-Verifier System for Generative Policies](https://mlsanity.com/paper/2512.21430/) (2025)
- [VeriSpace: Spatially Grounded Action Verification for Vision-Language-Action Models](https://mlsanity.com/paper/2606.10568/) (2026)
- [Unleashing More Actions via Action Compositional Training for VLA Models](https://mlsanity.com/paper/2607.00351/) (2026)
- [MAGMA-GEN: Validated Recovery Supervision from Ambiguous Failures via Counterfactual Re-Execution](https://mlsanity.com/paper/2609.20056/) (2026)

## Abstract (arXiv)

Test-time sampling promises to turn one action prediction into a set of distinct executable candidates that a verifier can choose among. Downstream fine-tuning works against that promise. A vision-language-action model trained to solve one task distribution concentrates its flow-matching decoder around the dominant demonstrated action, so repeated samples differ only marginally and the verifier receives many copies of one decision. We call this proposal contraction and identify it as a key constraint on test-time scaling: repeated samples can remain highly redundant as the candidate budget grows. Action Dynamic Sampling (ADS) alleviates the constraint on the proposal side, during training. At each training step, ADS integrates K additional trajectories from the current policy under fresh base noise, scores each by the flow support along its path with a Hutchinson trace estimator, and corrects the policy's local action distribution toward this weighted set through a detached finite-set KL term. Training cost rises; deployment cost is unchanged. Across simulation and four physical-robot tasks, ADS raises proposal spread without the success penalty that Gaussian perturbation incurs, lifts oracle best-of-8 success on RoboCasa from 57.6% to 63.0%, improves fixed verifiers by 2.4 to 4.9 points in simulation, and raises TokenPB by up to 13.0 points on real-world manipulation.