Diffusion and flow matching models have emerged as powerful robot policies, enabling Vision-Language-Action (VLA) models to generalize across diverse scenes and instructions. Yet, when trained via imitation learning, their high generative capacity makes them sensitive to noise in human demonstrations: jerks, pauses, and jitter which reduce action coherence. Reduced action coherence causes instability and trajectory drift during deployment, failures that are catastrophic in fine-grained manipulation where precision is crucial. In this paper, we present Action Coherence Guidance (ACG) for VLA models, a training-free test-time guidance algorithm that improves action coherence and thereby yields performance gains. Evaluated on RoboCasa, DexMimicGen, and real-world SO-101 tasks, ACG consistently improves action coherence and boosts success rates across diverse manipulation tasks. Code and project page are available at https://github.com/DAVIAN-Robotics/ACG and https://DAVIAN-Robotics.github.io/ACG , respectively.
@article{arxiv.2510.22201,
title = {ACG: Action Coherence Guidance for Flow-based Vision-Language-Action models},
author = {Minho Park and Kinam Kim and Junha Hyung and Hyojin Jang and Hoiyeong Jin and Jooyeol Yun and Hojoon Lee and Jaegul Choo},
journal= {arXiv preprint arXiv:2510.22201},
year = {2026}
}