cs.RONov 18, 2026

RePlan-VLA: Progress-Aware Replanning for Long-Horizon Vision-Language-Action Models

Authors: Apoorva Vashisth, Manav Kulshrestha, Damon Conover, Zachary Kingston, Aniket Bera

Organizations: Purdue University, West Lafayette, IN, USA · DEVCOM ARL, Adelphi, MD, USA

Abstract

Vision-Language-Action (VLA) models have emerged as a promising paradigm for general-purpose robotic manipulation, yet their performance often degrades on long-horizon tasks that require multiple interdependent manipulations. Instead of burdening the VLA policies with long-horizon reasoning, memory, action generation, progress tracking, and error recovery, we argue for leveraging their short-horizon manipulation capabilities within an execution-aware framework. To this end, we introduce RePlan-VLA, a VLA-agnostic framework that translates a VLA's short-horizon capabilities into reliable long-horizon execution. RePlan-VLA explicitly monitors the robot's motion for progress evaluation, and adaptively revises the future plan based on observed outcomes. We preserve the underlying VLA policy entirely, requiring no additional fine-tuning. Experiments on RoboCasa365 and CALVIN benchmarks show an improvement of 21.9% and 10.4% in success rate over the next strongest baseline. We also validate our approach for real-world deployment on a Franka Research 3 robot.

Figures & tables

Explore similar work

CardsList
  1. Towards Long-horizon Embodied Agents with Tool-Aligned Vision-Language-Action Models

    May 13, 2026Zixing Lei, Changxing Liu, Yichen Xiong +5Long-Horizon Robotic ManipulationTool-Using Vision-Language Agents

  2. Long-Horizon Manipulation via Trace-Conditioned VLA Planning

    Apr 23, 2026Isabella Liu, An-Chieh Cheng, Rui Yan +7Long-Horizon Robotic ManipulationLanguage-Conditioned Robot Manipulation

  3. PHR-VLA: Planning Horizon Reasoning for Vision-Language-Action Models

    Aug 27, 2026Davood Soleymanzadeh, Kaidi Zhang, Zhiyuan Zhang +4Vision-Language-Action ModelsReasoning for VLAs