Agentic-VLA: Efficient Online Adaptation for Vision-Language-Action Models

• URL: http://arxiv.org/abs/2605.22896v1
• Date: Thu, 21 May 2026 15:24:21 GMT
• Title: Agentic-VLA: Efficient Online Adaptation for Vision-Language-Action Models
• Abstract summary: Vision-Language-Action (VLA) models have emerged as a promising paradigm for robotic manipulation by leveraging pre-trained vision-language representations.<n>Current VLA training methods suffer from two critical limitations: poor generalization to novel environments and low training efficiency requiring extensive demonstrations.<n>We introduce Agentic-VLA, an agentic training framework that enablesVLAs to efficiently adapt online through three key innovations.
• Score: 13.803928398939847
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Vision-Language-Action (VLA) models have emerged as a promising paradigm for robotic manipulation by leveraging pre-trained vision-language representations. However, current VLA training methods suffer from two critical limitations: poor generalization to novel environments and low training efficiency requiring extensive demonstrations. We introduce Agentic-VLA, an agentic training framework that enables VLAs to efficiently adapt online through three key innovations: (1) Adaptive Reward Synthesis, which dynamically generates and adjusts reward functions based on the VLA's current capabilities and task complexity, decomposing complex tasks into learnable sub-goals for curriculum learning; (2) Language-Guided Exploration, where a critic model provides structured guidance for systematic exploration rather than random sampling; and (3) Experience Memory,which stores and retrieves task-relevant policy weights for warm-starting adaptation to similar tasks. We evaluate Agentic-VLA on the LIBERO benchmark, achieving substantial improvements: +12.3% on long-horizon tasks, +28.5% in 1-shot learning, and enabling cross-task transfer from 0% to 31.2% without task-specific demonstrations. Our framework also demonstrates 2.4x faster convergence compared to existing online adaptation methods. Beyond LIBERO, Agentic-VLA retains its advantage on the dual-arm RoboTwin 2.0 benchmark, including under its randomized Hard setting. These results establish Agentic-VLA as a significant step toward truly adaptive VLA systems capable of continuous learning in deployment.

Related papers

• EXPO-FT: Sample-Efficient Reinforcement Learning Finetuning for Vision-Language-Action Models [84.73890225707264]
  We present EXPO-FT, a system for stable, sample-efficient RL finetuning of pretrained VLA policies.<n>Our system achieves perfect task performance (30/30 successes) across all evaluated tasks within an average of 19.1 minutes of online robot data.<n>We release an open-source robustness with the aim of facilitating broader adoption of RL finetuning of VLA models in robotics.
  arXiv  Detail & Related papers  (2026-05-25T06:31:03Z)
• AceGRPO: Adaptive Curriculum Enhanced Group Relative Policy Optimization for Autonomous Machine Learning Engineering [52.67783579040657]
  AceGRPO is a machine learning system that prioritizes tasks at the agent's learning frontier to maximize learning efficiency.<n>Our trained Ace-30B model achieves a 100% valid submission rate on MLE-Bench-Lite, approaches the performance of proprietary frontier models, and outperforms larger open-source baselines.
  arXiv  Detail & Related papers  (2026-02-08T10:55:03Z)
• On-the-Fly VLA Adaptation via Test-Time Reinforcement Learning [61.38273866396522]
  Vision-Language-Action models have emerged as a powerful paradigm for general-purpose robot learning.<n>Current methods remain unsuitable for challenging simulated- or physical-world deployments.<n>We introduce a Test-Time Reinforcement Learning for VLAs framework that enables on-the-fly policy adaptation during inference.
  arXiv  Detail & Related papers  (2026-01-11T01:51:30Z)
• EVOLVE-VLA: Test-Time Training from Environment Feedback for Vision-Language-Action Models [57.75717492488268]
  Vision-Language-Action (VLA) models have advanced robotic manipulation by leveraging large language models.<n>Supervised Finetuning (SFT) requires hundreds of demonstrations per task, rigidly memorizing trajectories, and failing to adapt when deployment conditions deviate from training.<n>We introduce EVOLVE-VLA, a test-time training framework enabling VLAs to continuously adapt through environment interaction with minimal or zero task-specific demonstrations.
  arXiv  Detail & Related papers  (2025-12-16T18:26:38Z)
• Sample-Efficient Robot Skill Learning for Construction Tasks: Benchmarking Hierarchical Reinforcement Learning and Vision-Language-Action VLA Model [9.025728945376468]
  This study evaluates two leading approaches for teaching construction robots new skills.<n>The goal is to understand both task performance and the practical effort needed to deploy each approach on real jobs.
  arXiv  Detail & Related papers  (2025-12-16T02:56:13Z)
• SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning [81.7764584515496]
  Vision-Language-Action (VLA) models have emerged as a powerful paradigm for robotic manipulation.<n>These models face two fundamental challenges: scarcity and high cost of large-scale human-operated robotic trajectories.<n>We introduce SimpleVLA-RL, an efficient reinforcement learning framework tailored for VLA models.
  arXiv  Detail & Related papers  (2025-09-11T17:59:17Z)
• InstructVLA: Vision-Language-Action Instruction Tuning from Understanding to Manipulation [43.83789393525928]
  InstructVLA is an end-to-end vision-language model that preserves the flexible reasoning of large vision-language models (VLMs) while delivering leading manipulation performance.<n>InstructVLA introduces a novel training paradigm, Vision-Language-Action Instruction Tuning (VLA-IT), which employs multimodal training with mixture-of-experts adaptation.<n>On in-domain SimplerEnv tasks, InstructVLA achieves 30.5% improvement over SpatialVLA.
  arXiv  Detail & Related papers  (2025-07-23T13:57:06Z)
• Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success [100.226572152954]
  We present an optimized fine-tuning recipe for vision-language-action models (VLAs)<n>Our recipe boosts OpenVLA's average success rate across four task suites from 76.5% to 97.1% while increasing action generation throughput by 26$times$.<n>In real-world evaluations, our fine-tuning recipe enables OpenVLA to successfully execute dexterous, high-frequency control tasks on a bimanual ALOHA robot.
  arXiv  Detail & Related papers  (2025-02-27T00:30:29Z)
• DexVLA: Vision-Language Model with Plug-In Diffusion Expert for General Robot Control [7.626715427413578]
  Vision-language-action (VLA) models have shown promise for generalizable robot skills.<n>Current VLA models often focus on scaling the vision-language model (VLM) component, while the action space representation remains a critical bottleneck.<n>This paper introduces DexVLA, a novel framework designed to enhance the efficiency and generalization capabilities ofVLAs for complex, long-horizon tasks.
  arXiv  Detail & Related papers  (2025-02-09T11:25:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.