Agentic-VLA: Efficient Online Adaptation for Vision-Language-Action Models
Agentic-VLA introduces an agentic training framework that enables Vision-Language-Action (VLA) models to adapt efficiently online via three key innovations: Adaptive Reward Synthesis, Language-Guided Exploration, and Experience Memory. Evaluated on LIBERO benchmark, it achieves +12.3% on long-horizon tasks, +28.5% in 1-shot learning, and cross-task transfer from 0% to 31.2%. It also shows 2.4x faster convergence and retains advantages on the dual-arm RoboTwin 2.0 benchmark.
Article intelligence
Key points
- Adaptive Reward Synthesis: dynamically generates reward functions, decomposing complex tasks into learnable sub-goals.
- Language-Guided Exploration: a critic provides structured guidance for systematic exploration.
- Experience Memory: stores and retrieves policy weights for warm-starting similar tasks.
- Outperforms existing methods on LIBERO and RoboTwin 2.0, with 2.4x faster convergence.
Why it matters
This matters because adaptive Reward Synthesis: dynamically generates reward functions, decomposing complex tasks into learnable sub-goals.
Technical impact
May affect model selection, inference cost, product capability, and evaluation benchmarks.
[2605.22896] Agentic-VLA: Efficient Online Adaptation for Vision-Language-Action Models
[Submitted on 21 May 2026]
Title:Agentic-VLA: Efficient Online Adaptation for Vision-Language-Action Models
View a PDF of the paper titled Agentic-VLA: Efficient Online Adaptation for Vision-Language-Action Models, by Ruofan Jin and Zaixi Zhang
View PDF HTML (experimental)
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.
Comments: Total 15 pages
Subjects:
Robotics (cs.RO); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
Cite as: arXiv:2605.22896 [cs.RO]
(or arXiv:2605.22896v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2605.22896
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Zaixi Zhang [view email] [v1] Thu, 21 May 2026 15:24:21 UTC (1,975 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Agentic-VLA: Efficient Online Adaptation for Vision-Language-Action Models, by Ruofan Jin and Zaixi Zhang
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.RO
new | recent | 2026-05
Change to browse by:
cs cs.AI cs.LG
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
Loading...
Data provided by:
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)