Agentic-VLA: Efficient Online Adaptation for Vision-Language-Action Models
The article introduces Agentic-VLA, a new framework for improving Vision-Language-Action models in robotic manipulation. This framework addresses limitations in generalization and training efficiency through innovative techniques. The evaluation shows significant performance improvements across various benchmarks, indicating its potential for adaptive learning in real-world applications.
- ▪Agentic-VLA enhances VLA models by enabling efficient online adaptation.
- ▪The framework includes Adaptive Reward Synthesis, Language-Guided Exploration, and Experience Memory.
- ▪Agentic-VLA achieved a 12.3% improvement on long-horizon tasks and a 28.5% increase in 1-shot learning.
arXiv cs.AI files mainly under ai research. We currently carry 1,128 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | arXiv cs.AI |
| Canonical URL | https://arxiv.org/abs/2605.22896 |
| Publication time | Mon, 25 May 2026 00:00:00 -0400 |
| Retrieval time | 2026-05-25T04:07:35.648Z |
| Last seen | 2026-05-25T04:07:35.648Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | bvXTfEJN6ClJ · 2 stories |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
Computer Science > Robotics arXiv:2605.22896 (cs) [Submitted on 21 May 2026] Title:Agentic-VLA: Efficient Online Adaptation for Vision-Language-Action Models Authors:Ruofan Jin, Zaixi Zhang 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.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at arXiv cs.AI.
Discussion
0 commentsMore from arXiv cs.AI
