Reflective VLA: In-Context Action Consequences Make VLAs Generalize
Most vision-language-action (VLA) models are reactive, predicting the next action from the current observation alone, which limits generalization under distribution shift. This paper proposes Reflective VLA, which conditions decisions on a context of observation-action-consequence triplets, exposing deployment-specific action-effect mappings. On LIBERO-Plus and LIBERO-Plus-Hard, it improves success rates by 5.4 and 4.2 percentage points, with ablations confirming action consequences as the key.
[2606.25215] Reflective VLA: In-Context Action Consequences Make VLAs Generalize
[Submitted on 23 Jun 2026]
Title:Reflective VLA: In-Context Action Consequences Make VLAs Generalize
View a PDF of the paper titled Reflective VLA: In-Context Action Consequences Make VLAs Generalize, by Qing Lian and 2 other authors
View PDF HTML (experimental)
Abstract:Most vision-language-action (VLA) models are reactive: they predict the next action from the current instruction and observation, implicitly assuming that the current observation fully specifies the action-relevant state. In embodied control, however, embodiment-specific factors such as camera-to-robot geometry, robot calibration, or systematic actuation bias are often hard to identify from a single observation. As a result, reactive policies cannot reliably disambiguate these factors in general, overfitting to training environments and generalizing poorly at deployment. We propose Reflective VLA, which conditions each decision on a context of observation-action-consequence triplets. Each triplet records not only what the robot observed and executed, but also how the scene changed afterward, exposing the deployment-specific mapping from actions to observed effects. Architecturally, Reflective VLA routes all observation modalities through the VLM under shared attention, so the action expert reasons directly over past triplets and the current observation. A block-causal mask enables parallel multi-frame training without leakage and supports KV-cached real-time inference. On standard LIBERO and SimplerEnv-Bridge, Reflective VLA preserves strong in-distribution performance. Under distribution shift on LIBERO-Plus and the harder LIBERO-Plus-Hard, it improves average success rate by 5.4 and 4.2 percentage points over a matched reactive baseline. Ablations with a matched history-only baseline further show that action consequences -- rather than additional context length alone -- are the key to cross-environment generalization. Project page: this https URL
Subjects:
Computer Vision and Pattern Recognition (cs.CV); Robotics (cs.RO)
Cite as: arXiv:2606.25215 [cs.CV]
(or arXiv:2606.25215v1 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2606.25215
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Qing Lian [view email] [v1] Tue, 23 Jun 2026 22:23:35 UTC (3,059 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Reflective VLA: In-Context Action Consequences Make VLAs Generalize, by Qing Lian and 2 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.CV
new | recent | 2026-06
Change to browse by:
cs cs.RO
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?)