AI Paper Atlas

Research map / Vision-language and multimodal / Robot action and navigation

VLA-R1: Enhancing Reasoning in Vision-Language-Action Models

Angen Ye, Zeyu Zhang, Boyuan Wang, Xiaofeng Wang, Dapeng Zhang, Zheng Zhu

ECCV 2026 · Vision-language and multimodal › Robot action and navigation · approach: Vision-language-action foundation models · 50 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add chain-of-thought SFT (ablation)VLA-R1 · In-domain affordanceIoU: 23.74 -> 28.37Improved
add chain-of-thought SFT (ablation)VLA-R1 · In-domain trajectoryAvg distance: 128.38 -> 124.6Improved
add RLVR (GRPO) after CoT SFT (ablation)VLA-R1 · In-domain affordanceIoU: 28.37 -> 36.51Improved
add RLVR (GRPO) after CoT SFT (ablation)VLA-R1 · In-domain trajectoryAvg distance: 124.60 -> 91.74Improved
VLA-R1 versus ManipLVM-R1 baselineVLA-R1-3B · In-domain affordanceIoU: 31.00 -> 36.51 (~17.78%)Improved
VLA-R1 versus ManipLVM-R1 baselineVLA-R1-3B · In-domain trajectoryAvg distance: 110.87 -> 91.74 (~17.25% reduction)Improved
VLA-R1 versus ManipLVM-R1 baselineVLA-R1-3B · Out-of-domain affordanceIoU: 28.00 -> 33.96Improved
VLA-R1 versus ManipLVM-R1 baselineVLA-R1-3B · Out-of-domain trajectoryAvg distance: 131.99 -> 93.90Improved
VLA-R1 versus NORA in simulationVLA-R1 · Simulation trajectorysuccess rate: 5% -> 70%Improved
VLA-R1 versus NORA in simulationVLA-R1 · Simulation affordancesuccess rate: 40% -> 55%Improved
VLA-R1 versus NORA in real worldVLA-R1 · Real-world affordancesuccess rate: 35% -> 62.5%Improved
VLA-R1 versus NORA in real worldVLA-R1 · Real-world trajectorysuccess rate: 47.5% -> 75%Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy