AI Paper Atlas

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

ACoT-VLA: Action Chain-of-Thought for Vision-Language-Action Models

Linqing Zhong, Yi Liu, Yifei Wei, Ziyu Xiong, Si Liu, Guanghui Ren

CVPR 2026 · Vision-language and multimodal › Robot action and navigation · approach: Vision-language-action foundation models · 37 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 Explicit Action Reasoner (EAR) (ablation)pi0.5 · LIBEROavg success rate: 96.9 -> 98.3Improved
add Implicit Action Reasoner (IAR) (ablation)pi0.5 · LIBEROavg success rate: 96.9 -> 98.1Improved
add both EAR and IAR (ablation)pi0.5 · LIBEROavg success rate: 96.9 -> 98.5Improved
add EAR (ablation)pi0.5 (frozen LLM) · LIBERO-Plus (SFT)avg success rate: 75.7 -> 83.7Improved
add IAR (ablation)pi0.5 (frozen LLM) · LIBERO-Plus (SFT)avg success rate: 75.7 -> 80.4Improved
add EAR and IAR (ablation)pi0.5 (frozen LLM) · LIBERO-Plus (SFT)avg success rate: 75.7 -> 84.1Improved
use Downsample KV-cache interaction in IAR instead of Query (ablation)IAR · LIBEROavg success rate: 97.0 -> 98.1Improved
use Downsample instead of Attention Pooling in IAR (ablation)IAR · LIBEROavg success rate: 97.3 -> 98.1Improved
double action head size to 600M (10 denoise steps) without EAR (ablation)pi0.5 (frozen LLM) · LIBERO / LIBERO-Plusavg success rate: LIBERO 96.6 -> 97.6; LIBERO-Plus 75.7 -> 74.9Mixed
increase denoising steps from 10 to 20 at 600M head (ablation)pi0.5 (frozen LLM) · LIBERO-Plusavg success rate: 74.9 -> 75.1No clear effect
add 300M EAR to matched-size baseline (600M head, 10 steps) (ablation)pi0.5 (frozen LLM) · LIBERO-Plusavg success rate: 74.9 -> 83.7Improved
scale EAR from 300M to 500M (ablation)ACoT-VLA · LIBERO-Plus (SFT)avg success rate: 83.7 -> 80.9Hurt

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