AI Paper Atlas

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

BeTTER: Diagnose the Illusion of Embodied Reasoning in Vision-Language-Action Models

Haiweng Xu, Sipeng Zheng, Hao Luo, Wanpeng Zhang, Zongqing Lu

ECCV 2026 · Vision-language and multimodal › Robot action and navigation · approach: Embodied multimodal LLM agents · 0 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
scale InternVL-3.5 backbone up from 2B to 8B (ablation)InternVL-3.5 · RefSp.score: 6.00 -> 27.50Improved
scale InternVL-3.5 backbone up from 2B to 8B (ablation)InternVL-3.5 · EgoPlanscore: 33.38 -> 40.80Improved
add VLM-VLA co-training data to 2B model (ablation)InternVL-3.5 2B · RefSp.score: 6.00 -> 29.50Improved
add VLM-VLA co-training data to 2B model (ablation)InternVL-3.5 2B · EgoPlanscore: 33.38 -> 31.95No clear effect
use multi-patch high-res input instead of single 224px image (ablation)InternVL-3.5 2B + VLM + VLA data · RefSp.score: 7.50 -> 29.50Improved
add VLM pre-training to VLA-only pre-training (ablation)VLA policy · CALVIN ABC->Davg length: 3.86 -> 4.09Improved
add VLM pre-training to VLA-only pre-training (ablation)VLA policy · LIBEROsuccess rate: 96.3 -> 97.2No clear effect
add VLA (OXE) pre-training vs no pre-training (ablation)VLA policy · LIBEROsuccess rate: 97.4 -> 96.3No clear effect
add VLA (OXE) pre-training vs no pre-training (ablation)VLA policy · CALVIN ABC->Davg length: 3.67 -> 3.86Improved
test on unseen composition B->CGR00T-N1.6 · Packing Fast Food Ordersuccess (%): 75.0/40.0 -> 15.0Hurt
recombine spatial and semantic instructions under counterfactual layoutsGR00T-N1.6 · coffee tasktarget success (%): spatial 100.0%; semantic 5.0%Mixed

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