AI Paper Atlas

Research map / Multi-agent systems and games / Human-AI and goal-conditioned

Arcadia: Toward a Full-Lifecycle Framework for Embodied Lifelong Learning

Minghe Gao, Juncheng Li, Yuze Lin, Xuqi Liu, Jiaming Ji, Xiaoran Pan, Zihan Xu, Xian Li, Mingjie Li, Wei Ji, Rong Wei, Rui Tang and 6 more

CVPR 2026 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Embodied agent learning · 2 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 real-world feedback loop (ablation)Arcadia · VLN-CE-IsaacSR: 48.7 -> 50.1Improved
add real-world feedback loop (ablation)Arcadia · BridgeData V2success rate: 47.3 -> 52.4Improved
use dynamic generative scene reconstruction instead of retrieval-based (ablation)Arcadia · LIBEROsuccess rate: 81.4 -> 87.2Improved
use task-aligned autonomously collected data instead of static ScaleVLN/RLBench data (ablation)Arcadia · LIBEROsuccess rate: 72.9 -> 87.2Improved
use task-aligned autonomously collected data instead of static data (ablation)Arcadia · VLN-CE-IsaacSR: 43.0 -> 50.1Improved
use dense structured feedback instead of binary success/failure (ablation)Arcadia · VLN-CE-IsaacSR: 48.8 -> 50.1Improved
add joint VLN and VLA training on shared backbone (ablation)Arcadia · VLN-CE-IsaacSR: 49.8 -> 50.1No clear effect
add joint VLN and VLA training on shared backbone (ablation)Arcadia · LIBEROsuccess rate: 87.0 -> 87.2No clear effect
replace NaVILA external data with Arcadia self-collected data (no feedback)NaVILA · R2R Val-UnseenSR: 51.6 -> 54.2Improved
replace OpenVLA training data with Arcadia simulation data (no feedback)OpenVLA · LIBERO-10success rate: 53.7 -> 74.0Improved
apply Arcadia in real-world zero-shot navigationNaVILA · Real-world navigationsuccess rate: 13% -> 46%Improved

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