AI Paper Atlas

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

Embodied-R1: Reinforced Embodied Reasoning for General Robotic Manipulation

Yifu Yuan, Haiqin Cui, Yaoting Huang, Yibin Chen, Fei Ni, Zibin Dong, Pengyi Li, YAN ZHENG, Hongyao Tang, Jianye HAO

ICLR 2026 · Vision-language and multimodal › Robot action and navigation · approach: Memory and subgoal-based manipulation · 52 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
use RL (RFT) instead of SFT-only training (ablation)Embodied-R1 3B · Where2Placepointing accuracy: 41.25 -> 69.50Improved
use RL (RFT) instead of SFT-only training (ablation)Embodied-R1 3B · Part-Affordpointing accuracy: 40.20 -> 56.63Improved
use RL (RFT) instead of SFT-only training (ablation)Embodied-R1 3B · VABench-VMAE: 65.2 -> 45.0Improved
add ViRL common-sense data (ablation)Embodied-R1 3B · spatial benchmarksaverage rank: 3.4 -> 2.1Improved
add ViRL common-sense data (ablation)Embodied-R1 3B · SAT Realaccuracy: 73.9 -> 76.3Improved
add RL after SFT on spatial reasoning (ablation)Embodied-R1 3B · SAT Realaccuracy: 65.5 -> 76.3Improved
mix training data of multiple pointing abilities (ablation)Embodied-R1 · Part-Affordpointing accuracy: 51.25 -> 56.63Improved
mix training data of multiple pointing abilities (ablation)Embodied-R1 · VABench-Ppointing accuracy: 65.39 -> 66.00Improved
add point number constraint reward (ablation)Embodied-R1 · VABench-VMAE: 59.7 -> 44.97Improved
use visual trace branch instead of affordance pointsEmbodied-R1 · real-world xArmsuccess rate (%): 83.3 -> 87.5Improved
integrate Embodied-R1 visual trace into Diffusion PolicyDiffusion Policy · LIBERO averagesuccess rate (%): 64.4 -> 79.4Improved
use RGB-D dual-tower variant instead of RGBEmbodied-R1 · Open6DOR-Position overallaccuracy: 66.8 -> 94.3Improved

Later papers that compared with this method

2 later accepted papers report Embodied-R1 as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

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