The year/Independent research

Paper 2606.11324

Embodied-R1.5: Evolving Physical Intelligence via Embodied Foundation Models

Published
Jun 2026
Research lab
Independent
Citations
1
GitHub
48 stars

01 In brief

Summary

Embodied-R1.5 is an 8B-parameter Embodied Foundation Model (EFM) that unifies three embodied reasoning dimensions—cognition and spatial reasoning, planning and correction, and pointing and location—within a single architecture.

It uses three automated data pipelines to build a 15B-token corpus and a multi-task balanced RL recipe to resolve heterogeneous task conflicts.

A Planner-Grounder-Corrector (PGC) closed-loop framework enables autonomous long-horizon task execution and self-correction.

The model achieves state-of-the-art results on 16 of 24 embodied VLM benchmarks, averaging 70.4% on 21 accuracy-based benchmarks, surpassing Gemini-Robotics-ER-1.5 and GPT-5.4 by 17.0% and 21.7%, respectively.

Fine-tuned with minimal action data into Embodied-R1.5-VLA, it outperforms baselines like π0.5 across four manipulation benchmark suites, including 92.4% on SimplerEnv Google Robot Visual Matching.

Zero-shot real-robot experiments validate instruction following, affordance grounding, articulated object manipulation, and long-horizon tasks.

The project open-sources model weights, datasets, training code, and EmbodiedEvalKit, an evaluation framework supporting 25+ benchmarks.

02 From the paper

Abstract

We introduce Embodied-R1.5, a unified Embodied Foundation Model (EFM) that integrates comprehensive embodied reasoning capabilities, spanning embodied cognition, task planning, correction, and pointing, within a single architecture toward general physical intelligence. Leveraging three automated data construction pipelines to significantly expand the data coverage of critical capabilities, we build a large-scale data system of over 15B tokens, and design a multi-task balanced RL recipe to alleviate heterogeneous task conflicts. We further introduce a Planner-Grounder-Corrector (PGC) closed-loop framework that enables a single model to autonomously execute and self-correct over long-horizon tasks. With only 8B parameters, Embodied-R1.5 achieves SOTA on 16 out of 24 embodied VLM benchmarks, surpassing leading models like Gemini-Robotics-ER-1.5 and GPT-5.4. Benefiting from the internalized embodied capabilities, Embodied-R1.5 can be fine-tuned into a VLA with only a small amount of data, outperforming leading VLA models like $π_{0.5}$ across 4 popular manipulation benchmark suites. We further conduct extensive zero-shot real-robot experiments, validating performance in instruction following, affordance grounding, articulated object manipulation, and long-horizon complex tasks, demonstrating strong generalization to the physical world. We open-source model weights, datasets, training code, and EmbodiedEvalKit, an evaluation framework tailored for embodied tasks, to facilitate future research in EFMs.