Recent advances in deep thinking models have demonstrated remarkable reasoning capabilities on mathematical and coding tasks. However, their effectiveness in embodied domains which require continuous interaction with environments through image action interleaved trajectories remains largely -unexplored. We present Embodied Reasoner, a model that extends o1 style reasoning to interactive embodied search tasks. Unlike mathematical reasoning that relies primarily on logical deduction, embodied scenarios demand spatial understanding, temporal reasoning, and ongoing self-reflection based on interaction history. To address these challenges, we synthesize 9.3k coherent Observation-Thought-Action trajectories containing 64k interactive images and 90k diverse thinking processes (analysis, spatial reasoning, reflection, planning, and verification). We develop a three-stage training pipeline that progressively enhances the model's capabilities through imitation learning, self-exploration via rejection sampling, and self-correction through reflection tuning. The evaluation shows that our model significantly outperforms those advanced visual reasoning models, e.g., it exceeds OpenAI o1, o3-mini, and Claude-3.7 by +9\%, 24\%, and +13\%. Analysis reveals our model exhibits fewer repeated searches and logical inconsistencies, with particular advantages in complex long-horizon tasks. Real-world environments also show our superiority while exhibiting fewer repeated searches and logical inconsistency cases.

翻译：近期深度思维模型在数学与编程任务上展现出卓越的推理能力。然而，其在需要通过图像-动作交错轨迹与环境持续交互的具身领域中的有效性仍很大程度上未被探索。我们提出具身推理器，该模型将o1风格推理扩展至交互式具身搜索任务。与主要依赖逻辑演绎的数学推理不同，具身场景需要空间理解、时序推理以及基于交互历史的持续自我反思。为应对这些挑战，我们合成了9.3k条连贯的观察-思考-动作轨迹，包含64k张交互图像与90k个多样化思维过程（分析、空间推理、反思、规划与验证）。我们开发了一个三阶段训练流程，通过模仿学习、基于拒绝采样的自我探索以及反思调优的自我修正，逐步增强模型能力。评估表明，我们的模型显著优于先进的视觉推理模型，例如其性能超越OpenAI o1、o3-mini和Claude-3.7分别达+9%、24%和+13%。分析显示我们的模型表现出更少的重复搜索与逻辑不一致性，在复杂长程任务中具有特殊优势。真实环境测试同样证实了我们的优越性，同时展现出更少的重复搜索与逻辑不一致案例。