GenieReasoner: Unified Embodied Reasoning and Control
Figure 1 : We introduce the GenieReasoner system. (Left) Our system leverages large-scale general and embodied multimodal data to co-optimize high-level reasoning and low-level control within a unified autoregressive transformer. (Center) To bridge the gap between discrete planning and continuous execution, we introduce FACT, a novel action tokenizer that utilizes flow matching to reconstruct high-fidelity trajectories from quantized tokens. (Right) This unified design yields state-of-the-art results: GenieReasoner achieves a 41% accuracy improvement on our proposed ERIQ for embodied reasoning and demonstrates significantly lower reconstruction error (MSE) compared to π 0 \pi_{0} -FAST. Consequently, our model outperforms flow-based baselines (e.g., π 0.5 \pi_{0.5} ) in real-world robot manipulation tasks.
Paper context
Paper title: Unified Embodied VLM Reasoning with Robotic Action via Autoregressive Discretized Pre-training Abstract: General-purpose robotic systems operating in open-world environments must achieve both broad generalization and high-precision action execution, a combination that remains challenging for existing Vision-Language-Action (VLA) models. While large Vision-Language Models (VLMs) improve semantic generalization, insufficient embodied reasoning leads to brittle behavior, and conversely, strong reasoning alone is inadequate without precise control. To provide a decoupled and quantitative assessment of this bottleneck, we introduce Embodied Reasoning Intelligence Quotient (ERIQ), a large-scale embodied reasoning benchmark in robotic manipulation, comprising 6K+ question-answer pairs across four reasoning dimensions. By decoupling reasoning from execution, ERIQ enables systematic evaluation and reveals a strong positive correlation between embodied reasoning capability and end-to-end VLA generalization. To bridge the gap from reasoning to precise execution, we propose FACT, a flow-matching-based action tokenizer that converts continuous control into discrete sequences while preserving high-fidelity trajectory reconstruction. The resulting GenieReasoner jointly optimizes reasoning and action in a unified space, outperforming both continuous-action and prior discrete-action baselines in real-world tasks. Together, ERIQ and FACT provide a principled framework for diagnosing and overcoming the reasoning-precision trade-off, advancing robust, general-purpose robotic manipulation. Project p Passages referencing this figure: io/GenieReasoner/ I Introduction Figure 1 : We introduce the GenieReasoner system. This enables the GenieReasoner(illustrated in Figure 1 ) to co-optimize reasoning and action within a unified gradient space.
