G0.5: One Autoregressive Stream for Robot Reasoning and Action

• URL: http://arxiv.org/abs/2608.11739v1
• Date: Wed, 12 Aug 2026 07:26:47 GMT
• Title: G0.5: One Autoregressive Stream for Robot Reasoning and Action
• Abstract summary: We introduce G0.5, a pretrained autoregressive VLA in which a single transformer decoder emits reasoning and action tokens under a single objective.<n>Because reasoning and action share a single set of weights, the pretrained VLM's capabilities carry over to physical behavior.<n>G0.5 surpasses state-of-the-art models across 7 independent regimes.
• Score: 43.43377463558725
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: The prevailing recipe for Vision-Language-Action (VLA) models couples a pretrained VLM with a separately trained flow-matching action expert. This makes the VLM a context encoder rather than a decision-maker. We introduce G0.5, a pretrained autoregressive VLA in which a single transformer decoder emits reasoning and action tokens under a single objective. Three components make this tractable at foundation-model scale: a learnable cross-embodiment action tokenizer that maps heterogeneous robot actions into a shared vocabulary; a native chain-of-thought stream interleaving task decomposition, object grounding, and action hints with action tokens; and a visual memory module that injects multi-second history through the vision encoder. Because reasoning and action share a single set of weights, the pretrained VLM's capabilities carry over to physical behavior: the model follows instructions closely, and prompts directly steer action granularity, task horizon, and out-of-distribution scene handling without further training. Pretrained on a large collection of robot datasets together with VQA samples, G0.5 surpasses state-of-the-art models across 7 independent regimes: real-world fine-tuning on R1lite and R1pro robots (76.7\% vs.\ 53.3\% for $π_{0.5}$ and 24.4\% for GR00T-N1.7), the 2025 BEHAVIOR Challenge on 50 long-horizon household mobile manipulation tasks using a generalist policy (31.4\% vs.\ 26.3\% for $π_{0.5}$ and 26.1\% for the challenge winner), DROID post-training followed by zero-shot transfer to an unseen environment and objects (82.5\%), a language-following Pick-and-Place benchmark, LIBERO (98.9\%), RoboTwin 2.0 (93.3\%), and SimplerEnv-Bridge (87.3\%).

Related papers

• WLA$^3$: World Latent Action Modeling for Semantics, Dynamics, and Kinematics [33.75014442121971]
  We introduce WLA$3$ (World Latent Action Modeling for Semantics, Dynamics, and Kinematics), a unified generalist policy model framework.<n> WLA$3$ reuses representations learned by a World Latent Action Model (WLAM) across semantics, dynamics, and kinematics.<n>On LARYBench, the final 32D latent action reaches 67.89% average classification accuracy.
  arXiv  Detail & Related papers  (2026-09-14T16:59:00Z)
• GE-Act 2.0: Pretraining and Scaling a World-Action Model for Robotic Manipulation [63.853929983870955]
  We introduce Genie Envisioner Act 2.0 (GE-Act 2.0), a world-action model whose trainable generative and action components are all from scratch on manipulation data.<n>It combines a control-oriented autoencoder (CoAE), a single-step visual planner (SVP), and an inverse dynamics model (IDM)<n>The components are then jointly trained with knowledge-aligned selective optimization (KASO), which reduces mismatched supervision by selecting only predicted futures judged behaviorally compatible with the recorded action.
  arXiv  Detail & Related papers  (2026-09-04T17:16:48Z)
• Beyond Data Scaling: Representation-Centric Continued Pre-training for Vision-Language-Action Models [120.24139942108405]
  Scaling robot data is crucial for building generalist Vision-Language-Action (VLA) models.<n>Under a fixed robot-data budget, continued pre-training must turn limited trajectories into transferable visual-action knowledge.<n>We propose VLAct, a VLA-oriented VLM backbone trained on broad, heterogeneous, multi-embodiment robot data.
  arXiv  Detail & Related papers  (2026-08-27T17:59:40Z)
• LM-X: Explainable Action Modeling with Progress, Event, and Uncertainty Prediction for Generalist Robot Manipulation [28.431160101245837]
  Generalist vision--language--action (VLA) policies learn long-horizon behavior mainly through short-horizon action prediction.<n>We introduce LM-X, which organizes prediction across task, event, and motor scales without claiming anatomical correspondence.
  arXiv  Detail & Related papers  (2026-08-26T13:05:29Z)
• Act with Intent: Distilling Behavior Intent for Vision-Language-Action Models [15.173629384871013]
  Vision-Language-Action (VLA) models can turn multimodal context into robot actions, but their action decoders are still trained largely by behavior cloning.<n>We propose Intention Distillation (INDI), which distills behavior-level intent into the action decoder.
  arXiv  Detail & Related papers  (2026-08-24T16:42:49Z)
• GigaBrain-WBC-0.5: A Behavior World Model for Robust Whole-Body Control with Environment Interaction [68.67772166423812]
  We present GigaBrain-WBC-0.5, the first Behavior World Model (BWM) for humanoid whole-body control.<n>Rather than a purely reactive tracker, we train a causal Transformer to jointly predict its next action, next state, and the distribution over its next latent behavior command.<n>An automatic terrain-annotation pipeline recovers full 3D contact geometry from retargeted motion, enabling terrain annotation at the scale of existing motion datasets.
  arXiv  Detail & Related papers  (2026-08-18T18:21:36Z)
• Training Vision-Language-Action Models with Dense Embodied Chain-of-Thought Supervision [26.793499191581315]
  Cross-embodiment transfer in vision-language-action (VLA) models remains challenging.<n>We present ZR-0, a 2.6 billion parameter end-to-end VLA model that uses dense Embodied Chain-of-Reason (ECoT) supervision to align cross-embodiment representations.
  arXiv  Detail & Related papers  (2026-06-29T16:48:48Z)
• Two Bridges, One Pathway: From VLMs to Generalizable VLAs with Embodied Trajectory-Coupled Data [93.7685703383343]
  Vision-language models (VLMs) are powerful general-purpose reasoners, yet converting them into robot control policies is surprisingly difficult.<n>We argue that this gap can be bridged gradually with the right intermediate data.<n>We show that mixing task-relevant out-of-distribution ETC data with a small amount of action data enables the model to generalize to novel visual-language conditions.
  arXiv  Detail & Related papers  (2026-06-07T08:57:51Z)
• Uni-LaViRA: Language-Vision-Robot Actions Translation for Unified Embodied Navigation [60.07205156194741]
  Embodied navigation requires an agent to map language and visual observations to a stream of spatial actions that drive a real robot through environments it has never seen.<n>We present Uni-LaViRA, a unified agentic architecture that extends the same insight to four task families and to four heterogeneous real robots.
  arXiv  Detail & Related papers  (2026-05-26T18:52:04Z)
• FineVLA: Fine-Grained Instruction Alignment for Steerable Vision-Language-Action Policies [26.96931937675281]
  FineVLA is an open framework for action-aligned fine-grained VLA supervision.<n>It unifies 972,247 trajectories across 85K tasks from 10 open-source robot datasets.<n>It includes a benchmark with 500 videos, 10,816 atomic facts, and 1,030 VQA questions.
  arXiv  Detail & Related papers  (2026-05-26T17:01:10Z)
• RotVLA: Rotational Latent Action for Vision-Language-Action Model [54.22746299071677]
  We introduce RotVLA, a VLA framework built on a continuous rotational latent action representation.<n>Latent actions are modeled as elements of SO(n), providing continuity, compositionality, and structured geometry aligned with real-world action dynamics.<n>RotVLA consists of a VLM backbone and a flow-matching action head, pretrained on large-scale cross-embodiment robotic datasets and human videos.
  arXiv  Detail & Related papers  (2026-05-13T11:58:02Z)
• Human-to-Robot Interaction: Learning from Video Demonstration for Robot Imitation [5.967530183571141]
  Human-to-Robot'' imitation learning pipeline enables robots to acquire manipulation skills directly from unstructured video demonstrations.<n>Key innovation is a modular framework that decouples the learning process into two distinct stages.<n>For robot manipulation, our framework achieves an average success rate of 87.5% across all actions, with 100% success on reaching tasks and up to 90% on complex pick-and-place operations.
  arXiv  Detail & Related papers  (2026-02-22T13:26:27Z)
• Physical Autoregressive Model for Robotic Manipulation without Action Pretraining [65.8971623698511]
  We build upon autoregressive video generation models to propose a Physical Autoregressive Model (PAR)<n>PAR leverages the world knowledge embedded in video pretraining to understand physical dynamics without requiring action pretraining.<n>Experiments on the ManiSkill benchmark show that PAR achieves a 100% success rate on the PushCube task.
  arXiv  Detail & Related papers  (2025-08-13T13:54:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.