$τ_0$-VLA: a Hierarchical Robot Foundation Model with World-Model-Guided Test-Time Computation

• URL: http://arxiv.org/abs/2608.16885v1
• Date: Mon, 17 Aug 2026 17:59:11 GMT
• Title: $τ_0$-VLA: a Hierarchical Robot Foundation Model with World-Model-Guided Test-Time Computation
• Abstract summary: Long-horizon robot manipulation requires a robot to both execute individual skills reliably and sequence them coherently over extended tasks.<n>We introduce $_0$-VLA, a hierarchical robot foundation model that formulates high-level subtask generation as a compute-scalable inference problem.<n>A low-level policy then executes the generated subtask across multiple robot embodiments.
• Score: 51.05516457377339
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Long-horizon robot manipulation requires a robot to both execute individual skills reliably and sequence them coherently over extended tasks. Most hierarchical vision-language-action (VLA) models make each such decision with a single forward pass, leaving no mechanism to allocate additional computation to difficult or consequential choices. We introduce $τ_0$-VLA, a hierarchical robot foundation model that formulates high-level subtask generation as a compute-scalable inference problem through world-model-guided test-time computation. At each inference step, the high-level policy uses execution memory to generate a subtask and, when needed, searches over alternatives before committing to its output. A low-level policy then executes the generated subtask across multiple robot embodiments. The policy is trained on 40,115 hours of heterogeneous real-world data with multimodal co-training. Across in-domain and distribution-shifted settings, allocating additional test-time computation substantially improves next-subtask prediction accuracy, and these gains translate into higher closed-loop success on long-horizon robot manipulation tasks.

Related papers

• DSWAM: A Dual-System World Action Foundation Model for Fine-Grained Robot Manipulation [14.193285862278913]
  World Action Models (WAMs) provide a promising alternative to Vision-Language-Action (VLA) policies.<n>Existing WAMs excel at physically grounded execution, but typically lack the explicit language-level planning interface.<n>We introduce DSWAM, a Dual-System World Action Foundation Model for fine-grained robot manipulation.
  arXiv  Detail & Related papers  (2026-07-06T10:57:01Z)
• ELASTIC: Efficiently Learning to Adaptively Scale Test-Time Compute for Generative Control Policies [36.28264388380867]
  Generative control policies (GCPs) enable test-time scaling in robot control.<n>Test-time compute can be allocated along two axes: sequential scaling and parallel scaling.<n>We present ELASTIC, an algorithm that learns state-dependent test-time compute schedules for GCPs.
  arXiv  Detail & Related papers  (2026-06-30T05:00:32Z)
• RoboClaw: An Agentic Framework for Scalable Long-Horizon Robotic Tasks [28.827331437876452]
  We present RoboClaw, an agentic robotics framework that unifies data collection, policy learning, and task execution under a single VLM-driven controller.<n>At the policy level, RoboClaw introduces Entangled Action Pairs (EAP), which couple forward manipulation behaviors with inverse recovery actions to form self-resetting loops for autonomous data collection.<n>During deployment, the same agent performs high-level reasoning and dynamically orchestrates learned policy primitives to accomplish long-horizon tasks.
  arXiv  Detail & Related papers  (2026-03-12T05:22:59Z)
• RoboCerebra: A Large-scale Benchmark for Long-horizon Robotic Manipulation Evaluation [59.9896841079005]
  We introduce RoboCerebra, a benchmark for evaluating high-level reasoning in long-horizon robotic manipulation.<n>The dataset is constructed via a top-down pipeline, where GPT generates task instructions and decomposes them into subtask sequences.<n>Compared to prior benchmarks, RoboCerebra features significantly longer action sequences and denser annotations.
  arXiv  Detail & Related papers  (2025-06-07T06:15:49Z)
• RoBridge: A Hierarchical Architecture Bridging Cognition and Execution for General Robotic Manipulation [90.81956345363355]
  RoBridge is a hierarchical intelligent architecture for general robotic manipulation.<n>It consists of a high-level cognitive planner (HCP) based on a large-scale pre-trained vision-language model (VLM)<n>It unleashes the procedural skill of reinforcement learning, effectively bridging the gap between cognition and execution.
  arXiv  Detail & Related papers  (2025-05-03T06:17:18Z)
• Value Iteration for Learning Concurrently Executable Robotic Control Tasks [6.057772626591651]
  We propose a novel method to train redundant robots to execute multiple tasks concurrently.<n>We do so by first defining a notion of task independence between learned value functions.<n>We then use our definition of task independence to propose a cost functional that encourages a policy to accomplish its control objective.
  arXiv  Detail & Related papers  (2025-04-01T20:31:36Z)
• COHERENT: Collaboration of Heterogeneous Multi-Robot System with Large Language Models [49.24666980374751]
  COHERENT is a novel LLM-based task planning framework for collaboration of heterogeneous multi-robot systems.<n>A Proposal-Execution-Feedback-Adjustment mechanism is designed to decompose and assign actions for individual robots.<n>The experimental results show that our work surpasses the previous methods by a large margin in terms of success rate and execution efficiency.
  arXiv  Detail & Related papers  (2024-09-23T15:53:41Z)
• Decomposition-based Hierarchical Task Allocation and Planning for Multi-Robots under Hierarchical Temporal Logic Specifications [9.150196865878234]
  We formulate a decomposition-based hierarchical framework for robotic planning with temporal logic specifications. A Mixed Linear Program is used to assign sub-tasks to various robots. Our approach was experimentally applied to domains of navigation and manipulation.
  arXiv  Detail & Related papers  (2023-08-20T23:53:13Z)
• Dynamic Multi-Robot Task Allocation under Uncertainty and Temporal Constraints [52.58352707495122]
  We present a multi-robot allocation algorithm that decouples the key computational challenges of sequential decision-making under uncertainty and multi-agent coordination. We validate our results over a wide range of simulations on two distinct domains: multi-arm conveyor belt pick-and-place and multi-drone delivery dispatch in a city.
  arXiv  Detail & Related papers  (2020-05-27T01:10:41Z)
• Hierarchical Reinforcement Learning as a Model of Human Task Interleaving [60.95424607008241]
  We develop a hierarchical model of supervisory control driven by reinforcement learning. The model reproduces known empirical effects of task interleaving. The results support hierarchical RL as a plausible model of task interleaving.
  arXiv  Detail & Related papers  (2020-01-04T17:53:28Z)

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.