mlsanityData to 14 Oct 2026

Axiom-0: Hierarchical Self-Refinement for Vision-Language-Action Policies

arXiv 2610.14155 ↗First posted 9 Oct 2026cs.RO cs.CVcited by 0

On the map: Vision-language-action models → Generalist VLA models and benchmarks also fits: Reasoning and chain-of-thought in VLA

Abstract (arXiv)

Reliable manipulation requires policies that generalize across tasks, layouts, and object interactions. Vision-language-action (VLA) models combine pretrained multimodal understanding with learned control, but their performance remains limited on unfamiliar task compositions. We present Axiom-0, a VLA policy that addresses both the quality of its representations and their use in action generation through hierarchical self-refinement. Intra-VLM Representation Refinement (IVRR) strengthens selected intermediate features through consistency supervision with learned feature projections during training. VLM-Action Interface Refinement (VAIR) recursively updates the resulting conditioning before action generation. Joint optimization of the supervised VLM layers, VAIR, and the action generator connects the two components. On RoboCasa365, Axiom-0 achieves 62.32% overall success in our evaluation, exceeding the highest published leaderboard score (Paimon-0, 58.1%) by 4.22 percentage points and the Xiaomi-Robotics-1 reference by 4.92 points. Under the evaluated profiling setup, mean action-chunk generation latency increases by 1.7% over Xiaomi-Robotics-1. These results demonstrate improved task completion with modest inference overhead.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Generalist VLA models and benchmarks, one of 13 directions in Vision-language-action models. Builds on 10 of its 12 references that are in the map. First posted on arXiv 9 Oct 2026.

Builds on

10 of 12 references.

Closest ancestors · 3

Same direction, newest first

  1. 2026Xiaomi-Robotics-1: Scaling Vision-Language-Action Models with over 100K Hours of Real-World Trajectories16 Jul
  2. 2025π0.5: a Vision-Language-Action Model with Open-World Generalization22 Apr
  3. 2024π0: A Vision-Language-Action Flow Model for General Robot Control31 Oct

Other references · 7

  1. 2025SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Modelcited by 519
  2. 2025LIBERO-Plus: In-depth Robustness Analysis of Vision-Language-Action Modelscited by 303
  3. 2023Looped Transformers are Better at Learning Learning Algorithmscited by 149
  4. 2025Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action Modelcited by 134
  5. 2026RoboCasa365: A Large-Scale Simulation Framework for Training and Benchmarking Generalist Robotscited by 79
  6. 2025From Spatial to Actions: Grounding Vision-Language-Action Model in Spatial Foundation Priorscited by 28
  7. 2026LIBERO-Safety: A Comprehensive Benchmark for Physical and Semantic Safety in Vision-Language-Action Modelscited by 10

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026LoopVLA: Learning Sufficiency in Recurrent Refinement for Vision-Language-Action Models
  2. 2025VITA-VLA: Efficiently Teaching Vision-Language Models to Act via Action Expert Distillation
  3. 2026CoRE-VLA: Towards Scalable and Robust Vision-Language-Action Modeling via Conditional Routing of Experts
  4. 2026AC^2-VLA: Action-Context-Aware Adaptive Computation in Vision-Language-Action Models for Efficient Robotic Manipulation
  5. 2026CAC-VLA: Context-Gated Action Conditioning for Vision-Language-Action Models
  6. 2026Look Before Acting: Enhancing Vision Foundation Representations for Vision-Language-Action Models
  7. 2026From Knowing to Doing Precisely: A General Self-Correction and Termination Framework for VLA models
  8. 2025InstructVLA: Vision-Language-Action Instruction Tuning from Understanding to Manipulation