MPCoT: Reward-Guided Multi-Path Latent Reasoning for Test-Time Scalable Vision-Language-Action
cs.RO, cs.AI
Submitted: 2026-06-04
Updated: 2026-09-15
Comments: 14 pages, 5 figures, submitted to CoRL
Code: https://github.com/EDGSCOUT/MPCoT
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Training Large Language Models to Reason in a Continuous Latent Space
- Recurrent-Depth VLA: Implicit Test-Time Compute Scaling of Vision-Language-Action Models via Latent Iterative Reasoning
- $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
- Unified Vision-Language-Action Model
- FLOWER: Democratizing Generalist Robot Policies with Efficient Vision-Language-Action Flow Policies
- VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model
- AVA-VLA: Improving Vision-Language-Action models with Active Visual Attention
- WorldVLA: Towards Autoregressive Action World Model
- Compressed Chain of Thought: Efficient Reasoning Through Dense Representations
- Efficient Reasoning with Hidden Thinking
- Controlling Thinking Speed in Reasoning Models
- FAST: Efficient Action Tokenization for Vision-Language-Action Models
- NORA: A Small Open-Sourced Generalist Vision Language Action Model for Embodied Tasks
- UniVLA: Learning to Act Anywhere with Task-centric Latent Actions
- Interactive Post-Training for Vision-Language-Action Models
Related papers
- FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
- MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
- RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
- HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
- APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies
- Fine-tuning is Not Enough: A Parallel Framework for Collaborative Imitation and Reinforcement Learning in End-to-end Autonomous Driving