Anatomy of a Closed-Loop Collapse: A Causal Case Study of a Compressed VLA Policy

arXiv:2609.23048 · cs.RO, cs.LG · Submitted 2026-09-19 · Read on arXiv

cs.RO, cs.LG

Submitted: 2026-09-19

Updated: 2026-09-19

Comments: 8 pages, 1 figure, 5 tables. Accepted as a poster at the IROS 2026 Workshop on Building Scalable Infrastructure for Robot Learning: From Data Scaling to Real-World Deployment (ScaleInfra), Pittsburgh, PA, USA. Supplementary records: https://github.com/Xanadum/closed-loop-collapse

Code: https://github.com/Xanadum/closed-loop-collapse

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Distillation — 2× in this paper · explained in 2 episodes
• Trace — 1× in this paper · explained in 2 episodes

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