AI & ML
Agentic-Teacher: An Agentic Data Engine for Failure-Driven VLA Post-Training
arXiv cs.RO0 views
arXiv:2611.17394v1 Announce Type: new Abstract: Improving a pretrained vision-language-action (VLA) model requires demonstrations that address its weaknesses and provide effective supervision for learning. Coding agents can autonomously generate demonstrations through environment interaction, yet successful execution alone does not ensure effective supervision for VLA learning. We introduce Agentic-Teacher, an autonomous data engine for failure-driven VLA post-training. Given a VLA checkpoint, a task specification, and configured environment tools, the engine analyzes failed rollouts, selects intervention states, and iteratively develops closed-loop code policies through execution feedback. Validated policies become reusable demonstration generators that collect successful continuations from states where the VLA struggles. To make these demonstrations suitable for learning, Agentic-Teacher introduces temporally correlated action noise to broaden state-action coverage, removes idle frames while preserving gripper transitions, and filters trajectories using the frozen base model's flow-matching loss. The resulting demonstrations are combined with successful VLA rollouts for post-training, yielding an updated policy that operates without coding-agent assistance. Agentic-Teacher thus connects the weaknesses of a target VLA to both the generation and curation of its training data. In simulation, it improves $\pi_0$ success rates from 79.4% to 87.8% on LIBERO-10, from 80.4% to 90.6% on MetaWorld-10, and from 0% to 30.0% across three RoboCasa tasks.
Source:https://arxiv.org/abs/2611.17394PreviousColor Converter: My Contrast Audit Flagged 11 Colors That Already Passed WCAG AANextRacing the Clock: Teaching VLNs Budget-Conditioned Object Search
Related posts
Coordinate Frame Recovery, Per Class NMS and Null Return Modelling for Sim2Real V2X LiDAR Detection
0arXiv cs.RO
Geometric Refinement and Distributional Alignment for Sim2Real Roadside LiDAR Detection
0arXiv cs.RO
D-VLA: A High-Concurrency Distributed Asynchronous Reinforcement Learning Framework for Vision-Language-Action Models
0arXiv cs.RO
Beyond Trajectory Similarity: Evaluating Surgical Planning by Protocol Adherence
0arXiv cs.RO
HEIR: Harness Egocentric Intent for Human-Robot Interactions
0arXiv cs.RO
EmbodiExp: Compositional Experience Transfer for Embodied Agents
0arXiv cs.RO