arXiv:2606. 08508v1 Announce Type: cross Abstract: Generative robot policies fail unpredictably at deployment: they hesitate at critical moments, drift off-task, or commit to unrecoverable actions.
arXiv:2608.29967v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models demonstrate strong semantic understanding yet exhibit systematic failures during deployment. The conditions under...
arXiv:2608.25757v4 Announce Type: replace-cross Abstract: Large-scale vision--language--action (VLA) policies have advanced generalist robot control, yet most remain stimulus-to-action black boxes: a...
VLA-FAIL introduces a lightweight framework for detecting failures in vision-language-action models used in robotic manipulation. It combines two novel detectors: the first-layer Mahalanobis distance (LLMD) identifies out-of-distribution states by comparing token-wise deviations in last-layer features to training data, while the second, action chunk consistency (ACC), detects failures by spotting inconsistencies between consecutive action chunks in receding-horizon control. The authors also propose a threshold‑independent metric, “AUCPDT,” to evaluate detection accuracy and latency, and show through real‑world and simulation experiments that LLMD and ACC together provide reliable and early failure detection, outperforming more expensive baseline methods.
arXiv:2608. 04692v1 Announce Type: cross Abstract: Task-vector arithmetic offers a closed-form way to modify a model, yet its behavioral locality remains unclear in closed-loop robot control.
IndustrialVLA-Bench evaluates six released vision‑language‑action (VLA) and world‑action (WAM) robot policy models using a unified reporting schema. It measures clean capability on LIBERO, non‑language robustness on LIBERO‑Plus, instruction sensitivity on LIBERO‑Para, and observed execution cost, aggregating results across three random seeds. The benchmark also reports inference latency, peak memory, runtime mode, and evidence status for each system, enabling traceable comparisons without claiming one paradigm is universally superior.
arXiv:2604.16677v2 Announce Type: replace-cross Abstract: Vision-language-action (VLA) models have emerged as generalist robotic controllers that map visual observations and language instructions to...
EmbodiedSkills is a skill-based agent framework that enhances frozen vision‑language‑action (VLA) policies with world action models for consequence‑aware action selection. It defines reusable skills for observation, context encoding, candidate generation, consequence prediction, outcome evaluation, candidate comparison, and action execution, organized into five stages that support both continuous action chunks and pick‑and‑place primitives. The framework improves success rates on MetaWorld MT50, CLIPort, and CALVIN benchmarks by incorporating outcome predictions and lightweight comparators while keeping the core policy and observation encoders frozen.
LM‑X is a generalist vision‑language‑action policy that augments action prediction with three online, explicitly supervised signals: return‑to‑go (RTG) for task progress, event‑to‑go (ETG) for the next semantic transition, and heteroscedastic action flow for local reliability. By conditioning action generation on these signals, LM‑X embeds explainability directly into control rather than as a post‑hoc explanation. After a 20‑day pretraining run on 64 GPUs, LM‑X outperforms an action‑only backbone by 16.0 points and a single‑head variant by 10.8 points, and achieves 74.1 % success on 50 RoboTwin2.0 tasks and 68.6 % on seven real‑robot tasks, surpassing the GR00T N1.7 baseline.
arXiv:2608. 11739v1 Announce Type: cross Abstract: The prevailing recipe for Vision-Language-Action (VLA) models couples a pretrained VLM with a separately trained flow-matching action expert.
The paper introduces FailBank, a four‑stage self‑evolving framework that transforms runtime feedback from safety shields into lasting policy improvements for vision‑language‑action (VLA) models. By using a counterfactual correction teacher, outcome‑aware admission, and guarded LoRA updates, FailBank converts useful shield proposals into corrective targets while preserving successful actions as anchors. Experiments on the VLA‑Arena benchmark show that FailBank boosts task success rates by up to 8.5 percentage points and reduces cumulative policy cost by up to 35.6%, outperforming both base policies and traditional runtime shielding.
The study examines how different vision‑language‑action (VLA) policies execute a manipulation task by comparing the geometry of their end‑effectors across 15,000 closed‑loop LIBERO rollouts. By pairing 3,600 configuration‑matched policy executions, the authors find that when both policies succeed, their end‑effector trajectories are much closer (median DTW distance 0.0120 m) than when only one succeeds (0.0380 m), a pattern consistent across all tasks, policy pairs, and nine representations. Even successful executions remain as far from same‑task demonstrations as the demonstrations are from each other, indicating that task‑associated geometry, rather than training data overlap, drives these differences.