NeurVLA: Unleashing Failure-Handling Capability of Vision-Language-Action Models via Neural-Symbolic Reasoning

Xuqi Liu, Minghe Gao, Juncheng Li, Siliang Tang
Proceedings of the 43rd International Conference on Machine Learning, PMLR 306:76290-76304, 2026.

Abstract

Vision-Language-Action models have recently shown promising progress in embodied robotic manipulation, yet their generalization to diverse open-ended embodied tasks is often hindered by execution failures. While prior work has explored failure handling, existing approaches still suffer from two fundamental limitations: coarse-grained failure correction and unreliable failure prevention. These limitations lead to brittle decision-making when VLA models are deployed in novel tasks and environments. To address them, we propose NeurVLA, a neural-symbolic framework that jointly addresses failure correction and prevention via neural-symbolic reasoning and further internalizes these failure-handling capabilities into VLA models. Experiments demonstrate that NeurVLA achieves strong performance and robust generalization across diverse tasks.

Cite this Paper

BibTeX
@InProceedings{pmlr-v306-liu26am, title = {{N}eur{VLA}: Unleashing Failure-Handling Capability of Vision-Language-Action Models via Neural-Symbolic Reasoning}, author = {Liu, Xuqi and Gao, Minghe and Li, Juncheng and Tang, Siliang}, booktitle = {Proceedings of the 43rd International Conference on Machine Learning}, pages = {76290--76304}, year = {2026}, editor = {Zhang, Tong and Dudik, Miroslav and Jaggi, Martin and Agarwal, Alekh and Li, Sharon and Schuurmans, Dale and Zhu, Jerry and Berkenkamp, Felix and Dong, Hanze and Bietti, Alberto}, volume = {306}, series = {Proceedings of Machine Learning Research}, month = {06--11 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v306/main/assets/liu26am/liu26am.pdf}, url = {https://proceedings.mlr.press/v306/liu26am.html}, abstract = {Vision-Language-Action models have recently shown promising progress in embodied robotic manipulation, yet their generalization to diverse open-ended embodied tasks is often hindered by execution failures. While prior work has explored failure handling, existing approaches still suffer from two fundamental limitations: coarse-grained failure correction and unreliable failure prevention. These limitations lead to brittle decision-making when VLA models are deployed in novel tasks and environments. To address them, we propose NeurVLA, a neural-symbolic framework that jointly addresses failure correction and prevention via neural-symbolic reasoning and further internalizes these failure-handling capabilities into VLA models. Experiments demonstrate that NeurVLA achieves strong performance and robust generalization across diverse tasks.} }
Endnote
%0 Conference Paper %T NeurVLA: Unleashing Failure-Handling Capability of Vision-Language-Action Models via Neural-Symbolic Reasoning %A Xuqi Liu %A Minghe Gao %A Juncheng Li %A Siliang Tang %B Proceedings of the 43rd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2026 %E Tong Zhang %E Miroslav Dudik %E Martin Jaggi %E Alekh Agarwal %E Sharon Li %E Dale Schuurmans %E Jerry Zhu %E Felix Berkenkamp %E Hanze Dong %E Alberto Bietti %F pmlr-v306-liu26am %I PMLR %P 76290--76304 %U https://proceedings.mlr.press/v306/liu26am.html %V 306 %X Vision-Language-Action models have recently shown promising progress in embodied robotic manipulation, yet their generalization to diverse open-ended embodied tasks is often hindered by execution failures. While prior work has explored failure handling, existing approaches still suffer from two fundamental limitations: coarse-grained failure correction and unreliable failure prevention. These limitations lead to brittle decision-making when VLA models are deployed in novel tasks and environments. To address them, we propose NeurVLA, a neural-symbolic framework that jointly addresses failure correction and prevention via neural-symbolic reasoning and further internalizes these failure-handling capabilities into VLA models. Experiments demonstrate that NeurVLA achieves strong performance and robust generalization across diverse tasks.
APA
Liu, X., Gao, M., Li, J. & Tang, S.. (2026). NeurVLA: Unleashing Failure-Handling Capability of Vision-Language-Action Models via Neural-Symbolic Reasoning. Proceedings of the 43rd International Conference on Machine Learning, in Proceedings of Machine Learning Research 306:76290-76304 Available from https://proceedings.mlr.press/v306/liu26am.html.

Related Material