# ReconVLA: An Uncertainty-Guided and Failure-Aware Vision-Language-Action Framework for Robotic Control

arXiv: https://arxiv.org/abs/2604.16677 · HTML: https://mlsanity.com/paper/2604.16677/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Failure recovery and robustness, one of 13 directions in Vision-language-action models.
- Builds on 39 of its 51 references that are in the map.
- First posted on arXiv 17 Apr 2026.

## Placed in

- Vision-language-action models / [Failure recovery and robustness](https://mlsanity.com/vla/failure-recovery-and-robustness/)

## Builds on (most cited first, 30 of 39)

- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [π0: A Vision-Language-Action Flow Model for General Robot Control](https://mlsanity.com/paper/2410.24164/) (2024)
- [Do As I Can, Not As I Say: Grounding Language in Robotic Affordances](https://mlsanity.com/paper/2204.01691/) (2022)
- [PaLM-E: An Embodied Multimodal Language Model](https://mlsanity.com/paper/2303.03378/) (2023)
- [Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success](https://mlsanity.com/paper/2502.19645/) (2025)
- [A Generalist Agent](https://mlsanity.com/paper/2205.06175/) (2022)
- [A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantification](https://mlsanity.com/paper/2107.07511/) (2021)
- [Conformalized Quantile Regression](https://mlsanity.com/paper/1905.03222/) (2019)
- [Towards Out-Of-Distribution Generalization: A Survey](https://mlsanity.com/paper/2108.13624/) (2021)
- [Robots That Ask For Help: Uncertainty Alignment for Large Language Model Planners](https://mlsanity.com/paper/2307.01928/) (2023)
- [Foundation Models in Robotics: Applications, Challenges, and the Future](https://mlsanity.com/paper/2312.07843/) (2023)
- [Uncertainty Quantification and Deep Ensembles](https://mlsanity.com/paper/2007.08792/) (2020)
- [AHA: A Vision-Language-Model for Detecting and Reasoning Over Failures in Robotic Manipulation](https://mlsanity.com/paper/2410.00371/) (2024)
- [Dropout Sampling for Robust Object Detection in Open-Set Conditions](https://mlsanity.com/paper/1710.06677/) (2017)
- [A Survey on Vision-Language-Action Models: An Action Tokenization Perspective](https://mlsanity.com/paper/2507.01925/) (2025)
- [Vision-Language-Action Models for Robotics: A Review Towards Real-World Applications](https://mlsanity.com/paper/2510.07077/) (2025)
- [SAFE: Multitask Failure Detection for Vision-Language-Action Models](https://mlsanity.com/paper/2506.09937/) (2025)
- [RoboMonkey: Scaling Test-Time Sampling and Verification for Vision-Language-Action Models](https://mlsanity.com/paper/2506.17811/) (2025)
- [Conformal Prediction for Natural Language Processing: A Survey](https://mlsanity.com/paper/2405.01976/) (2024)
- [Can We Detect Failures Without Failure Data? Uncertainty-Aware Runtime Failure Detection for Imitation Learning Policies](https://mlsanity.com/paper/2503.08558/) (2025)
- [Conformal Decision Theory: Safe Autonomous Decisions from Imperfect Predictions](https://mlsanity.com/paper/2310.05921/) (2023)
- [Failure Prediction at Runtime for Generative Robot Policies](https://mlsanity.com/paper/2510.09459/) (2025)
- [Run-time Observation Interventions Make Vision-Language-Action Models More Visually Robust](https://mlsanity.com/paper/2410.01971/) (2024)
- [Exploring Predictive Uncertainty and Calibration in NLP: A Study on the Impact of Method & Data Scarcity](https://mlsanity.com/paper/2210.15452/) (2022)
- [Uncertainty-Aware Data Aggregation for Deep Imitation Learning](https://mlsanity.com/paper/1905.02780/) (2019)
- [Evaluating Uncertainty and Quality of Vision-Language-Action-enabled Robots](https://mlsanity.com/paper/2507.17049/) (2025)

## Built on by (most cited first, 5 of 5)

- [AEGIS: A Backup Reflex for Physical AI](https://mlsanity.com/paper/2606.06660/) (2026)
- [FabriVLA: A Lightweight Vision-Language-Action Model with Conformal Action Chunk Uncertainty](https://mlsanity.com/paper/2607.08575/) (2026)
- [FabriMAE I Trust Myself? Self-Evaluating VLA Action Generation with Markov Attention Entropy](https://mlsanity.com/paper/2608.16697/) (2026)
- [Toward Unified Robot Learning: Bridging Representation, Vision-Language-Action, and World Models](https://mlsanity.com/paper/2609.03927/) (2026)
- [Quantile Head for Vision-Language-Action Models](https://mlsanity.com/paper/2609.34061/) (2026)

## Abstract (arXiv)

Vision-language-action (VLA) models have emerged as generalist robotic controllers capable of mapping visual observations and natural language instructions to continuous action sequences. However, VLAs provide no calibrated measure of confidence in their action predictions, thus limiting their reliability in real-world settings where uncertainty and failures must be anticipated. To address this problem we introduce ReconVLA, a reliable conformal model that produces uncertainty-guided and failure-aware control signals. Concretely, our approach applies conformal prediction directly to the action token outputs of pretrained VLA policies, yielding calibrated uncertainty estimates that correlate with execution quality and task success. Furthermore, we extend conformal prediction to the robot state space to detect outliers or unsafe states before failures occur, providing a simple yet effective failure detection mechanism that complements the action-level uncertainty. We evaluate ReconVLA in both simulation and real robot experiments across diverse manipulation tasks. Our results show that conformalized action predictions consistently improve failure anticipation, reduce catastrophic errors, and provide a calibrated measure of confidence without retraining or modifying the underlying VLA.