Neural Information Processing Systems http://nips.cc/

Assessing reliably the confidence of a deep neural net and predicting its failures is of primary importance for the practical deployment of these models. In this paper, we propose a new target criterion for model confidence, corresponding to the True Class Probability (TCP). We show how using the TCP is more suited than relying on the classic Maximum Class Probability (MCP). We provide in addition theoretical guarantees for TCP in the context of failure prediction. Since the true class is by essence unknown at test time, we propose to learn TCP criterion on the training set, introducing a specific learning scheme adapted to this context. Extensive experiments are conducted for validating the relevance of the proposed approach. We study various network architectures, small and large scale datasets for image classification and semantic segmentation. We show that our approach consistently outperforms several strong methods, from MCP to Bayesian uncertainty, as well as recent approaches specifically designed for failure prediction.

Robotic manipulation is a fundamental component of automation. However, traditional perception-planning pipelines often fall short in open-ended tasks due to limited flexibility, while the architecture of a single end-to-end Vision-Language-Action (VLA) offers promising capabilities but lacks crucial mechanisms for anticipating and recovering from failure. To address these challenges, we propose FPC-VLA, a dual-model framework that integrates VLA with a supervisor for failure prediction and correction. The supervisor evaluates action viability through vision-language queries and generates corrective strategies when risks arise, trained efficiently without manual labeling. A dual-stream fusion module further refines actions by leveraging past predictions. Evaluation results on multiple simulation platforms (SIMPLER and LIBERO) and robot embodiments (WidowX, Google Robot, Franka) show that FPC-VLA outperforms state-of-the-art models in both zero-shot and fine-tuned settings. Successful real-world deployments on diverse, long-horizon tasks confirm FPC-VLA's strong generalization and practical utility for building more reliable autonomous systems.

The convergence of the Internet of Things (IoT) and Industry 4.0 has significantly enhanced data-driven methodologies within the nuclear industry, notably enhancing safety and economic efficiency. This advancement challenges the precise prediction of future maintenance needs for assets, which is crucial for reducing downtime and operational costs. However, the effectiveness of data-driven methodologies in the nuclear sector requires extensive domain knowledge due to the complexity of the systems involved. Thus, this paper proposes a novel predictive maintenance methodology that combines data-driven techniques with domain knowledge from a nuclear equipment. The methodological originality of this paper is located on two levels: highlighting the limitations of purely data-driven approaches and demonstrating the importance of knowledge in enhancing the performance of the predictive models. The applicative novelty of this work lies in its use within a domain such as a nuclear industry, which is highly restricted and ultrasensitive due to security, economic and environmental concerns. A detailed real-world case study which compares the current state of equipment monitoring with two scenarios, demonstrate that the methodology significantly outperforms purely data-driven methods in failure prediction. While purely data-driven methods achieve only a modest performance with a prediction horizon limited to 3 h and a F1 score of 56.36%, the hybrid approach increases the prediction horizon to 24 h and achieves a higher F1 score of 93.12%.

Imitation learning (IL) with generative models, such as diffusion and flow matching, has enabled robots to perform complex, long-horizon tasks. However, distribution shifts from unseen environments or compounding action errors can still cause unpredictable and unsafe behavior, leading to task failure. Early failure prediction during runtime is therefore essential for deploying robots in human-centered and safety-critical environments. We propose FIPER, a general framework for Failure Prediction at Runtime for generative IL policies that does not require failure data. FIPER identifies two key indicators of impending failure: (i) out-of-distribution (OOD) observations detected via random network distillation in the policy's embedding space, and (ii) high uncertainty in generated actions measured by a novel action-chunk entropy score. Both failure prediction scores are calibrated using a small set of successful rollouts via conformal prediction. A failure alarm is triggered when both indicators, aggregated over short time windows, exceed their thresholds. We evaluate FIPER across five simulation and real-world environments involving diverse failure modes. Our results demonstrate that FIPER better distinguishes actual failures from benign OOD situations and predicts failures more accurately and earlier than existing methods. We thus consider this work an important step towards more interpretable and safer generative robot policies. Code, data and videos are available at https://tum-lsy.github.io/fiper_website.

Neural Information Processing Systems http://nips.cc/

The inherent non-deterministic nature of autonomous agents, particularly within low-code/no-code (LCNC) environments, presents significant reliability challenges. Agents can become trapped in unforeseen loops, generate inaccurate outputs, or encounter unrecoverable failures, leading to user frustration and a breakdown of trust. This report proposes a novel architectural pattern to address these issues: the integration of a secondary, "metacognitive" layer that actively monitors the primary LCNC agent. Inspired by human introspection, this layer is designed to predict impending task failures based on a defined set of triggers, such as excessive latency or repetitive actions. Upon predicting a failure, the metacognitive agent proactively initiates a human handoff, providing the user with a clear summary of the agent's "thought process" and a detailed explanation of why it could not proceed. An empirical analysis of a prototype system demonstrates that this approach significantly increases the overall task success rate. However, this performance gain comes with a notable increase in computational overhead. The findings reframe human handoffs not as an admission of defeat but as a core design feature that enhances system resilience, improves user experience, and builds trust by providing transparency into the agent's internal state. The report discusses the practical and ethical implications of this approach and identifies key directions for future research.

Early-exit models accelerate inference by attaching internal classifiers to intermediate layers of the network, allowing computation to halt once a prediction meets a predefined exit criterion. Most early-exit methods rely on confidence-based exit strategies, which has motivated prior work to calibrate intermediate classifiers in pursuit of improved performance-efficiency trade-offs. In this paper, we argue that calibration metrics can be misleading indicators of multi-exit model performance. Specifically, we present empirical evidence showing that miscalibrated networks can outperform calibrated ones. As an alternative, we propose using failure prediction as a more informative proxy for early-exit model performance. Unlike calibration, failure prediction captures changes in sample rankings and correlates strongly with efficiency gains, offering a more reliable framework for designing and evaluating early-exit models.