While Large Language Models (LLMs) can accelerate Model-Based Systems Engineering (MBSE) for software-defined vehicles, their probabilistic nature causes "architectural drift", fabricating interfaces in behavioral views that lack structural foundations. To enforce deterministic interface alignment, we propose a stateful, multi-agent validation pipeline. The framework utilizes a sequential generation matrix (Class->Activity->Sequence) and Vehicle Signal Specification (VSS)-grounded Retrieval-Augmented Generation (RAG). An independent AI Validator Agent dynamically audits outputs against a strict error taxonomy, triggering state-preserving backtracking loops to resolve incompatibilities. Evaluated on an Advanced Driver Assistance System (ADAS) scenario, standard RAG yielded 0

Perception plays a central role in connected and autonomous vehicles (CAVs), underpinning not only conventional modular driving stacks, but also cooperative perception systems and recent end-to-end driving models. While deep learning has greatly improved perception performance, its statistical nature makes perfect predictions difficult to attain. Meanwhile, standard training objectives and evaluation benchmarks treat all perception errors equally, even though only a subset is safety-critical. In this paper, we investigate safety-aligned evaluation and optimization for 3D object detection that explicitly characterize high-impact errors. Building on our previously proposed safety-oriented metric, NDS-USC, and safety-aware loss function, EC-IoU, we make three contributions. First, we present an expanded study of single-vehicle 3D object detection models across diverse neural network architectures and sensing modalities, showing that gains under standard metrics such as mAP and NDS may not translate to safety-oriented criteria represented by NDS-USC. With EC-IoU, we reaffirm the benefit of safety-aware fine-tuning for improving safety-critical detection performance. Second, we conduct an ego-centric, safety-oriented evaluation of AV-infrastructure cooperative object detection models, underscoring its superiority over vehicle-only models and demonstrating a safety impact analysis that illustrates the potential contribution of cooperative models to "Vision Zero." Third, we integrate EC-IoU into SparseDrive and show that safety-aware perception hardening can reduce collision rate by nearly 30

Long-term LLM agents must preserve information across interactions while distinguishing repeated evidence, historical states, updates, and unresolved contradictions. Existing textual memory systems retrieve semantically relevant memories efficiently but often leave these relationships implicit, whereas richer structured approaches model them through global graphs, hierarchical abstractions, or reflection at greater complexity. We introduce MemoryLACE (MemLACE), a lightweight memory framework that explicitly models the lifecycle of textual evidence through sparse merge, supersession, and contradiction relations while preserving atomic natural-language memories and their provenance. Rather than retrieving memories independently, MemLACE reconstructs relation-aware evidence units that expose current, historical, supporting, and conflicting evidence for downstream reasoning. Across BEAM and StructMemEval, using open-weight and proprietary LLM backbones, MemLACE achieves the highest overall performance in same-backbone comparisons while reducing end-to-end runtime on BEAM by 66.6

This paper concerns the universal and adaptive control solutions for a class of mechanically docked vehicles under complex motion interference. The kinematic and dynamic models of the connected vehicles are first established, followed by the design of a model-based cascaded control framework. An improved adaptive safety geofencing method is then introduced, integrating capability constraints and barrier functions to modify the reference trajectory within the kinematic loop and ensure position safety near obstacles. Furthermore, an adaptive gain filtering extended state observer (AGFESO) is proposed to achieve low-peak, small-oscillation disturbance estimation from noisy measurements, thereby enhancing the practical robustness of dynamic feedback control through feedforward compensation. In addition, an active fault-tolerant mechanism is developed to optimize the allocation of control inputs at the actuator level, mitigating performance degradation under random actuator faults. Finally, the advantages and effectiveness of the proposed design scheme for connected vehicles under composite interferences are demonstrated by simulation and experimental examples. (c) 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.

As large language models (LLMs) advance and multi-agent systems aim to overcome the limits of standalone agents, robust communication protocols are becoming essential infrastructure for distributed agent networks. Nonetheless, the fragmented protocol landscape presents a significant interoperability challenge. This study develops a technical taxonomy to classify and analyze LLM agent communication protocols. Following an established iterative method, we defined the taxonomy's purpose, meta-characteristic, and ending conditions, then performed five iterations, three empirical-to-conceptual and two conceptual-to-empirical, on nine actively maintained open-source protocols with demonstrable adoption. The taxonomy comprises five dimensions: counterparty, payload, interaction state, discovery mechanism, and schema flexibility. Classification reveals recurring architectural patterns: all sampled agent-to-agent protocols combine hybrid payloads with session-state persistence; most protocols support multiple predefined schemas, and two negotiate schemas at runtime, indicating a trend toward schema flexibility; decentralized discovery remains rare. Analysis suggests short-term convergence pressure toward protocols unifying agent-to-agent and agent-to-context (tool and data) communication. Long-term, however, no single protocol is likely to maximize versatility, efficiency, and portability simultaneously. The field will more likely evolve toward a federated, layered protocol stack. The framework guides protocol selection and highlights open research gaps such as privacy and policy enforcement.}

Technological advances in the automotive industry have increased the complexity of vehicle testing and simultaneously require sophisticated methods to ensure safety, accuracy and reproducibility. Testing on proving grounds is essential to validate advanced systems at performance limits or for durability testing under controlled and repeatable conditions. However, these tests require precise planning, compliance and accuracy, which are error-prone and physically demanding for vehicles and drivers. Automation helps to overcome these challenges. This work presents an innovative approach using an Intelligent Test Coordinator (ITC) and Robot Driving System (RDS) for test vehicles to automate test preparation and execution. The ITC uses a Large Language Model and error feedback to automate the design of test procedures and generate precise RDS instructions for real-world test scenarios. Simulations validate test setups before execution, and vehicles equipped with RDS perform driverless testing. The performance of the ITC is validated by creating 240 test setups for different driving scenarios. The robot-guided vehicles perform real-world tests based on test setups on various tracks, including flat asphalt surfaces and handling tracks. These tests demonstrate that the proposed approach outperforms human-driven vehicles in terms of safety, accuracy and repeatability. The proposed approach to automation enhances testing efficiency and facilitates comprehensive validation of vehicle safety and performance.

Meta-reinforcement learning enables fast adaptation by extracting shared structure from related tasks, but existing end-to-end methods often couple task inference with embodiment-specific control. This coupling can obscure non-parametric task semantics, reduce sample efficiency, and limit cross-agent reuse. We propose a meta-knowledge reutilization framework that learns task-level knowledge on a dynamics-simplified agent and transfers it to heterogeneous agents. The framework uses a Bayesian non-parametric prior to organize latent task modes and a high-level policy to generate task-level magnitude guidance. To bridge reusable task knowledge with different embodiments, we introduce a semantic-magnitude interface and a lightweight temporal adaptor, which convert frozen meta-knowledge into temporally aligned subgoals for embodiment-specific low-level controllers. Experiments on multiple locomotion agents show that our framework reduces final-step tracking error by 94.75

Mobile manipulation requires the coordinated control of a mobile base and a robotic arm while simultaneously perceiving both global scene context and fine-grained object details. Existing single-view approaches often fail in unstructured environments due to limited fields of view, exploration, and generalization abilities. Moreover, classical controllers, although stable, struggle with efficiency and manipulability near singularities. To address these challenges, we propose M4Diffuser, a hybrid framework that integrates a Multi-View Diffusion Policy with a novel Reduced and Manipulability-aware QP (ReM-QP) controller for mobile manipulation. The diffusion policy leverages proprioceptive states and complementary camera perspectives with both close-range object details and global scene context to generate task-relevant end-effector goals in the world frame. These high-level goals are then executed by the ReM-QP controller, which eliminates slack variables for computational efficiency and incorporates manipulability-aware preferences for robustness near singularities. Comprehensive experiments in simulation and real-world environments show that M4Diffuser achieves 8%–56% higher success rates and reducing collisions by 3%–32% over baselines. Our approach demonstrates robust performance for smooth whole-body coordination, and strong generalization to unseen tasks, paving the way for reliable mobile manipulation in unstructured environments. Details of the demo and supplemental material are available on our project website https://sites.google.com/view/m4diffuser-anonymous.

Diagnosing esophageal motility disorders, including dysphagia, pose significant challenges due to the complexity of high-resolution impedance manometry (HRIM) data and variability in clinical interpretation. Thiswork explores the feasibility of a multimodal machine learning (ML)-based classification approach that combines HRIM recordings with patient-specific information and incorporates a graph-based modeling of esophageal physiology. We analyze HRIM recordings with corresponding patient information from 104 patientswith esophageal motility disorders collected atTUMUniversity Hospital. Patient data include demographic, clinical, and symptom information extracted from structured questionnaires and free-text notes using keyword detection and large language model-based processing. HRIM data are represented as spatiotemporal graphs, where nodes correspond to pressure values along the esophagus and edges encode spatial adjacency and impedance dynamics.Agraph neural network (GNN) is applied to learn physiologically meaningful representations,which are fused with patient embeddings for multi-category, multi-class classification of swallow events. The impact of patient features and graphbased modeling is evaluated by ablation studies and comparison to vision-based classifier baselines. The proposed multimodal approach, incorporating patient-specific information, indicates improvements over models that rely solely on HRIM-derived features across all classification categories. Additionally, the graph-based modeling provides gains compared to vision-based baselines. Our experiments systematically assess the complementary contribution of multiple modalities, as well as demonstrate the feasibility of our proposed graph-based approach. Our initial findings demonstrate that integrating patient-level data with graph-based representations of HRIM signals appears to be a promising direction for more accurate classification of esophageal motility disorders. For further validation, future studies should include larger and more representative datasets to confirm these trends and ensure generalizability.

Accurate vehicle localization is a critical challenge in urban environments where GPS signals are often unreliable. This paper presents a cooperative multi-sensor and multi-modal localization approach to address this issue by fusing data from vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) systems. Our approach integrates cooperative data with a point cloud registration-based simultaneous localization and mapping (SLAM) algorithm. The system processes point clouds generated from diverse sensor modalities, including vehicle-mounted LiDAR and stereo cameras, as well as sensors deployed at intersections. By leveraging shared data from infrastructure, our method significantly improves localization accuracy and robustness in complex, GPS-noisy urban scenarios.

The Transformer architecture is widely regarded as the most powerful tool for natural language processing, but due to a high number of complex operations, it inherently faces the issue of high energy consumption. To address this issue, we consider Spiking Neural Networks (SNNs), which are an energy-efficient alternative to conventional Artificial Neural Networks (ANNs) due to their naturally event-driven approach to processing information. However, this inherently makes them difficult to train. Often, many SNN-based models circumvent this issue by converting pre-trained ANNs. More recently, attempts have been made to design directly trainable SNN-based adaptations of the Transformer model structure. Although the results showed great promise, the application field was computer vision. Moreover, the proposed model incorporates only encoder blocks. In this paper, we propose SpikeDecoder, a fully SNN-based implementation of the Transformer decoder block, for applications in natural language processing. In a series of experiments, we analyze the impact of exchanging different blocks of the ANN model with spike-based alternatives to identify trade-offs and significant sources of performance loss. We further investigate the role of residual connections and the selection of SNN-compatible normalization techniques. Besides the work on the model architecture, we formulate and compare different embedding methods to project text data into spikes. Finally, we demonstrate that our proposed SNN-based decoder block reduces the theoretical energy consumption by 87

General-purpose robotic skills from end-to-end demonstrations often leads to task-specific policies that fail to generalize beyond the training distribution. Therefore, we introduce FunCanon, a framework that converts long-horizon manipulation tasks into sequences of action chunks, each defined by an actor, verb, and object. These chunks focus policy learning on the actions themselves, rather than isolated tasks, enabling compositionality and reuse. To make policies pose-aware and category-general, we perform functional object canonicalization for functional alignment and automatic manipulation trajectory transfer, mapping objects into shared functional frames using affordance cues from large vision–language models. An object-centric and action-centric diffusion policy FuncDiffuser trained on this aligned data naturally respects object affordances and poses, simplifying learning and improving generalization ability. Experiments on simulated and real-world benchmarks demonstrate category-level generalization, cross-task behavior reuse, and robust sim-to-real deployment, showing that functional canonicalization provides a strong inductive bias for scalable imitation learning in complex manipulation domains. Details of the demo and supplemental material are available on our project website https://sites.google.com/view/funcanon-anonymous.

Transformer-based architectures have shown remarkable performance in vision and language tasks but pose unique challenges for safety-critical applications. This paper presents a conceptual framework for integrating Transformers into automotive systems from a safety perspective. We outline how multimodal Foundation Models can leverage sensor diversity and redundancy to improve fault tolerance and robustness. Our proposed architecture combines multiple independent modality-specific encoders that fuse their representations into a shared latent space, supporting fail-operational behavior if one modality degrades. We demonstrate how different input modalities could be fused in order to maintain consistent scene understanding. By structurally embedding redundancy and diversity at the representational level, this approach bridges the gap between modern deep learning and established functional safety practices, paving the way for certifiable AI systems in autonomous driving.

Multi-task offline safe reinforcement learning (RL) promises to learn a shared optimal safe policy from offline data across multiple tasks. This paradigm provides an effective means for the widespread application of RL in multi-task scenarios with high risk and interaction costs. However, the triple challenges of multi-tasking, safety constraints, and out-of-distribution (OOD) actions pose a significant hurdle for existing methods to ensure safety while maximizing reward returns. In this work, we propose a Conditional Diffusion model with Contextual Prompts (CDCP) to address these challenges. Concretely, we first rethink the requirements and challenges in current multi-task decision-making and control scenarios and establish the objectives of multi-task offline safe RL. Subsequently, we transform the multi-task constrained optimization problem into a conditional generation problem using the diffusion model. Based on this, we design a classifier-free guided cost-constraint strategy to provide flexible cost constraints and eliminate extrapolation errors from OOD actions via supervised learning. Additionally, we introduce a novel contextual prompting method to enhance multi-task representation accuracy and adaptability to unseen tasks. A gradient loss synchronization strategy is also introduced to eliminate gradient interference, improving training stability. Finally, extensive experiments demonstrate that the CDCP algorithm exhibits higher performance and safety in multi-task scenarios than the current state-of-the-art baseline methods. It meets different cost constraints without further training, providing a more flexible cost-constraint solution for the multi-task safe RL.

Reliable object detection is critical for automated driving, yet even state-of-the-art detectors inevitably make errors that can compromise safety. Introspection methods that predict detector failures enable safer deployment by triggering fallback mechanisms or alerting human operators. However, existing approaches rely solely on last-layer features or hand-crafted statistics, discarding valuable information from earlier layers that capture different levels of visual abstraction. We propose Layer Feature Attention (LFA), a lightweight introspection method that learns to aggregate features from multiple backbone layers through an attention mechanism. Our key insight is that detection errors manifest differently across feature hierarchies: low-level layers capture fine-grained details essential for detecting small or occluded objects, while high-level layers encode semantic information for scene understanding. LFA learns layer importance weights end-to-end, enabling both improved error prediction and interpretable analysis of which feature levels are most indicative of detector failures. Extensive experiments on KITTI and BDD100K demonstrate that LFA achieves state-of-the-art introspection performance, outperforming single-layer baselines across multiple detector architectures.

Machine learning (ML) models have achieved remarkable success in areas ranging from healthcare to autonomous systems. Yet, their inherent complexity frequently obscures the reasoning behind their decisions, undermining transparency, accountability, and user trust. Compounding this issue is the absence of a universal methodology for comparing and ranking interpretability across diverse ML models and interpretability techniques. This paper addresses this gap by introducing a configurable framework of quantitative metrics to evaluate and rank interpretability. Our approach offers a structured, heuristic basis for assessing model clarity, decision logic, and accessibility, enabling practitioners to systematically compare interpretability across a wide range of algorithms and techniques. The resulting scores are intended as a practical, domain-configurable heuristic guide for comparison rather than a universal notion of interpretability.

Physical AI systems must reason about real-world dynamics in order to perceive, predict, and act safely under partial observability and uncertainty. World models–learned predictive representations of environment dynamics and action consequences–have emerged as a unifying framework for integrating perception, prediction, planning, and control in embodied agents. This survey provides a comprehensive and technically grounded review of learning-based world models for Physical AI, with particular emphasis on closed-loop decision-making. We organize existing approaches along six compositional design dimensions: state abstraction, temporal dynamics, uncertainty source and treatment, structural prior, observation modality, and decision coupling. Beyond this design-oriented taxonomy, we analyze how world models interact with optimization–highlighting compounding error, planner exploitation, rollout horizon management, and uncertainty calibration as central design tensions. We further examine evaluation methodologies, benchmark ecosystems, and sim-to-real transfer challenges, and synthesize open problems in long-horizon consistency, physical constraint enforcement, data efficiency, and safety. By clarifying recurring trade-offs across robotics and model-based reinforcement learning, this survey outlines principled directions for building reliable and scalable Physical AI systems.

Soft-bodied organisms exhibit prominent morphological adaptability, dynamically reconfiguring shape and stiffness to achieve versatile behaviors. Inspired by these systems, soft robots with diverse morphologies have emerged, yet a unified control framework that rapidly adapts across configurations remains elusive. Here, we introduce a generalizable control system that enables rapid cross-configuration adaptation via reinforcement learning in a shared linear Koopman embedding space. By encoding robot dynamics into this embedding space, our method decouples control policies from specific morphologies, allowing real-time, model-free policy adaptation without retraining from scratch. We validate our system across 33 distinct robot configurations. Our system achieves a 75 × reduction in transfer samples across configurations, while sustaining robust performance under high-speed motion, heavy payloads, and multiactuator faults, and achieving real-world skills previously unattainable in soft robotics. This work establishes an adaptable control framework for diverse soft robot configurations and may offer insights for generalizable control in complex physical systems.

Generalist humanoid motion trackers have recently achieved strong simulation metrics by scaling data and training, yet often remain brittle on hardware during sustained teleoperation due to interface- and dynamics-induced errors. We present MOSAIC, an open-source, full-stack system for humanoid motion tracking and whole-body teleoperation across multiple interfaces. MOSAIC first learns a teleoperation-oriented general motion tracker via RL on a multi-source motion bank with adaptive resampling and rewards that emphasize world-frame motion consistency, which is critical for mobile teleoperation. To bridge the sim-to-real interface gap without sacrificing generality, MOSAIC then performs rapid residual adaptation: an interface-specific policy is trained using minimal interface-specific data, and then distilled into the general tracker through an additive residual module, outperforming naive fine-tuning or continual learning. We validate MOSAIC with systematic ablations, out-of-distribution benchmarking, and real-robot experiments demonstrating robust offline motion replay and online long-horizon teleoperation under realistic latency and noise.

Generating regulation-compliant test scenarios is essential for validating safety-critical automotive systems, yet Large Language Models (LLMs) struggle to ground outputs in long, hierarchical standards. We present RegulaRAG, a Retrieval-Augmented Generation (RAG) pipeline that couples SmartChunking, reference-aware enrichment of paragraphs and tables via graph traversal, with Smart Retrieve Rerank over these enriched units. To test our system, we evaluate on a manually curated dataset covering all scenarios in UN Regulation No. 152 (AEBS). Our study comprises: (i) a three-step progressive search that identifies near-optimal retrieval parameters without exhaustive grid search; (ii) head-to-head comparisons against five baseline RAG systems; and (iii) a robustness stress test that scales the source corpus with distractor content. Outputs are evaluated using a customized penalized scoring metric. Across all experiments, RegulaRAG achieves the highest average Meta-Score (82.99), outperforming the next-best system by 43