Beyond Static Leaderboards: Predictive Validity for the Evaluation of LLM Agents

Agent benchmarks are growing fast, but no single benchmark touches more than four or five of the dimensions that deployment exposes. This paper aggregates the largest coordinated deep-dive of one MCP-based industrial-agent benchmark to date: fourteen parallel implementation studies covering new asset classes (including a multi-modal visual extension), alternative orchestrations, retrieval strategies, reasoning modes, infrastructure optimizations, and evaluation-methodology probes. Consolidating those studies with seven prior agent benchmarks, we argue that aggregate-score leaderboards systematically underspecify deployed-agent evaluation. Rankings derived from aggregate scores do not transfer to out-of-distribution settings; recent public-to-hidden competition retrospectives provide direct empirical evidence of this rank instability. We propose ranking configurations by predictive validity, the correlation between in-sample and out-of-sample rank, rather than in-sample mean, and report a twelve-tier measurement apparatus that exposes the deployment-relevant dimensions HELM and its agent-era successors collapse. The position is operationalized through three falsifiable out-of-distribution criteria with explicit thresholds; existing evidence partly supports it but is too thin to confirm. We close with a pre-registered pilot design and a field-level vision for what the next generation of agentic benchmarks should report.

HiMem-WAM: Hierarchical Memory-Gated World Action Models for Robotic Manipulation

World Action Models (WAMs) have emerged as a new powerful paradigm for embodied intelligence, learning action-relevant visual dynamics that significantly enhance generalization and robustness. However, existing WAMs still struggle with task-relevant memory in long-horizon robotic manipulation. To address this, we present HiMem-WAM, a Hierarchical Memory-Gated WAM that integrates motion-centric latent actions, high-level skill latents, and boundary-triggered memory updates. Specifically, we develop a hierarchical latent action framework that jointly learns low-level motion and high-level skill latents, providing structured temporal abstraction. Meanwhile, a boundary-aware memory gate writes compact task states at predicted skill transitions, enabling causal inference without test-time generation of future video or optical flow estimation. Evaluated on LIBERO, LIBERO-PLUS, RMBench and real-world tasks, HiMem-WAM shows that hierarchical latents improve robustness under deployment perturbations, and the memory module substantially benefits memory-dependent long-horizon manipulation.

STAGE: Tackling Semantic Drift in Multimodal Federated Graph Learning

Federated graph learning (FGL) enables collaborative training on graph data across multiple clients. As graph data increasingly contain multimodal node attributes such as text and images, multimodal federated graph learning (MM-FGL) has become an important yet substantially harder setting. The key challenge is that clients from different modality domains may not share a common semantic space: even for the same concept, their local encoders can produce inconsistent representations before collaboration begins. This makes direct parameter coordination unreliable and further causes two downstream problems: forcing heterogeneous client representations into a naively shared semantic space may create false semantic agreement, and graph message passing may amplify residual inconsistency across neighborhoods. To address this issue, we propose \textbf{STAGE}, a protocol-first framework for MM-FGL. Instead of relying on direct parameter averaging, STAGE builds a shared semantic space that first translates heterogeneous multimodal features into comparable representations and then regulates how these representations propagate over local graph structures. In this way, STAGE not only improves cross-client semantic calibration, but also reduces the risk of inconsistency amplification during graph learning. Extensive experiments on 8 multimodal-attributed graphs across 5 graph-centric and modality-centric tasks show that STAGE consistently achieves state-of-the-art performance while reducing per-round communication payload.

EmbodiedClaw: Conversational Workflow Execution for Embodied AI Development

Embodied AI research is increasingly moving beyond single-task, single-environment policy learning toward multi-task, multi-scene, and multi-model settings. This shift substantially increases the engineering overhead and development time required for stages such as evaluation environment construction, trajectory collection, model training, and evaluation. To address this challenge, we propose a new paradigm for embodied AI development in which users express goals and constraints through conversation, and the system automatically plans and executes the development workflow. We instantiate this paradigm with EmbodiedClaw, a conversational agent that turns high-frequency, high-cost embodied research activities, including environment creation and revision, benchmark transformation, trajectory synthesis, model evaluation, and asset expansion, into executable skills. Experiments on end-to-end workflow tasks, capability-specific evaluations, human researcher studies, and ablations show that EmbodiedClaw reduces manual engineering effort while improving executability, consistency, and reproducibility. These results suggest a shift from manual toolchains to conversationally executable workflows for embodied AI development.

Synthesis4AD: Synthetic Anomalies are All You Need for 3D Anomaly Detection

Industrial 3D anomaly detection performance is fundamentally constrained by the scarcity and long-tailed distribution of abnormal samples. To address this challenge, we propose Synthesis4AD, an end-to-end paradigm that leverages large-scale, high-fidelity synthetic anomalies to learn more discriminative representations for 3D anomaly detection. At the core of Synthesis4AD is 3D-DefectStudio, a software platform built upon the controllable synthesis engine MPAS, which injects geometrically realistic defects guided by higher-dimensional support primitives while simultaneously generating accurate point-wise anomaly masks. Furthermore, Synthesis4AD incorporates a multimodal large language model (MLLM) to interpret product design information and automatically translate it into executable anomaly synthesis instructions, enabling scalable and knowledge-driven anomalous data generation. To improve the robustness and generalization of the downstream detector on unstructured point clouds, Synthesis4AD further introduces a training pipeline based on spatial-distribution normalization and geometry-faithful data augmentations, which alleviates the sensitivity of Point Transformer architectures to absolute coordinates and improves feature learning under realistic data variations. Extensive experiments demonstrate state-of-the-art performance on Real3D-AD, MulSen-AD, and a real-world industrial parts dataset. The proposed synthesis method MPAS and the interactive system 3D-DefectStudio will be publicly released at https://github.com/hustCYQ/Synthesis4AD.

AtomVLA: Scalable Post-Training for Robotic Manipulation via Predictive Latent World Models

Vision-Language-Action (VLA) models demonstrate remarkable potential for generalizable robotic manipulation. The execution of complex multi-step behaviors in VLA models can be improved by robust instruction grounding, a critical component for effective control. However, current paradigms predominantly rely on coarse, high-level task instructions during supervised fine-tuning. This instruction grounding gap leaves models without explicit intermediate guidance, leading to severe compounding errors in long-horizon tasks. Therefore, bridging this instruction gap and providing scalable post-training for VLA models is urgent. To tackle this problem, we propose \method, the first subtask-aware VLA framework integrated with a scalable offline post-training pipeline. Our framework leverages a large language model to decompose high-level demonstrations into fine-grained atomic subtasks. This approach utilizes a pretrained predictive world model to score candidate action chunks against subtask goals in the latent space, mitigating error accumulation while significantly improving long-horizon robustness. Furthermore, this approach enables highly efficient Group Relative Policy Optimization without the prohibitive expenses associated with online rollouts on physical robots. Extensive simulations validate that our AtomVLA maintains strong robustness under perturbations. When evaluated against fundamental baseline models, it achieves an average success rate of 97.0\% on the LIBERO benchmark and 48.0\% on the LIBERO-PRO benchmark. Finally, experiments conducted in the real world using the Galaxea R1 Lite platform confirm its broad applicability across diverse tasks, especially long-horizon tasks. All datasets, checkpoints, and code will be released to the public domain following the acceptance of this work for future research.

Levarging Learning Bias for Noisy Anomaly Detection

This paper addresses the challenge of fully unsupervised image anomaly detection (FUIAD), where training data may contain unlabeled anomalies. Conventional methods assume anomaly-free training data, but real-world contamination leads models to absorb anomalies as normal, degrading detection performance. To mitigate this, we propose a two-stage framework that systematically exploits inherent learning bias in models. The learning bias stems from: (1) the statistical dominance of normal samples, driving models to prioritize learning stable normal patterns over sparse anomalies, and (2) feature-space divergence, where normal data exhibit high intra-class consistency while anomalies display high diversity, leading to unstable model responses. Leveraging the learning bias, stage 1 partitions the training set into subsets, trains sub-models, and aggregates cross-model anomaly scores to filter a purified dataset. Stage 2 trains the final detector on this dataset. Experiments on the Real-IAD benchmark demonstrate superior anomaly detection and localization performance under different noise conditions. Ablation studies further validate the framework's contamination resilience, emphasizing the critical role of learning bias exploitation. The model-agnostic design ensures compatibility with diverse unsupervised backbones, offering a practical solution for real-world scenarios with imperfect training data. Code is available at https://github.com/hustzhangyuxin/LLBNAD.

Visual Anomaly Detection under Complex View-Illumination Interplay: A Large-Scale Benchmark

The practical deployment of Visual Anomaly Detection (VAD) systems is hindered by their sensitivity to real-world imaging variations, particularly the complex interplay between viewpoint and illumination which drastically alters defect visibility. Current benchmarks largely overlook this critical challenge. We introduce Multi-View Multi-Illumination Anomaly Detection (M2AD), a new large-scale benchmark comprising 119,880 high-resolution images designed explicitly to probe VAD robustness under such interacting conditions. By systematically capturing 999 specimens across 10 categories using 12 synchronized views and 10 illumination settings (120 configurations total), M2AD enables rigorous evaluation. We establish two evaluation protocols: M2AD-Synergy tests the ability to fuse information across diverse configurations, and M2AD-Invariant measures single-image robustness against realistic view-illumination effects. Our extensive benchmarking shows that state-of-the-art VAD methods struggle significantly on M2AD, demonstrating the profound challenge posed by view-illumination interplay. This benchmark serves as an essential tool for developing and validating VAD methods capable of overcoming real-world complexities. Our full dataset and test suite will be released at https://hustcyq.github.io/M2AD to facilitate the field.

Scaling Graph-Based ANNS Algorithms to Billion-Size Datasets: A Comparative Analysis

Algorithms for approximate nearest-neighbor search (ANNS) have been the topic of significant recent interest in the research community. However, evaluations of such algorithms are usually restricted to a small number of datasets with millions or tens of millions of points, whereas real-world applications require algorithms that work on the scale of billions of points. Furthermore, existing evaluations of ANNS algorithms are typically heavily focused on measuring and optimizing for queries-per second (QPS) at a given accuracy, which can be hardware-dependent and ignores important metrics such as build time. In this paper, we propose a set of principled measures for evaluating ANNS algorithms which refocuses on their scalability to billion-size datasets. These measures include ability to be efficiently parallelized, build times, and scaling relationships as dataset size increases. We also expand on the QPS measure with machine-agnostic measures such as the number of distance computations per query, and we evaluate ANNS data structures on their accuracy in more demanding settings required in modern applications, such as evaluating range queries and running on out-of-distribution data. We optimize four graph-based algorithms for the billion-scale setting, and in the process provide a general framework for making many incremental ANNS graph algorithms lock-free. We use our framework to evaluate the aforementioned graph-based ANNS algorithms as well as two alternative approaches.