Composing basic skills from simple tasks to accomplish composite tasks is crucial for modern intelligent systems. We investigate the in-context composition ability of language models to perform composite tasks that combine basic skills demonstrated in in-context examples. This is more challenging than the standard setting, where skills and their composition can be learned in training. We conduct systematic experiments on various representative open-source language models, utilizing linguistic and logical tasks designed to probe composition abilities. The results reveal that simple task examples can have a surprising negative impact on the performance, because the models generally struggle to recognize and assemble the skills correctly, even with Chain-of-Thought examples. Theoretical analysis further shows that it is crucial to align examples with the corresponding steps in the composition. This inspires a method for the probing tasks, whose improved performance provides positive support for our insights.

Log-based anomaly detection (LogAD) is critical for maintaining the reliability and availability of large-scale online service systems. While machine learning, deep learning, and large language models (LLMs)-based methods have advanced the LogAD, they often suffer from limited interpretability, high inference costs, and extensive preprocessing requirements, limiting their practicality for real-time, high-volume log analysis. In contrast, rule-based systems offer efficiency and transparency, but require significant manual effort and are difficult to scale across diverse and evolving environments. In this paper, We present CodeAD, a novel framework that automatically synthesizes lightweight Python rule functions for LogAD using LLMs. CodeAD introduces a hierarchical clustering and anchor-grounded sampling strategy to construct representative contrastive log windows, enabling LLMs to discern discriminative anomaly patterns. To ensure robustness and generalizability, CodeAD employs an agentic workflow that iteratively generates, tests, repairs, and refines the rules until it meets correctness and abstraction requirements. The synthesized rules are interpretable, lightweight, and directly executable on raw logs, supporting efficient and transparent online anomaly detection. Our comprehensive experiments on three public datasets (BGL, Hadoop, Thunderbird) demonstrate that CodeAD achieves an average absolute improvement of 3.6% F1 score over the state-of-the-art baselines, while processing large datasets up to 4x faster and at a fraction of the cost (total LLM invocation cost under 4 USD per dataset). These results highlight CodeAD as a practical and scalable solution for online monitoring systems, enabling interpretable, efficient, and automated LogAD in real-world environment.

With the rapid advancement of internet technologies, network services have become critical for delivering diverse and reliable applications to users. However, the exponential growth in the number of available services has resulted in many similar offerings, posing significant challenges in selecting optimal services. Predicting Quality of Service (QoS) accurately thus becomes a fundamental prerequisite for ensuring reliability and user satisfaction. However, existing QoS prediction methods often fail to capture rich contextual information and exhibit poor performance under extreme data sparsity and structural noise. To bridge this gap, we propose a novel architecture, QoSMGAA, specifically designed to enhance prediction accuracy in complex and noisy network service environments. QoSMGAA integrates a multi-order attention mechanism to aggregate extensive contextual data and predict missing QoS values effectively. Additionally, our method incorporates adversarial neural networks to perform autoregressive supervised learning based on transformed interaction matrices. To capture complex, higher-order interactions among users and services, we employ a discrete sampling technique leveraging the Gumbel-Softmax method to generate informative negative samples. Comprehensive experimental validation conducted on large-scale real-world datasets demonstrates that our proposed model significantly outperforms existing baseline methods, highlighting its strong potential for practical deployment in service selection and recommendation scenarios.

Recently, semantically constrained adversarial examples (SemanticAE), which are directly generated from natural language instructions, have become a promising avenue for future research due to their flexible attacking forms. To generate SemanticAEs, current methods fall short of satisfactory attacking ability as the key underlying factors of semantic uncertainty in human instructions, such as referring diversity, descriptive incompleteness, and boundary ambiguity, have not been fully investigated. To tackle the issues, this paper develops a multi-dimensional instruction uncertainty reduction (InSUR) framework to generate more satisfactory SemanticAE, i.e., transferable, adaptive, and effective. Specifically, in the dimension of the sampling method, we propose the residual-driven attacking direction stabilization to alleviate the unstable adversarial optimization caused by the diversity of language references. By coarsely predicting the language-guided sampling process, the optimization process will be stabilized by the designed ResAdv-DDIM sampler, therefore releasing the transferable and robust adversarial capability of multi-step diffusion models. In task modeling, we propose the context-encoded attacking scenario constraint to supplement the missing knowledge from incomplete human instructions. Guidance masking and renderer integration are proposed to regulate the constraints of 2D/3D SemanticAE, activating stronger scenario-adapted attacks. Moreover, in the dimension of generator evaluation, we propose the semantic-abstracted attacking evaluation enhancement by clarifying the evaluation boundary, facilitating the development of more effective SemanticAE generators. Extensive experiments demonstrate the superiority of the transfer attack performance of InSUR. Moreover, we realize the reference-free generation of semantically constrained 3D adversarial examples for the first time.

Recent investigations into effective context lengths of modern flagship large language models (LLMs) have revealed major limitations in effective question answering (QA) and reasoning over long and complex contexts for even the largest and most impressive cadre of models. While approaches like retrieval-augmented generation (RAG) and chunk-based re-ranking attempt to mitigate this issue, they are sensitive to chunking, embedding and retrieval strategies and models, and furthermore, rely on extensive pre-processing, knowledge acquisition and indexing steps. In this paper, we propose Tagging-Augmented Generation (TAG), a lightweight data augmentation strategy that boosts LLM performance in long-context scenarios, without degrading and altering the integrity and composition of retrieved documents. We validate our hypothesis by augmenting two challenging and directly relevant question-answering benchmarks -- NoLima and NovelQA -- and show that tagging the context or even just adding tag definitions into QA prompts leads to consistent performance gains over the baseline -- up to 17% for 32K token contexts, and 2.9% in complex reasoning question-answering for multi-hop queries requiring knowledge across a wide span of text. Additional details are available at https://sites.google.com/view/tag-emnlp.

Language models (LMs) often struggle to generate diverse, human-like creative content, raising concerns about the long-term homogenization of human thought through repeated exposure to similar outputs. Yet scalable methods for evaluating LM output diversity remain limited, especially beyond narrow tasks such as random number or name generation, or beyond repeated sampling from a single model. We introduce Infinity-Chat, a large-scale dataset of 26K diverse, real-world, open-ended user queries that admit a wide range of plausible answers with no single ground truth. We introduce the first comprehensive taxonomy for characterizing the full spectrum of open-ended prompts posed to LMs, comprising 6 top-level categories (e.g., brainstorm & ideation) that further breaks down to 17 subcategories. Using Infinity-Chat, we present a large-scale study of mode collapse in LMs, revealing a pronounced Artificial Hivemind effect in open-ended generation of LMs, characterized by (1) intra-model repetition, where a single model consistently generates similar responses, and more so (2) inter-model homogeneity, where different models produce strikingly similar outputs. Infinity-Chat also includes 31,250 human annotations, across absolute ratings and pairwise preferences, with 25 independent human annotations per example. This enables studying collective and individual-specific human preferences in response to open-ended queries. Our findings show that LMs, reward models, and LM judges are less well calibrated to human ratings on model generations that elicit differing idiosyncratic annotator preferences, despite maintaining comparable overall quality. Overall, INFINITY-CHAT presents the first large-scale resource for systematically studying real-world open-ended queries to LMs, revealing critical insights to guide future research for mitigating long-term AI safety risks posed by the Artificial Hivemind.

Large language models (LLMs) have become indispensable for automated code generation, yet the quality and security of their outputs remain a critical concern. Existing studies predominantly concentrate on adversarial attacks or inherent flaws within the models. However, a more prevalent yet underexplored issue concerns how the quality of a benign but poorly formulated prompt affects the security of the generated code. To investigate this, we first propose an evaluation framework for prompt quality encompassing three key dimensions: goal clarity, information completeness, and logical consistency. Based on this framework, we construct and publicly release CWE-BENCH-PYTHON, a large-scale benchmark dataset containing tasks with prompts categorized into four distinct levels of normativity (L0-L3). Extensive experiments on multiple state-of-the-art LLMs reveal a clear correlation: as prompt normativity decreases, the likelihood of generating insecure code consistently and markedly increases. Furthermore, we demonstrate that advanced prompting techniques, such as Chain-of-Thought and Self-Correction, effectively mitigate the security risks introduced by low-quality prompts, substantially improving code safety. Our findings highlight that enhancing the quality of user prompts constitutes a critical and effective strategy for strengthening the security of AI-generated code.

Complex events such as wildfires, floods, and heatwaves are no longer isolated phenomena but interlinked hazards that propagate through interconnected infrastructure networks. When one system fails, others that depend on it often cascade toward collapse, producing widespread disruption and social inequity. Recent crises including the 2023 Vermont flooding, the 2024 Texas winter freeze, and the 2025 Southern California wildfire illustrate how climate - amplified events can simultaneously strain energy, water, communication, and transportation systems. Traditional risk assessments, which often treat hazards as discrete and static events, are insufficient to capture the evolving and compounding nature of modern disasters. Digital Twin (DT) technology offers a promising avenue for improving situational awareness and decision - making under such conditions. Originally introduced for aerospace engineering and later adopted across industrial sectors, DTs create real - time virtual counterparts of physical systems using sensor data, predictive modeling, and feedback control (Grieves & Vickers, 2018; Tao et al., 2019) . Within the built environment, DTs have been applied to asset monitoring, predictive maintenance, and urban system management (Errandonea et al., 2020; Fogli, 2019; Fuller et al., 2020) . However, most conventional DTs rely on stable connectivity, complete datasets, and deterministic control assumptions that are not held during crises characterized by cascading failures and data disruption. To address these challenges, the concept of the Risk - Informed Digital Twin (RDT) integrates probabilistic modeling, uncertainty quantification, and decision support within the DT architecture (Pignatta & Alibrandi, 2022; Zio & Miqueles, 2024) .

Anomaly detection in complex, high-dimensional data, such as UA V sensor readings, is essential for operational safety but challenging for existing methods due to their limited sensitivity, scalability, and inability to capture intricate dependencies. We propose the Diffuse to Detect (DTD) framework, a novel approach that innovatively adapts diffusion models for anomaly detection, diverging from their conventional use in generative tasks with high inference time. By comparison, DTD employs a single-step diffusion process to predict noise patterns, enabling rapid and precise identification of anomalies without reconstruction errors. This approach is grounded in robust theoretical foundations that link noise prediction to the data distribution's score function, ensuring reliable deviation detection. By integrating Graph Neural Networks to model sensor relationships as dynamic graphs, DTD effectively captures spatial (inter-sensor) and temporal anomalies. Its two-branch architecture, with parametric neural network-based energy scoring for scalability and nonparametric statistical methods for interpretability, provides flexible trade-offs between computational efficiency and transparency. Extensive evaluations on UA V sensor data, multivariate time series, and images demonstrate DTD's superior performance over existing methods, underscoring its generality across diverse data modalities. This versatility, combined with its adaptability, positions DTD as a transformative solution for safety-critical applications, including industrial monitoring and beyond.

Edge intelligent applications like VR/AR and language model based chatbots have become widespread with the rapid expansion of IoT and mobile devices. However, constrained edge devices often cannot serve the increasingly large and complex deep learning (DL) models. To mitigate these challenges, researchers have proposed optimizing and offloading partitions of DL models among user devices, edge servers, and the cloud. In this setting, users can take advantage of different services to support their intelligent applications. For example, edge resources offer low response latency. In contrast, cloud platforms provide low monetary cost computation resources for computation-intensive workloads. However, communication between DL model partitions can introduce transmission bottlenecks and pose risks of data leakage. Recent research aims to balance accuracy, computation delay, transmission delay, and privacy concerns. They address these issues with model compression, model distillation, transmission compression, and model architecture adaptations, including internal classifiers. This survey contextualizes the state-of-the-art model offloading methods and model adaptation techniques by studying their implication to a multi-objective optimization comprising inference latency, data privacy, and resource monetary cost.