Zibin Zheng

Jiezhu Cheng, Cuiyun Gao, Zibin Zheng

Modern software systems are usually highly configurable, providing users with customized functionality through various configuration options. Understanding how system performance varies with different option combinations is important to determine optimal configurations that meet specific requirements. Due to the complex interactions among multiple options and the high cost of performance measurement under a huge configuration space, it is challenging to study how different configurations influence the system performance. To address these challenges, we propose HINNPerf, a novel hierarchical interaction neural network for performance prediction of configurable systems. HINNPerf employs the embedding method and hierarchic network blocks to model the complicated interplay between configuration options, which improves the prediction accuracy of the method. Besides, we devise a hierarchical regularization strategy to enhance the model robustness. Empirical results on 10 real-world configurable systems show that our method statistically significantly outperforms state-of-the-art approaches by achieving average 22.67% improvement in prediction accuracy. In addition, combined with the Integrated Gradients method, the designed hierarchical architecture provides some insights about the interaction complexity and the significance of configuration options, which might help users and developers better understand how the configurable system works and efficiently identify significant options affecting the performance.

Yuxuan Chen, Mingwei Liu, Guangsheng Ou et al.

Code search is essential for code reuse, allowing developers to efficiently locate relevant code snippets. The advent of powerful decoder-only Large Language Models (LLMs) has revolutionized many code intelligence tasks. However, their effectiveness for the retrieval-based task of code search, particularly compared to established encoder-based models, remains underexplored. This paper addresses this gap by presenting a large-scale systematic evaluation of eleven decoder-only LLMs, analyzing their performance across zero-shot and fine-tuned settings. Our results show that fine-tuned decoder-only models, particularly CodeGemma, significantly outperform encoder-only models like UniXcoder, achieving a 40.4% higher Mean Average Precision (MAP) on the CoSQA$^+$ benchmark. Our analysis further reveals two crucial nuances for practitioners: first, the relationship between model size and performance is non-monotonic, with mid-sized models often outperforming larger variants; second, the composition of the training data is critical, as a multilingual dataset enhances generalization while a small amount of data from a specific language can act as noise and interfere with model effectiveness. These findings offer a comprehensive guide to selecting and optimizing modern LLMs for code search.

Kaifeng He, Mingwei Liu, Chong Wang et al.

Code generation with large language models (LLMs) is highly sensitive to token selection during decoding, particularly at uncertain decision points that influence program logic. While standard strategies such as greedy decoding treat all tokens uniformly, they overlook code-specific uncertainty patterns, leading to suboptimal performance. This paper presents an empirical study revealing that many generation errors stem from token ranking mistakes at high-uncertainty steps, where the correct token is present but not top-ranked. Motivated by these findings, we propose AdaDec, a lookahead-based uncertainty-guided adaptive decoding framework that integrates a token-level pause-then-rerank mechanism driven by token uncertainty. AdaDec learns model-specific uncertainty thresholds and applies a lookahead-based reranking strategy when uncertainty is high. Experiments on HumanEval+, MBPP+, and DevEval benchmarks show that AdaDec improves Pass@1 accuracy by up to 20.9% in absolute terms over greedy decoding. More importantly, it consistently outperforms both competitive baselines like Beam Search and state-of-the-art adaptive decoding methods such as AdapT, while maintaining high efficiency through selective, uncertainty-triggered pausing. Our results highlight the promise of uncertainty-aware adaptive decoding for improving both the reliability and efficiency of LLM-based code generation.

Yanlin Wang, Xinyi Xu, Jiachi Chen et al.

The rise of large language models (LLMs) has sparked a surge of interest in agents, leading to the rapid growth of agent frameworks. Agent frameworks are software toolkits and libraries that provide standardized components, abstractions, and orchestration mechanisms to simplify agent development. Despite widespread use of agent frameworks, their practical applications and how they influence the agent development process remain underexplored. Different agent frameworks encounter similar problems during use, indicating that these recurring issues deserve greater attention and call for further improvements in agent framework design. Meanwhile, as the number of agent frameworks continues to grow and evolve, more than 80% of developers report difficulties in identifying the frameworks that best meet their specific development requirements. In this paper, we conduct the first empirical study of LLM-based agent frameworks, exploring real-world experiences of developers in building AI agents. To compare how well the agent frameworks meet developer needs, we further collect developer discussions for the ten previously identified agent frameworks, resulting in a total of 11,910 discussions. Finally, by analyzing these discussions, we compare the frameworks across five dimensions: development efficiency, functional abstraction, learning cost, performance optimization, and maintainability, which refers to how easily developers can update and extend both the framework itself and the agents built upon it over time. Our comparative analysis reveals significant differences among frameworks in how they meet the needs of agent developers. Overall, we provide a set of findings and implications for the LLM-driven AI agent framework ecosystem and offer insights for the design of future LLM-based agent frameworks and agent developers.

Yuchang Zhu, Jintang Li, Zibin Zheng et al.

Group fairness for Graph Neural Networks (GNNs), which emphasizes algorithmic decisions neither favoring nor harming certain groups defined by sensitive attributes (e.g., race and gender), has gained considerable attention. In particular, the objective of group fairness is to ensure that the decisions made by GNNs are independent of the sensitive attribute. To achieve this objective, most existing approaches involve eliminating sensitive attribute information in node representations or algorithmic decisions. However, such ways may also eliminate task-related information due to its inherent correlation with the sensitive attribute, leading to a sacrifice in utility. In this work, we focus on improving the fairness of GNNs while preserving task-related information and propose a fair GNN framework named FairSAD. Instead of eliminating sensitive attribute information, FairSAD enhances the fairness of GNNs via Sensitive Attribute Disentanglement (SAD), which separates the sensitive attribute-related information into an independent component to mitigate its impact. Additionally, FairSAD utilizes a channel masking mechanism to adaptively identify the sensitive attribute-related component and subsequently decorrelates it. Overall, FairSAD minimizes the impact of the sensitive attribute on GNN outcomes rather than eliminating sensitive attributes, thereby preserving task-related information associated with the sensitive attribute. Furthermore, experiments conducted on several real-world datasets demonstrate that FairSAD outperforms other state-of-the-art methods by a significant margin in terms of both fairness and utility performance. Our source code is available at https://github.com/ZzoomD/FairSAD.

Yuchang Zhu, Jintang Li, Yatao Bian et al.

Recent studies have highlighted fairness issues in Graph Neural Networks (GNNs), where they produce discriminatory predictions against specific protected groups categorized by sensitive attributes such as race and age. While various efforts to enhance GNN fairness have made significant progress, these approaches are often tailored to specific sensitive attributes. Consequently, they necessitate retraining the model from scratch to accommodate changes in the sensitive attribute requirement, resulting in high computational costs. To gain deeper insights into this issue, we approach the graph fairness problem from a causal modeling perspective, where we identify the confounding effect induced by the sensitive attribute as the underlying reason. Motivated by this observation, we formulate the fairness problem in graphs from an invariant learning perspective, which aims to learn invariant representations across environments. Accordingly, we propose a graph fairness framework based on invariant learning, namely FairINV, which enables the training of fair GNNs to accommodate various sensitive attributes within a single training session. Specifically, FairINV incorporates sensitive attribute partition and trains fair GNNs by eliminating spurious correlations between the label and various sensitive attributes. Experimental results on several real-world datasets demonstrate that FairINV significantly outperforms state-of-the-art fairness approaches, underscoring its effectiveness. Our code is available via: https://github.com/ZzoomD/FairINV/.

Jin Jia, Zhiling Deng, Zhuangbin Chen et al.

As LLM-based Multi-Agent Systems (MAS) are increasingly deployed for complex tasks, ensuring their reliability has become a pressing challenge. Since MAS coordinate through unstructured natural language rather than rigid protocols, they are prone to semantic failures (e.g., hallucinations, misinterpreted instructions, and reasoning drift) that propagate silently without raising runtime exceptions. Prevailing evaluation approaches, which measure only end-to-end task success, offer limited insight into how these failures arise or how effectively agents recover from them. To bridge this gap, we propose MAS-FIRE, a systematic framework for fault injection and reliability evaluation of MAS. We define a taxonomy of 15 fault types covering intra-agent cognitive errors and inter-agent coordination failures, and inject them via three non-invasive mechanisms: prompt modification, response rewriting, and message routing manipulation. Applying MAS-FIRE to three representative MAS architectures, we uncover a rich set of fault-tolerant behaviors that we organize into four tiers: mechanism, rule, prompt, and reasoning. This tiered view enables fine-grained diagnosis of where and why systems succeed or fail. Our findings reveal that stronger foundation models do not uniformly improve robustness. We further show that architectural topology plays an equally decisive role, with iterative, closed-loop designs neutralizing over 40% of faults that cause catastrophic collapse in linear workflows. MAS-FIRE provides the process-level observability and actionable guidance needed to systematically improve multi-agent systems.

Zhiyuan Fang, Yuegui Huang, Zicong Hong et al.

Mixture of Experts (MoE), with its distinctive sparse structure, enables the scaling of language models up to trillions of parameters without significantly increasing computational costs. However, the substantial parameter size presents a challenge for inference, as the expansion in GPU memory cannot keep pace with the growth in parameters. Although offloading techniques utilise memory from the CPU and disk and parallelise the I/O and computation for efficiency, the computation for each expert in MoE models is often less than the I/O, resulting in numerous bubbles in the pipeline. Therefore, we propose Klotski, an efficient MoE inference engine that significantly reduces pipeline bubbles through a novel expert-aware multi-batch pipeline paradigm. The proposed paradigm uses batch processing to extend the computation time of the current layer to overlap with the loading time of the next layer. Although this idea has been effectively applied to dense models, more batches may activate more experts in the MoE, leading to longer loading times and more bubbles. Thus, unlike traditional approaches, we balance computation and I/O time and minimise bubbles by orchestrating their inference orders based on their heterogeneous computation and I/O requirements and activation patterns under different batch numbers. Moreover, to adapt to different hardware environments and models, we design a constraint-sensitive I/O-compute planner and a correlation-aware expert prefetcher for a schedule that minimises pipeline bubbles. Experimental results demonstrate that Klotski achieves a superior throughput-latency trade-off compared to state-of-the-art techniques, with throughput improvements of up to 85.12x.

Zhiyuan Fang, Zicong Hong, Yuegui Huang et al.

Large Language Models (LLMs) have demonstrated impressive performance across various tasks, and their application in edge scenarios has attracted significant attention. However, sparse-activated Mixture-of-Experts (MoE) models, which are well suited for edge scenarios, have received relatively little attention due to their high memory demands. Offload-based methods have been proposed to address this challenge, but they face difficulties with expert prediction. Inaccurate expert predictions can result in prolonged inference delays. To promote the application of MoE models in edge scenarios, we propose Fate, an offloading system designed for MoE models to enable efficient inference in resource-constrained environments. The key insight behind Fate is that gate inputs from adjacent layers can be effectively used for expert prefetching, achieving high prediction accuracy without additional GPU overhead. Furthermore, Fate employs a shallow-favoring expert caching strategy that increases the expert hit rate to 99\%. Additionally, Fate integrates tailored quantization strategies for cache optimization and IO efficiency. Experimental results show that, compared to Load on Demand and Expert Activation Path-based method, Fate achieves up to 4.5x and 1.9x speedups in prefill speed and up to 4.1x and 2.2x speedups in decoding speed, respectively, while maintaining inference quality. Moreover, Fate's performance improvements are scalable across different memory budgets.

Zekai Zhang, Dan Li, Shunyu Wu et al.

Prognostic and Health Management (PHM) are crucial ways to avoid unnecessary maintenance for Cyber-Physical Systems (CPS) and improve system reliability. Predicting the Remaining Useful Life (RUL) is one of the most challenging tasks for PHM. Existing methods require prior knowledge about the system, contrived assumptions, or temporal mining to model the life cycles of machine equipment/devices, resulting in diminished accuracy and limited applicability in real-world scenarios. This paper proposes a Bi-directional Adversarial network with Covariate Encoding for machine Remaining Useful Life (BACE-RUL) prediction, which only adopts sensor measurements from the current life cycle to predict RUL rather than relying on previous consecutive cycle recordings. The current sensor measurements of mechanical devices are encoded to a conditional space to better understand the implicit inner mechanical status. The predictor is trained as a conditional generative network with the encoded sensor measurements as its conditions. Various experiments on several real-world datasets, including the turbofan aircraft engine dataset and the dataset collected from degradation experiments of Li-Ion battery cells, show that the proposed model is a general framework and outperforms state-of-the-art methods.

Jingwen Tan, Gopi Krishnan Rajbahadur, Zi Li et al.

Dataset license compliance is a critical yet complex aspect of developing commercial AI products, particularly with the increasing use of publicly available datasets. Ambiguities in dataset licenses pose significant legal risks, making it challenging even for software IP lawyers to accurately interpret rights and obligations. In this paper, we introduce LicenseGPT, a fine-tuned foundation model (FM) specifically designed for dataset license compliance analysis. We first evaluate existing legal FMs (i.e., FMs specialized in understanding and processing legal texts) and find that the best-performing model achieves a Prediction Agreement (PA) of only 43.75%. LicenseGPT, fine-tuned on a curated dataset of 500 licenses annotated by legal experts, significantly improves PA to 64.30%, outperforming both legal and general-purpose FMs. Through an A/B test and user study with software IP lawyers, we demonstrate that LicenseGPT reduces analysis time by 94.44%, from 108 seconds to 6 seconds per license, without compromising accuracy. Software IP lawyers perceive LicenseGPT as a valuable supplementary tool that enhances efficiency while acknowledging the need for human oversight in complex cases. Our work underscores the potential of specialized AI tools in legal practice and offers a publicly available resource for practitioners and researchers.

Dan Lin, Shunfeng Lu, Ziyan Liu et al.

Cross-chain bridges play a vital role in enabling blockchain interoperability. However, due to the inherent design flaws and the enormous value they hold, they have become prime targets for hacker attacks. Existing detection methods show progress yet remain limited, as they mainly address single-chain behaviors and fail to capture cross-chain semantics. To address this gap, we leverage heterogeneous graph attention networks, which are well-suited for modeling multi-typed entities and relations, to capture the complex execution semantics of cross-chain behaviors. We propose BridgeShield, a detection framework that jointly models the source chain, off-chain coordination, and destination chain within a unified heterogeneous graph representation. BridgeShield incorporates intra-meta-path attention to learn fine-grained dependencies within cross-chain paths and inter-meta-path attention to highlight discriminative cross-chain patterns, thereby enabling precise identification of attack behaviors. Extensive experiments on 51 real-world cross-chain attack events demonstrate that BridgeShield achieves an average F1-score of 92.58%, representing a 24.39% improvement over state-of-the-art baselines. These results validate the effectiveness of BridgeShield as a practical solution for securing cross-chain bridges and enhancing the resilience of multi-chain ecosystems.

Junyuan Fang, Huimin Liu, Han Yang et al.

In recent years, graph neural networks (GNNs) have shown great potential in addressing various graph structure-related downstream tasks. However, recent studies have found that current GNNs are susceptible to malicious adversarial attacks. Given the inevitable presence of adversarial attacks in the real world, a variety of defense methods have been proposed to counter these attacks and enhance the robustness of GNNs. Despite the commendable performance of these defense methods, we have observed that they tend to exhibit a structural bias in terms of their defense capability on nodes with low degree (i.e., tail nodes), which is similar to the structural bias of traditional GNNs on nodes with low degree in the clean graph. Therefore, in this work, we propose a defense strategy by including hetero-homo augmented graph construction, $k$NN augmented graph construction, and multi-view node-wise attention modules to mitigate the structural bias of GNNs against adversarial attacks. Notably, the hetero-homo augmented graph consists of removing heterophilic links (i.e., links connecting nodes with dissimilar features) globally and adding homophilic links (i.e., links connecting nodes with similar features) for nodes with low degree. To further enhance the defense capability, an attention mechanism is adopted to adaptively combine the representations from the above two kinds of graph views. We conduct extensive experiments to demonstrate the defense and debiasing effect of the proposed strategy on benchmark datasets.

Qichao Wang, Huan Ma, Wentao Wei et al.

The rapid development of digital economy has led to the emergence of various black and shadow internet industries, which pose potential risks that can be identified and managed through digital risk management (DRM) that uses different techniques such as machine learning and deep learning. The evolution of DRM architecture has been driven by changes in data forms. However, the development of AI-generated content (AIGC) technology, such as ChatGPT and Stable Diffusion, has given black and shadow industries powerful tools to personalize data and generate realistic images and conversations for fraudulent activities. This poses a challenge for DRM systems to control risks from the source of data generation and to respond quickly to the fast-changing risk environment. This paper aims to provide a technical analysis of the challenges and opportunities of AIGC from upstream, midstream, and downstream paths of black/shadow industries and suggest future directions for improving existing risk control systems. The paper will explore the new black and shadow techniques triggered by generative AI technology and provide insights for building the next-generation DRM system.

Qinglin Yang, Yetong Zhao, Huawei Huang et al.

Metaverse as the latest buzzword has attracted great attention from both industry and academia. Metaverse seamlessly integrates the real world with the virtual world and allows avatars to carry out rich activities including creation, display, entertainment, social networking, and trading. Thus, it is promising to build an exciting digital world and to transform a better physical world through the exploration of the metaverse. In this survey, we dive into the metaverse by discussing how Blockchain and Artificial Intelligence (AI) fuse with it through investigating the state-of-the-art studies across the metaverse components, digital currencies, AI applications in the virtual world, and blockchain-empowered technologies. Further exploitation and interdisciplinary research on the fusion of AI and Blockchain towards metaverse will definitely require collaboration from both academia and industries. We wish that our survey can help researchers, engineers, and educators build an open, fair, and rational future metaverse.

Lu Liu, Sicong Zhou, Huawei Huang et al.

Decentralized Autonomous Organization (DAO) is believed to play a significant role in our future society governed in a decentralized way. In this article, we first explain the definitions and preliminaries of DAO. Then, we conduct a literature review of the existing studies of DAO published in the recent few years. Through the literature review, we find out that a comprehensive survey towards the state-of-the-art studies of DAO is still missing. To fill this gap, we perform such an overview by identifying and classifying the most valuable proposals and perspectives closely related to the combination of DAO and blockchain technologies. We anticipate that this survey can help researchers, engineers, and educators acknowledge the cutting-edge development of blockchain-related DAO technologies.

Peilin Zheng, Zibin Zheng, Hong-ning Dai

Blockchain-based cryptocurrencies have received extensive attention recently. Massive data has been stored on permission-less blockchains. The analysis on massive blockchain data can bring huge business values. However, the lack of well-processed up-to-date blockchain datasets impedes big data analytics of blockchain data. To fill this gap, we collect and process the up-to-date on-chain data from Ethereum, which is one of the most popular permission-less blockchains. We name these well-processed Ethereum datasets as XBlock-ETH, which consists of the data of blockchain transactions, smart contracts, and cryptocurrencies (i.e., tokens). The basic statistics and exploration of these datasets are presented. We also outline the possible research opportunities. The datasets with the raw data and codes have been publicly released online.

Kele Xu, Haibo Mi, Dawei Feng et al.

Valuable training data is often owned by independent organizations and located in multiple data centers. Most deep learning approaches require to centralize the multi-datacenter data for performance purpose. In practice, however, it is often infeasible to transfer all data to a centralized data center due to not only bandwidth limitation but also the constraints of privacy regulations. Model averaging is a conventional choice for data parallelized training, but its ineffectiveness is claimed by previous studies as deep neural networks are often non-convex. In this paper, we argue that model averaging can be effective in the decentralized environment by using two strategies, namely, the cyclical learning rate and the increased number of epochs for local model training. With the two strategies, we show that model averaging can provide competitive performance in the decentralized mode compared to the data-centralized one. In a practical environment with multiple data centers, we conduct extensive experiments using state-of-the-art deep network architectures on different types of data. Results demonstrate the effectiveness and robustness of the proposed method.