Deploying LLM-powered agents in enterprise scenarios such as cloud technical support demands high-quality, domain-specific skills. However, existing skill creators lack domain grounding, producing skills poorly aligned with real-world task requirements. Moreover, once deployed, there is no systematic mechanism to trace execution failures back to skill deficiencies and drive targeted refinements, leaving skill quality stagnant despite accumulating operational evidence. We introduce SkillForge, a self-evolving framework that closes an end-to-end creation-evaluation-refinement loop. To produce well-aligned initial skills, a Domain-Contextualized Skill Creator grounds skill synthesis in knowledge bases and historical support tickets. To enable continuous self-optimization, a three-stage pipeline -- Failure Analyzer, Skill Diagnostician, and Skill Optimizer -- automatically diagnoses execution failures in batch, pinpoints the underlying skill deficiencies, and rewrites the skill to eliminate them. This cycle runs iteratively, allowing skills to self-improve with every round of deployment feedback. Evaluated on five real-world cloud support scenarios spanning 1,883 tickets and 3,737 tasks, experiments show that: (1) the Domain-Contextualized Skill Creator produces substantially better initial skills than the generic skill creator, as measured by consistency with expert-authored reference responses from historical tickets; and (2) the self-evolution loop progressively improves skill quality from diverse starting points (including expert-authored, domain-created, and generic skills) across successive rounds, demonstrating that automated evolution can surpass manually curated expert knowledge.

Abstract Phishing email attacks have evolved into a significant threat, causing substantial economic and political harm. However, existing detection methods often neglect the data heterogeneity resulting from diverse email sources and are trained on balanced email datasets, which do not accurately reflect real-world scenarios. Meanwhile, with increasing privacy protection regulations, it is crucial to develop methods that enhance phishing email detection capabilities while preserving user privacy. To address these challenges, we propose PhFL, a framework based on heterogeneous federated learning, for detecting phishing emails. PhFL decouples clients’ models into representation learning models and classifiers. The representation learning models can be tailored to clients’ specific needs, and the classifiers are globally shared and re-trained on the server, leveraging the class feature means generated by the representation learning models. Our framework allows each client to leverage its private data locally without providing emails to other clients or the server. The collaboration of class feature means and re-training of classifiers effectively address the challenges of class imbalance and data heterogeneity, enabling improved model performance. Experimental results demonstrate that PhFL outperforms other federated learning methods, particularly when different clients have email datasets from diverse sources and face imbalanced class distributions.

Quality assurance of deep neural networks (DNNs) is crucial for the deployment of DNN-based software, especially in mission- and safety-critical tasks. Inspired by structural white-box testing in traditional software, many test criteria have been proposed to test DNNs, i.e., to exhibit erroneous behaviors by activating new test units that have not been covered, such as new neurons, values, and decision paths. Many studies have been done to evaluate the effectiveness of DNN test coverage criteria. However, existing empirical studies mainly focused on measuring the effectiveness of DNN test criteria for improving the adversarial robustness of DNNs, while ignoring the correctness property when testing DNNs. To fill in this gap, we conduct a comprehensive study on 11 structural coverage criteria, 6 widely-used image datasets, and 9 popular DNNs. We investigate the effectiveness of DNN coverage criteria over natural inputs from four aspects: (1) the correlation between test coverage and test diversity; (2) the effects of criteria parameters and target DNNs; (3) the effectiveness to prioritize in-distribution natural inputs that lead to erroneous behaviors; and (4) the capability to detect out-of-distribution natural samples. Our findings include: (1) For measuring the diversity, coverage criteria considering the relationship between different neurons are more effective than coverage criteria that treat each neuron independently. For instance, the neuron-path criteria (i.e., SNPC and ANPC) show high correlation with test diversity, which is promising to measure test diversity for DNNs. (2) The hyper-parameters have a big influence on the effectiveness of criteria, especially those relevant to the granularity of test criteria. Meanwhile, the computational complexity is one of the important issues to be considered when designing deep learning test coverage criteria, especially for large-scale models. (3) Test criteria related to data distribution (i.e., LSA and DSA, SNAC, and NBC) can be used to prioritize both in-distribution natural faults and out-of-distribution inputs. Furthermore, for OOD detection, the boundary metrics (i.e., SNAC and NBC) are also effective indicators with lower computational costs and higher detection efficiency compared with LSA and DSA. These findings motivate follow-up research on scalable test coverage criteria that improve the correctness of DNNs.

Open source software (OSS) licenses regulate the conditions under which OSS can be legally reused, distributed, and modified. However, a common issue arises when incorporating third-party OSS accompanied with licenses, i.e., license incompatibility, which occurs when multiple licenses exist in one project and there are conflicts between them. Despite being problematic, fixing license incompatibility issues requires substantial efforts due to the lack of license understanding and complex package dependency. In this paper, we propose LiResolver, a fine-grained, scalable, and flexible tool to resolve license incompatibility issues for open source software. Specifically, it first understands the semantics of licenses through fine-grained entity extraction and relation extraction. Then, it detects and resolves license incompatibility issues by recommending official licenses in priority. When no official licenses can satisfy the constraints, it generates a custom license as an alternative solution. Comprehensive experiments demonstrate the effectiveness of LiResolver, with 4.09% false positive (FP) rate and 0.02% false negative (FN) rate for incompatibility issue localization, and 62.61% of 230 real-world incompatible projects resolved by LiResolver. We discuss the feedback from OSS developers and the lessons learned from this work. All the datasets and the replication package of LiResolver have been made publicly available to facilitate follow-up research.

Open source software (OSS) licenses regulate the conditions under which users can reuse, modify, and distribute the software legally. However, there exist various OSS licenses in the community, written in a formal language, which are typically long and complicated to understand. In this paper, we conducted a 661-participants online survey to investigate the perspectives and practices of developers towards OSS licenses. The user study revealed an indeed need for an automated tool to facilitate license understanding. Motivated by the user study and the fast growth of licenses in the community, we propose the first study towards automated license summarization. Specifically, we released the first high quality text summarization dataset and designed two tasks, i.e., license text summarization (LTS), aiming at generating a relatively short summary for an arbitrary license, and license term classification (LTC), focusing on the attitude inference towards a predefined set of key license terms (e.g., Distribute). Aiming at the two tasks, we present LiSum, a multi-task learning method to help developers overcome the obstacles of understanding OSS licenses. Comprehensive experiments demonstrated that the proposed jointly training objective boosted the performance on both tasks, surpassing state-of-the-art baselines with gains of at least 5 points w.r.t. F1 scores of four summarization metrics and achieving 95.13% micro average F1 score for classification simultaneously. We released all the datasets, the replication package, and the questionnaires for the community.

Identification of drug-target interactions (DTIs) is crucial for drug discovery and drug repositioning. Existing graph neural network (GNN) based methods only aggregate information from directly connected nodes restricted in a drug-related or a target-related network, and are incapable of capturing long-range dependencies in the biological heterogeneous graph. In this paper, we propose the heterogeneous graph attention network (HGAN) to capture the complex structures and rich semantics in the biological heterogeneous graph for DTI prediction. HGAN enhances heterogeneous graph structure learning from both the intra-layer perspective and the inter-layer perspective. Concretely, we develop an enhanced graph attention diffusion layer (EGADL), which efficiently builds connections between node pairs that may not be directly connected, enabling information passing from important nodes multiple hops away. By stacking multiple EGADLs, we further enlarge the receptive field from the inter-layer perspective. HGAN advances 15 state-of-the-art methods on two heterogeneous biological datasets, achieving the results near to 1 in terms of AUC and AUPR. We also find that enlarging receptive fields from the inter-layer perspective (stacking layers) is more effective than that from the intra-layer perspective (attention diffusion) for HGAN to achieve promising DTI prediction performances. The code is available at https://github.com/Zora-LM/HGAN-DTI.