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.

Recent studies have demonstrated the effectiveness of LLM test-time scaling. However, existing approaches to incentivize LLMs’ deep thinking abilities generally require large-scale data or significant training efforts. Meanwhile, it remains unclear how to improve the thinking abilities of less powerful base models. In this work, we introduce S^2R, an efficient framework that enhances LLM reasoning by teaching models to self-verify and self-correct during inference. Specifically, we first initialize LLMs with iterative self-verification and self-correction behaviors through supervised fine-tuning on carefully curated data. The self-verification and self-correction skills are then further strengthened by outcome-level and process-level reinforcement learning with minimized resource requirements. Our results demonstrate that, with only 3.1k behavior initialization samples, Qwen2.5-math-7B achieves an accuracy improvement from 51.0% to 81.6%, outperforming models trained on an equivalent amount of long-CoT distilled data. We also discuss the effect of different RL strategies on enhancing LLMs’ deep reasoning. Extensive experiments and analysis based on three base models across both in-domain and out-of-domain benchmarks validate the effectiveness of S^2R.

Multi-Depot Vehicle Routing Problem (MDVRP) requires constructing routes from multiple depots to geographically dispersed customers under capacity constraints. Unlike single-depot routing problems, MDVRP requires determining not only the routing relationship between customers but also the assignment relationship of customers to depots. In this paper, we propose a Hyper-Relation Fusion (HRF) neural combinatorial optimization algorithm to solve MDVRP, considering both heterogeneous relationships and homogeneous relationships between depots and customers. The heterogeneous relationships of depot-customer and customer-customer are captured through graph attention to distinguish different types of connectivity. The homogeneous relationships are learned by aggregating the features of all nodes via a graph convolutional network. Finally, HRF fuses the original node features, heterogeneous features, and homogeneous features, which are further processed through an encoder-decoder architecture to generate the solution. Comprehensive experiments on synthetic and benchmark datasets demonstrate that HRF surpasses the state-of-the-art metaheuristics and learning-based methods in solution quality. Our code is available at https://github.com/lxy0068/HRF-MDVRP.

Hand gesture is a new emerging biometric trait containing both physiological and behavioral characteristics. With the popularity of various cameras, and the rich identity features and contactless authentication mode embedded in gestures themselves, vision-based hand gesture authentication has great potential value. However, current hand gesture authentication methods heavily rely on defined gestures and require identical enrollment and verification gestures, which limits the user-friendliness and efficiency of authentication. It is arguably true that authentication in a simpler and faster way, without the need to remember gestures, will be more approachable. Thus, a fast dynamic random hand gesture authentication method is introduced, in which users can perform a random improvised gesture in both the enrollment and verification stage. To better utilize the physiological and behavioral characteristics of hand gestures, an efficient network named Temporal Difference Symbiotic Neural Network (TDS-Net) equipped with our designed behavioral energy-based feature fusion module (BE-Fusion module) is proposed. Extensive experiments on the SCUT-DHGA dataset demonstrate that TDS-Net outperforms the recent state-of-the-art methods.

In recent years, biometrics have received considerable attention for its reliability and usability. Dynamic-hand-gesture is one of the representative biometric modalities, with advantages of safety and template-replaceability, has huge potential value. However, due to the lack of large-scale dataset and comprehensive evaluation methods, few researches are intended to study the dynamic-hand-gesture authentication method. In this article, we introduce a new dataset SCUT-DHGA, which is the first large-scale Dynamic-Hand-Gestures-Authentication dataset. SCUT-DHGA contains 29,160 dynamic-hand-gesture video sequences and more than 1.86 million frames for both color and depth modalities acquired from 193 volunteers. Six kinds of dynamic-hand-gestures are carefully designed for researching two types of authentication tasks: gesture-predefined authentication and gesture-free authentication. To investigate the hypothesis that users' gestures would be variant after time-span, which will degrade the performance of a dynamic-hand-gesture authentication system, two separate sessions' data were acquired from 50 volunteers with an average interval of one week. Beside the SCUT-DHGA dataset, we also benchmark this dataset with our proposed DHGA-net. By releasing such a large-scale dataset and benchmark, we expect dynamic-hand-gesture authentication methods to gain further improvement and generalization.

The SALSA algorithm combines the main features of the PageRank and the HITS, which achieves better results than PageRank and HITS algorithm. The SALSA divides the nodes into two types of authority and hub as the HITS algorithm and adopts the random walk mode like the PageRank. Here tries applying the SALSA algorithm to the scene that recommends actors for films and TV dramas. The basic data is crawled by web crawler from douban.com, and it contains 500 films and 500 TV dramas with their chief four actors and scores. In this experiment, the films and TV dramas are seen as hub nodes, and the actors are seen as authority node. After hundred interactions of SALSA algorithm, a network index of each node is calculated. The higher the value is, the more worthy of recommendation.