Multi-behavior recommendation systems enhance prediction accuracy for target behavior (e.g., purchase) by integrating auxiliary behaviors such as viewing and adding to cart. However, existing models face two fundamental challenges regarding data characteristics: On one hand, they typically treat all auxiliary behaviors equally or apply simple weighting, lacking effective mechanisms to evaluate and filter inherent noise, leading to contaminated feature representations. On the other hand, when fusing sparse target features with abundant auxiliary features, the critical target signal is easily diluted, losing its dominant role in the final prediction. To address this, we propose a Target-Enhanced Gated Transformer model TEGT. Its core innovations include: a behavior-adaptive gating module that filters source-level noise through nonlinear transformations and hard thresholding while generating importance weights; a target-guided dual-modulation attention mechanism utilizes target behavior as queries to retrieve semantically relevant auxiliary signals, then applies secondary modulation by combining gated weights to ensure both noise resistance and target dominance in the fusion process; a lightweight collaborative semantic enhancement module clusters the fused representations and employs cluster-center contrastive learning to explicitly amplify collaborative signals under sparse target behavior. Extensive experiments on three real-world datasets show that TEGT consistently outperforms state-of-the-art baselines, it achieves remarkable improvements of up to 9.73% in Recall@10 and 9.16% in NDCG@10.

Existing LLM-driven recommendation systems (RS) suffer from over-reliance on a single pre-trained model, which limits adaptability across diverse scenarios due to differences in large language models' strengths in semantics, knowledge, and reasoning. To address this issue, we propose AMLrec (Adaptive Multi-LLM Recommendation), a dynamic routing-based adaptive multi-LLM collaboration framework that unifies two dominant paradigms—LLM as Recommender and LLM + Recommender—through decision knowledge complementation. For each user or item, a lightweight encoder generates embeddings that are compared with learnable LLM prototypes using cosine similarity to select the most suitable models. In the first paradigm, selected LLMs generate recommendations via structured prompts, and their outputs are aggregated to form the final recommendation list. In the second paradigm, chosen LLMs produce semantic embeddings, which are fused with learnable embeddings after PCA-based dimensionality reduction and aligned using a lightweight adapter to bridge distribution gaps. Notably, AMLrec does not require fine-tuning of the underlying LLMs, significantly reducing computational overhead. Experiments on real-world datasets demonstrate that the proposed approach consistently outperforms single-LLM baselines across all evaluation metrics, validating its effectiveness. The main contributions of this work are threefold: introducing dynamic routing for multi-LLM recommendation system collaboration, proposing a unified architecture that harmonizes both paradigms, and enabling efficient adaptation without LLM fine-tuning. The code is available at https://github.com/Jiale-12138/AMLrec.

Multi-behavior recommender systems improve prediction accuracy of target behaviors (e.g., purchases) by integrating auxiliary behaviors (e.g., page views). However, existing models face two key limitations: (1) Static propagation mechanisms and inflexible dependency modeling fail to capture dynamic changes in user preferences and cascading relationships between behaviors; (2) Sparse target behavior data usually leads to excessive influence of auxiliary signals, which degrades recommendation quality. To address these challenges, we propose the Dynamic Dependency-Aware Collaborative Contrastive Learning Multi-Behavior Recommendation Model, MBDCC. MBDCC has two dedicated modules: (1) Behavioral gating cascade and cross-attention fusion module, which dynamically models cascading dependencies between behaviors through learnable gate control transfer units controlled by behavioral attributes. This replaces static propagation with adaptive feature flow regulation, capturing evolving user preferences. Meanwhile, it uses a target-guided cross-attention mechanism to selectively fuse semantically relevant auxiliary signals using the target behavior as a query, addressing inflexible cross-behavioral dependency modeling; (2) Collaborative semantic enhancement module, it constructs a user similarity measure matrix based on co-occurrence frequency of interaction items in target behavior, and clusters nodes using a hybrid clustering strategy. By introducing contrastive learning between nodes and their clustering centers, the collaborative semantic information between similar nodes under the target behavior is effectively captured and amplified, alleviating the challenge of sparse target interaction data. Extensive experiments on three real-world datasets show that MBDCC consistently outperforms state-of-the-art baselines, it achieves remarkable improvements of up to 6.84% in Recall@10 and 5.18% in NDCG@50. Moreover, ablation experiments further demonstrate the correctness of our motivation and the necessity of the various modules of the MBDCC model.

Abstract Recently, many deep learning-based models have been successfully applied to click-through rate prediction. However, most previous models focus only on feature-level interactions between a single user behavior and the target item or only treat the user’s historical behavior as a sequence to uncover the hidden interests behind it when mining user interests. This can lead to user interest that evolves over time dynamically being ignored or the interest shown by a single user’s behavior not being exploited. Based on the above problems, we propose evolving interest with feature co-action network (EIFCN). Specifically, we first design user dynamic interest network to treat the user’s historical behavior as a sequence of information, and tap into the user’s hidden interests over time. In this part, we use a multi-head self-attention mechanism to initially process the data and then pass it into the deep learning network. Then a feature co-action network is designed to mine the user’s single behavior and the displayed feature-level interactions of the target item. Experimental results show that the EIFCN model performs better than other models.

With the rapid development of location-based social networks (LBSNs), point of interest (POI) recommendation has become an important way to meet users' personalized demands. The aim of POI recommendation is to provide personalized recommendation of POIs for mobile users. However, traditional POI recommendation systems cannot satisfy users' personalized demands. The reason is that the traditional POI recommendation system cannot recommend the next POI to a user based on the user's context information. Also, the traditional POI recommendation system provides no real-time guarantee on performance. In this demo, we propose a novel real-time next POI recommendation system named R2SIGTP which provides more personalized real-time recommendation compared with existing ones. Our system has the following advantages: 1) it has real-time performance; 2) it uses a unified approach to integrate geographic and preference information; 3) it considers the feedback of each single user to provide more personalized recommendation. We have implemented our system. R2SIGTP is easy to use and can be used by the mobile terminal's browser to recommend the next POI to the user in real-time based on the automatically identified user location and current time. The experimental results on real-world LBSNs show that R2SIGTP's performance is satisfactory.

With the continuous construction and development of university library, how to find interesting books from the massive books is becoming a concerned problem. In this paper, we develop a personalized book recommender system based on Chinese Library Classification Method named CLCM. CLCM uses Upper and Lower Level Relations Model (ULLRM) to describe the characteristic words and fuses the Dominant and Recessive Feedback Model (DRFM) to update the users' preferences. And visualization of book inquiry improves the efficiency of inquiring. The experimental results show that CLCM performs much better than the state-of-the art approaches in the university library.