Interactive recommendation is a typical information-seeking task that allows users to interactively express their needs through natural language and obtain personalized recommendations. Large language model-powered (LLM-powered) agents have become a new paradigm in interactive recommendations, effectively capturing users' real-time needs and enhancing personalized experiences. However, due to limited planning and generalization capabilities, existing formulations of LLM-powered interactive recommender agents struggle to effectively address diverse and complex user intents, such as intuitive, unrefined, or occasionally ambiguous requests. To tackle this challenge, we propose a novel ThoughtAugmented Interactive Recommender Agent system (TAIRA) that addresses complex user intents through distilled thought patterns. Specifically, TAIRA is designed as an LLM-powered multi-agent system featuring a manager agent that orchestrates recommendation tasks by decomposing user needs and planning subtasks, with its planning capacity strengthened through Thought Pattern Distillation (TPD), a thought-augmentation method that extracts high-level thoughts from the agent's and human experts' experiences. Through comprehensive experiments conducted across multiple designed datasets, TAIRA exhibits significantly enhanced performance compared to existing methods. Notably, TAIRA's thought augmentation strategies endow the agent system with the ability to solve complex tasks while generalizing effectively on novel tasks, validating its potential as a foundational framework for agent systems, particularly in complex user intent scenarios.

Transformer structures have been widely used in sequential recommender systems (SRS). However, as user interaction histories increase, computational time and memory requirements also grow. This is mainly caused by the standard attention mechanism. Although there exist many methods employing efficient attention and SSM-based models, these approaches struggle to effectively model long sequences and may exhibit unstable performance on short sequences. To address these challenges, we design a sparse attention mechanism, BlossomRec, which models both long-term and short-term user interests through attention computation to achieve stable performance across sequences of varying lengths. Specifically, we categorize user interests in recommendation systems into long-term and short-term interests, and compute them using two distinct sparse attention patterns, with the results combined through a learnable gated output. Theoretically, it significantly reduces the number of interactions participating in attention computation. Extensive experiments on four public datasets demonstrate that BlossomRec, when integrated with state-of-the-art Transformer-based models, achieves comparable or even superior performance while significantly reducing memory usage, providing strong evidence of BlossomRec's efficiency and effectiveness. The code is available at https://github.com/Applied-Machine-Learning-Lab/WWW2026_BlossomRec.

In the era of data-centric AI, the focus of recommender systems has shifted from model-centric innovations to data-centric approaches. The success of modern AI models is built on large-scale datasets, but this also results in significant training costs. Dataset distillation has emerged as a key solution, condensing large datasets to accelerate model training while preserving model performance. However, condensing discrete and sequentially correlated user-item interactions, particularly with extensive item sets, presents considerable challenges. This paper introduces TD3, a novel Tucker Decomposition based Dataset Distillation method within a meta-learning framework, designed for sequential recommendation. TD3 distills a fully expressive synthetic sequence summary from original data. To efficiently reduce computational complexity and extract refined latent patterns, Tucker decomposition decouples the summary into four factors: synthetic user latent factor, temporal dynamics latent factor, shared item latent factor, and a relation core that models their interconnections. Additionally, a surrogate objective in bi-level optimization is proposed to align feature spaces extracted from models trained on both original data and synthetic sequence summary beyond the naive performance matching approach. In the inner-loop, an augmentation technique allows the learner to closely fit the synthetic summary, ensuring an accurate update of it in the outer-loop. To accelerate the optimization process and address long dependencies, RaT-BPTT is employed for bi-level optimization. Experiments and analyses on multiple public datasets have confirmed the superiority and cross-architecture generalizability of the proposed designs. Codes are released at https://github.com/USTC-StarTeam/TD3.

As the demand for more personalized recommendation grows and a dramatic boom in commercial scenarios arises, the study on multi-scenario recommendation (MSR) has attracted much attention, which uses the data from all scenarios to simultaneously improve their recommendation performance. However, existing methods tend to integrate insufficient scenario knowledge and neglect learning personalized cross-scenario preferences, thus leading to sub-optimal performance. Meanwhile, though large language model (LLM) has shown great capability of reasoning and capturing semantic information, the high inference latency and high computation cost of tuning hinder its implementation in industrial recommender systems. To fill these gaps, we propose an LLM-enhanced paradigm LLM4MSR in this work. Specifically, we first leverage LLM to uncover multi-level knowledge from the designed scenario- and user-level prompt without fine-tuning the LLM, then adopt hierarchical meta networks to generate multi-level meta layers to explicitly improve the scenario-aware and personalized recommendation capability. Our experiments on KuaiSAR-small, KuaiSAR, and Amazon datasets validate significant advantages of LLM4MSR: (i) the effectiveness and compatibility with different multi-scenario backbone models, (ii) high efficiency and deployability on industrial recommender systems, and (iii) improved interpretability. The implemented code and data is available to ease reproduction.

Model editing aims to precisely alter the behaviors of large language models (LLMs) in relation to specific knowledge, while leaving unrelated knowledge intact. This approach has proven effective in addressing issues of hallucination and outdated information in LLMs. However, the potential of using model editing to modify knowledge in the medical field remains largely unexplored, even though resolving hallucination is a pressing need in this area. Our observations indicate that current methods face significant challenges in dealing with specialized and complex knowledge in medical domain. Therefore, we propose MedLaSA, a novel Layer-wise Scalable Adapter strategy for medical model editing. MedLaSA harnesses the strengths of both adding extra parameters and locate-then-edit methods for medical model editing. We utilize causal tracing to identify the association of knowledge in neurons across different layers, and generate a corresponding scale set from the association value for each piece of knowledge. Subsequently, we incorporate scalable adapters into the dense layers of LLMs. These adapters are assigned scaling values based on the corresponding specific knowledge, which allows for the adjustment of the adapter's weight and rank. The more similar the content, the more consistent the scale between them. This ensures precise editing of semantically identical knowledge while avoiding impact on unrelated knowledge. To evaluate the editing impact on the behaviours of LLMs, we propose two model editing studies for medical domain: (1) editing factual knowledge for medical specialization and (2) editing the explanatory ability for complex knowledge. We build two novel medical benchmarking datasets and introduce a series of challenging and comprehensive metrics. Extensive experiments on medical LLMs demonstrate the editing efficiency of MedLaSA, without affecting unrelated knowledge.

Achieving carbon neutrality within industrial operations has become increasingly imperative for sustainable development. It is both a significant challenge and a key opportunity for operational optimization in industry 4.0. In recent years, Deep Reinforcement Learning (DRL) based methods offer promising enhancements for sequential optimization processes and can be used for reducing carbon emissions. However, existing DRL methods need a pre-defined reward function to assess the impact of each action on the final sustainable development goals (SDG). In many real applications, such a reward function cannot be given in advance. To address the problem, this study proposes a Performance based Adversarial Imitation Learning (PAIL) engine. It is a novel method to acquire optimal operational policies for carbon neutrality without any pre-defined action rewards. Specifically, PAIL employs a Transformer-based policy generator to encode historical information and predict following actions within a multi-dimensional space. The entire action sequence will be iteratively updated by an environmental simulator. Then PAIL uses a discriminator to minimize the discrepancy between generated sequences and real-world samples of high SDG. In parallel, a Q-learning framework based performance estimator is designed to estimate the impact of each action on SDG. Based on these estimations, PAIL refines generated policies with the rewards from both discriminator and performance estimator. PAIL is evaluated on multiple real-world application cases and datasets. The experiment results demonstrate the effectiveness of PAIL comparing to other state-of-the-art baselines. In addition, PAIL offers meaningful interpretability for the optimization in carbon neutrality.

It is always challenging task for students to select right universities. For students, graduate job placement is the most important component of university quality. However, existing university evaluation methods predominantly depend on either subjective criteria, such as the perceived quality of the learning environment and academic prestige, or on factors like faculty excellence, which may not provide a precise indication of graduate job placement. Indeed, there is still a lack of a data-driven approach to accurately measure university quality based on the employment situation of graduates. Moreover, the inherently unsupervised nature of university evaluation, compounded by the absence of a reasonable ground truth, necessitates the development of a reliable supervised methodology to precisely quantify university quality. Our basic assumption is that highly influential companies would attract graduates from high-ranking universities. To this end, in this paper, we formulate university evaluation problem into the graduate flow prediction problem, and propose an Influence based Graph Autoencoder (IGAE) method to learn the representation of universities based on the employment of their graduates. Specifically, we first build a talent transition graph based on the massive resume information. This graph reveals the flow of talent between institutions. Then, considering the asymmetric and heterogeneous properties of talent flow, an unidirectional aggregation process with a heterogeneous attention mechanism is designed to encode the nodes in the directed graph and preserve the influence terms at the same time. Afterwards, a novel dual self-attention module is exploited to capture the dynamic pattern of institutions to forecast future employment. Furthermore, we design an influence based decoder to predict the existence of talent flows and estimate the frequency of employment, which can be learnt in a joint learning framework. Finally, we conduct extensive experiments on a real-world dataset for performance evaluation. The experimental results clearly validate the effectiveness of our approach compared to the state-of-the-art baselines, and we provide a case study on university influence analysis.

Collaborative filtering (CF) from implicit datasets has attracted much attention in recent years. The current mainstream pairwise methods optimize the Area Under the Curve (AUC) and are empirically proven to be helpful to exploit implicit feedback, but lead to not addressing the rank-biased scenarios where positive items are supposed to be placed on the top-k positions. Although there exist listwise methods, they have low efficiency and are not particularly adequate for general implicit feedback situations. To that end, in this paper, we propose a new framework, namely Collaborative List-and-Pairwise Filtering (CLAPF), which aims to introduce pairwise thinking into listwise methods. Specifically, we first smooth a well-known rank-biased measure called Mean Average Precision (MAP) as a low-bound version to make it can be optimized. After that, we combined the objective functions of optimizing the MAP with pairwise comparisons. The CLAPF framework is a new hybrid model that provides the idea of utilizing a listwise measure in a pairwise way on implicit feedback.

Click-Through Rate (CTR) prediction of intelligent marketing systems is of great importance, in which feature interaction selection plays a key role. Most approaches model interactions of features by the same pre-defined operation under expert guidance, among which improper interactions may bring unnecessary noise and complicate the training process. To that end, in this paper, we aim to adaptively evolve the model to select proper operations to interact on feature pairs under task guidance. Inspired by natural evolution, we propose a general Cognitive EvoLutionary Search (CELS) framework, where cognitive ability refers to the malleability of organisms to orientate to the environment. Specifically, we conceptualize interactions as genomes, models as organisms, and tasks as natural environments. Mirroring how genetic malleability develops environmental adaptability, we thus diagnose the fitness of models to simulate the survival rates of organisms for natural selection, thereby an evolution path can be planned and visualized, offering an intuitive interpretation of the mechanisms underlying interaction modeling and selection. Based on the CELS framework, we develop four instantiations including individual-based search and population-based search. We demonstrate how individual mutation and population crossover enable CELS to evolve into diverse models suitable for various tasks and data, providing ready-to-use models. Extensive experiments on real-world datasets demonstrate that CELS significantly outperforms state-of-the-art approaches.

Every organization has organizational networks for exchange of ideas and information. It is believed that organizational network analysis (ONA) can help the business be more effective. While considerable research efforts have been made for visualizing and analyzing relationships in organizational networks, it lacks a holistic way to model the complex social structures and rich semantic information of these networks. Indeed, employee behaviors can occur across different communication platforms, such as email and instant messaging systems, which naturally lead to the multiplex structure of organizational social networks. Meanwhile, it is also a challenge to model the impact of semantic information, such as employee attributes and organization charts, and the collaboration relationships of employees. To this end, in this paper, we propose a Multiplex Attentive Network Embedding (MANE) approach for modeling organizational social networks in a holistic way. Specifically, we first develop a multiple attributed random walk approach to jointly model multiple networks, with the integration of external work information. Then, we preserve the network structure by maximizing the probability of predicting the central node based on the surrounding context nodes. In particular, we introduce an attention mechanism to assign a weight to each context node in the training process, according to its attributed relation and structural relation with the central node by utilizing the k-core algorithm and the shortest path algorithm. In this way, the embedding results can be kept consistent with their structural relationships. Furthermore, to solve some department-level tasks, we introduce an attentive relational transition method to learn the representation of departments in the organizational networks. Finally, we evaluate the performance of MANE with extensive experiments on real-world data for three important talent management tasks, namely employee performance prediction, employee turnover prediction and department performance prediction. We also conduct a link prediction task to validate the effectiveness of employee embedding. Experimental results clearly show the effectiveness and interpretability of MANE for organizational network analysis.

The implicit feedback based collaborative filtering (CF) has attracted much attention in recent years, mainly because users implicitly express their preferences in many real-world scenarios. The current mainstream pairwise methods optimize the Area Under the Curve (AUC) and are empirically proved to be helpful to exploit binary relevance data, but lead to either not address the ranking problem, or not specifically focus on top-$k$recommendation. Although there exists the listwise method maximizes the Mean Reciprocal Rank (MRR), it has low efficiency and is not particularly adequate for general implicit feedback situations. To that end, in this paper, we propose a new framework, namelyCollaborative List-and-Pairwise Filtering (CLAPF), which aims to introduce pairwise thinking into listwise methods. Specifically, we smooth another well-known rank-biased measure called Mean Average Precision (MAP), and respectively combine two rank-biased metrics (MAP, MRR) with the pairwise objective function to capture the performance of top-$k$recommendation. Furthermore, the sampling scheme for CLAPF is discussed to accelerate the convergence speed. Our CLAPF framework is a new hybrid model that provides an idea of utilizing rank-biased measures in a pairwise way on implicit feedback. Empirical studies demonstrated CLAPF outperforms state-of-the-art approaches on real-world datasets.

How to identify high-potential talent (HIPO) earlier in their career always has strategic importance for human resource management. While tremendous efforts have been made in this direction, most existing approaches are still based on the subjective selection of human resource experts. This could lead to unintentional bias and inconsistencies. To this end, in this paper, we propose a neural network based dynamic social profiling approach for quantitatively identifying HIPOs from the newly-enrolled employees by modeling the dynamics of their behaviors in organizational social networks. A basic assumption is that HIPOs usually perform more actively and have higher competencies than their peers to accumulate their social capitals during their daily work practice. Along this line, we first propose to model the social profiles of employees with both Graph Convolutional Network (GCN) and social centrality analysis in a comprehensive way. Then, an adaptive Long Short Term Memory (LSTM) network with global attention mechanism is designed to capture the profile dynamics of employees in the organizational social networks during their early career. Finally, extensive experiments on real-world data clearly validate the effectiveness of our approach as well as the interpretability of our results.

As users implicitly express their preferences to items on many real-world applications, the implicit feedback based collaborative filtering has attracted much attention in recent years. Pairwise methods have shown state-of-the-art solutions for dealing with the implicit feedback, with the assumption that users prefer the observed items to the unobserved items. However, for each user, the huge unobserved items are not equal to represent her preference. In this paper, we propose a Multiple Pairwise Ranking (MPR) approach, which relaxes the simple pairwise preference assumption in previous works by further tapping the connections among items with multiple pairwise ranking criteria. Specifically, we exploit the preference difference among multiple pairs of items by dividing the unobserved items into different parts. Empirical studies show that our algorithms outperform the state-of-the-art methods on real-world datasets.

The prediction of academic performance is one of the most important tasks in educational data mining, and has been widely studied in MOOCs and intelligent tutoring systems. Academic performance could be affected with factors like personality, skills, social environment, the use of library books and so on. However, it is still less investigated that how could the use of library books affect academic performance of college students and even leverage book-loan history for predicting academic performance. To this end, we propose a supervised content-aware matrix factorization for mutual reinforcement of academic performance prediction and library book recommendation. This model not only addresses the sparsity challenge by explainable dimension reduction techniques, but also promotes library book recommendation by recommending "right" books for students based on their performance levels and book meta information. Finally, we evaluate the proposed model on three years of the book-loan history and cumulative grade point average of 13,047 undergraduate students in one university. The results show that the proposed model outperforms the competing baselines on both tasks, and that academic performance is not only predictable from the book-loan history but also improves the recommendation of library books for students.