SCIRGC: Multi-Granularity Citation Recommendation and Citation Sentence Preference Alignment

Citations are crucial in scientific research articles as they highlight the connection between the current study and prior work. However, this process is often time-consuming for researchers. In this study, we propose the SciRGC framework, which aims to automatically recommend citation articles and generate citation sentences for citation locations within articles. The framework addresses two key challenges in academic citation generation: 1) how to accurately identify the author's citation intent and find relevant citation papers, and 2) how to generate high-quality citation sentences that align with human preferences. We enhance citation recommendation accuracy in the citation article recommendation module by incorporating citation networks and sentiment intent, and generate reasoning-based citation sentences in the citation sentence generation module by using the original article abstract, local context, citation intent, and recommended articles as inputs. Additionally, we propose a new evaluation metric to fairly assess the quality of generated citation sentences. Through comparisons with baseline models and ablation experiments, the SciRGC framework not only improves the accuracy and relevance of citation recommendations but also ensures the appropriateness of the generated citation sentences in context, providing a valuable tool for interdisciplinary researchers.

Catoni-Style Change Point Detection for Regret Minimization in Non-Stationary Heavy-Tailed Bandits

Regret minimization in stochastic non-stationary bandits gained popularity over the last decade, as it can model a broad class of real-world problems, from advertising to recommendation systems. Existing literature relies on various assumptions about the reward-generating process, such as Bernoulli or subgaussian rewards. However, in settings such as finance and telecommunications, heavy-tailed distributions naturally arise. In this work, we tackle the heavy-tailed piecewise-stationary bandit problem. Heavy-tailed bandits, introduced by Bubeck et al., 2013, operate on the minimal assumption that the finite absolute centered moments of maximum order $1+\epsilon$ are uniformly bounded by a constant $v<+\infty$, for some $\epsilon \in (0,1]$. We focus on the most popular non-stationary bandit setting, i.e., the piecewise-stationary setting, in which the mean of reward-generating distributions may change at unknown time steps. We provide a novel Catoni-style change-point detection strategy tailored for heavy-tailed distributions that relies on recent advancements in the theory of sequential estimation, which is of independent interest. We introduce Robust-CPD-UCB, which combines this change-point detection strategy with optimistic algorithms for bandits, providing its regret upper bound and an impossibility result on the minimum attainable regret for any policy. Finally, we validate our approach through numerical experiments on synthetic and real-world datasets.

Adaptive Location Hierarchy Learning for Long-Tailed Mobility Prediction

Human mobility prediction is crucial for applications ranging from location-based recommendations to urban planning, which aims to forecast users' next location visits based on historical trajectories. Despite the severe long-tailed distribution of locations, the problem of long-tailed mobility prediction remains largely underexplored. Existing long-tailed learning methods primarily focus on rebalancing the skewed distribution at the data, model, or class level, neglecting to exploit the spatiotemporal semantics of locations. To address this gap, we propose the first plug-and-play framework for long-tailed mobility prediction in an exploitation and exploration manner, named \textbf{A}daptive \textbf{LO}cation \textbf{H}ier\textbf{A}rchy learning (ALOHA). First, we construct city-tailored location hierarchy based on Large Language Models (LLMs) by exploiting Maslow's theory of human motivation to design Chain-of-Thought (CoT) prompts that captures spatiotemporal semantics. Second, we optimize the location hierarchy predictions by Gumbel disturbance and node-wise adaptive weights within the hierarchical tree structure. Experiments on state-of-the-art models across six datasets demonstrate the framework's consistent effectiveness and generalizability, which strikes a well balance between head and tail locations. Weight analysis and ablation studies reveal the optimization differences of each component for head and tail locations. Furthermore, in-depth analyses of hierarchical distance and case study demonstrate the effective semantic guidance from the location hierarchy. Our code will be made publicly available.

Light distillation for Incremental Graph Convolution Collaborative Filtering

Recommender systems presently utilize vast amounts of data and play a pivotal role in enhancing user experiences. Graph Convolution Networks (GCNs) have surfaced as highly efficient models within the realm of recommender systems due to their ability to capture extensive relational information. The continuously expanding volume of data may render the training of GCNs excessively costly. To tackle this problem, incrementally training GCNs as new data blocks come in has become a vital research direction. Knowledge distillation techniques have been explored as a general paradigm to train GCNs incrementally and alleviate the catastrophic forgetting problem that typically occurs in incremental settings. However, we argue that current methods based on knowledge distillation introduce additional parameters and have a high model complexity, which results in unrealistic training time consumption in an incremental setting and thus difficult to actually deploy in the real world. In this work, we propose a light preference-driven distillation method to distill the preference score of a user for an item directly from historical interactions, which reduces the training time consumption in the incremental setting significantly without noticeable loss in performance. The experimental result on two general datasets shows that the proposed method can save training time from 1.5x to 9.5x compared to the existing methods and improves Recall@20 by 5.41% and 10.64% from the fine-tune method.

MedDreamer: Model-Based Reinforcement Learning with Latent Imagination on Complex EHRs for Clinical Decision Support

Timely and personalized treatment decisions are essential across a wide range of healthcare settings where patient responses vary significantly and evolve over time. Clinical data used to support these decisions are often irregularly sampled, sparse, and noisy. Existing decision support systems commonly rely on discretization and imputation, which can distort critical temporal dynamics and degrade decision quality. Moreover, they often overlook the clinical significance of irregular recording frequencies, filtering out patterns in how and when data is collected. Reinforcement Learning (RL) is a natural fit for clinical decision-making, enabling sequential, long-term optimization in dynamic, uncertain environments. However, most existing treatment recommendation systems are model-free and trained solely on offline data, making them sample-inefficient, sensitive to data quality, and poorly generalizable across tasks or cohorts. To address these limitations, we propose MedDreamer, a two-phase model-based RL framework for personalized treatment recommendation. MedDreamer uses a world model with an Adaptive Feature Integration (AFI) module to effectively model irregular, sparse clinical data. Through latent imagination, it simulates plausible patient trajectories to enhance learning, refining its policy using a mix of real and imagined experiences. This enables learning policies that go beyond suboptimal historical decisions while remaining grounded in clinical data. To our knowledge, this is the first application of latent imagination to irregular healthcare data. Evaluations on sepsis and mechanical ventilation (MV) treatment using two large-scale EHR datasets show that MedDreamer outperforms both model-free and model-based baselines in clinical outcomes and off-policy metrics.

DoctorAgent-RL: A Multi-Agent Collaborative Reinforcement Learning System for Multi-Turn Clinical Dialogue

Large language models (LLMs) have demonstrated excellent capabilities in the field of biomedical question answering, but their application in real-world clinical consultations still faces core challenges. Existing systems rely on a one-way information transmission mode where patients must fully describe their symptoms in a single round, leading to nonspecific diagnostic recommendations when complaints are vague. Traditional multi-turn dialogue methods based on supervised learning are constrained by static data-driven paradigms, lacking generalizability and struggling to intelligently extract key clinical information. To address these limitations, we propose DoctorAgent-RL, a reinforcement learning (RL)-based multi-agent collaborative framework that models medical consultations as a dynamic decision-making process under uncertainty. The doctor agent continuously optimizes its questioning strategy within the RL framework through multi-turn interactions with the patient agent, dynamically adjusting its information-gathering path based on comprehensive rewards from the Consultation Evaluator. This RL fine-tuning mechanism enables LLMs to autonomously develop interaction strategies aligned with clinical reasoning logic, rather than superficially imitating patterns in existing dialogue data. Notably, we constructed MTMedDialog, the first English multi-turn medical consultation dataset capable of simulating patient interactions. Experiments demonstrate that DoctorAgent-RL outperforms existing models in both multi-turn reasoning capability and final diagnostic performance, demonstrating practical value in assisting clinical consultations. https://github.com/JarvisUSTC/DoctorAgent-RL

AgentRecBench: Benchmarking LLM Agent-based Personalized Recommender Systems

The emergence of agentic recommender systems powered by Large Language Models (LLMs) represents a paradigm shift in personalized recommendations, leveraging LLMs' advanced reasoning and role-playing capabilities to enable autonomous, adaptive decision-making. Unlike traditional recommendation approaches, agentic recommender systems can dynamically gather and interpret user-item interactions from complex environments, generating robust recommendation strategies that generalize across diverse scenarios. However, the field currently lacks standardized evaluation protocols to systematically assess these methods. To address this critical gap, we propose: (1) an interactive textual recommendation simulator incorporating rich user and item metadata and three typical evaluation scenarios (classic, evolving-interest, and cold-start recommendation tasks); (2) a unified modular framework for developing and studying agentic recommender systems; and (3) the first comprehensive benchmark comparing 10 classical and agentic recommendation methods. Our findings demonstrate the superiority of agentic systems and establish actionable design guidelines for their core components. The benchmark environment has been rigorously validated through an open challenge and remains publicly available with a continuously maintained leaderboard~\footnote[2]{https://tsinghua-fib-lab.github.io/AgentSocietyChallenge/pages/overview.html}, fostering ongoing community engagement and reproducible research. The benchmark is available at: \hyperlink{https://huggingface.co/datasets/SGJQovo/AgentRecBench}{https://huggingface.co/datasets/SGJQovo/AgentRecBench}.

Think Again! The Effect of Test-Time Compute on Preferences, Opinions, and Beliefs of Large Language Models

As Large Language Models (LLMs) become deeply integrated into human life and increasingly influence decision-making, it's crucial to evaluate whether and to what extent they exhibit subjective preferences, opinions, and beliefs. These tendencies may stem from biases within the models, which may shape their behavior, influence the advice and recommendations they offer to users, and potentially reinforce certain viewpoints. This paper presents the Preference, Opinion, and Belief survey (POBs), a benchmark developed to assess LLMs' subjective inclinations across societal, cultural, ethical, and personal domains. We applied our benchmark to evaluate leading open- and closed-source LLMs, measuring desired properties such as reliability, neutrality, and consistency. In addition, we investigated the effect of increasing the test-time compute, through reasoning and self-reflection mechanisms, on those metrics. While effective in other tasks, our results show that these mechanisms offer only limited gains in our domain. Furthermore, we reveal that newer model versions are becoming less consistent and more biased toward specific viewpoints, highlighting a blind spot and a concerning trend. POBS: https://ibm.github.io/POBS

Unlocking the Power of Diffusion Models in Sequential Recommendation: A Simple and Effective Approach

In this paper, we focus on the often-overlooked issue of embedding collapse in existing diffusion-based sequential recommendation models and propose ADRec, an innovative framework designed to mitigate this problem. Diverging from previous diffusion-based methods, ADRec applies an independent noise process to each token and performs diffusion across the entire target sequence during training. ADRec captures token interdependency through auto-regression while modeling per-token distributions through token-level diffusion. This dual approach enables the model to effectively capture both sequence dynamics and item representations, overcoming the limitations of existing methods. To further mitigate embedding collapse, we propose a three-stage training strategy: (1) pre-training the embedding weights, (2) aligning these weights with the ADRec backbone, and (3) fine-tuning the model. During inference, ADRec applies the denoising process only to the last token, ensuring that the meaningful patterns in historical interactions are preserved. Our comprehensive empirical evaluation across six datasets underscores the effectiveness of ADRec in enhancing both the accuracy and efficiency of diffusion-based sequential recommendation systems.

Hierarchical Tree Search-based User Lifelong Behavior Modeling on Large Language Model

Large Language Models (LLMs) have garnered significant attention in Recommendation Systems (RS) due to their extensive world knowledge and robust reasoning capabilities. However, a critical challenge lies in enabling LLMs to effectively comprehend and extract insights from massive user behaviors. Current approaches that directly leverage LLMs for user interest learning face limitations in handling long sequential behaviors, effectively extracting interest, and applying interest in practical scenarios. To address these issues, we propose a Hierarchical Tree Search-based User Lifelong Behavior Modeling framework (HiT-LBM). HiT-LBM integrates Chunked User Behavior Extraction (CUBE) and Hierarchical Tree Search for Interest (HTS) to capture diverse interests and interest evolution of user. CUBE divides user lifelong behaviors into multiple chunks and learns the interest and interest evolution within each chunk in a cascading manner. HTS generates candidate interests through hierarchical expansion and searches for the optimal interest with process rating model to ensure information gain for each behavior chunk. Additionally, we design Temporal-Ware Interest Fusion (TIF) to integrate interests from multiple behavior chunks, constructing a comprehensive representation of user lifelong interests. The representation can be embedded into any recommendation model to enhance performance. Extensive experiments demonstrate the effectiveness of our approach, showing that it surpasses state-of-the-art methods.