This study explores strategies for optimizing news headline recommendations through preference-based learning. Using real-world data of user interactions with French-language online news posts, we learn a headline recommender agent under a contextual bandit setting. This allows us to explore the impact of translation on engagement predictions, as well as the benefits of different interactive strategies on user engagement during data collection. Our results show that explicit exploration may not be required in the presence of noisy contexts, opening the door to simpler but efficient strategies in practice.

For personalized marketing, a new challenge of how to effectively algorithm the A/B testing to maximize user response is urgently to be overcome. In this paper, we present a new approach, the RL-LLM-AB test framework, for using reinforcement learning strategy optimization combined with LLM to automate and personalize A/B tests. The RL-LLM-AB test is built upon the pre-trained instruction-tuned language model. It first generates A/B versions of candidate content variants using a Prompt-Conditioned Generator, and then dynamically embeds and fuses the user portrait and the context of the current query with the multi-modal perception module to constitute the current interaction state. The content version is then selected in real-time through the policy optimization module with an Actor-Critic structure, and long-term revenue is estimated according to real-time feedback (such as click-through rate and conversion rate). Furthermore, a Memory-Augmented Reward Estimator is embedded into the framework to capture long-term user preference drift, which helps to generalize policy across multiple users and content contexts. Numerical results demonstrate the superiority of our proposed RL-LLM-ABTest over existing A/B testing methods, including classical A/B testing, Contextual Bandits, and benchmark reinforcement learning approaches on real-world marketing data.

If you've had a passing interest in Apple over the past year, you've likely heard of the company's struggles in the AI race. Apple Intelligence, which arrived slightly late after the launch of the iPhone 16, fell short of expectations, and Apple has yet to deliver the much-improved Siri it promised at WWDC 2024. Siri got a new look and an integration with ChatGPT, but its ability to understand your personal context via emails, messages, notes, and calendar was "indefinitely" delayed earlier this year as Apple is reportedly facing several challenges. Even if Apple delivered a better Siri, would people use it? Despite arriving first, Siri has long been derided by iPhone owners, often the butt of a joke, as Google Assistant and Alexa rose to the top.

With the rapid growth of fintech, personalized financial product recommendations have become increasingly important. Traditional methods like collaborative filtering or content-based models often fail to capture users' latent preferences and complex relationships. We propose a hybrid framework integrating large language models (LLMs) and graph neural networks (GNNs). A pre-trained LLM encodes text data (e.g., user reviews) into rich feature vectors, while a heterogeneous user-product graph models interactions and social ties. Through a tailored message-passing mechanism, text and graph information are fused within the GNN to jointly optimize embeddings. Experiments on public and real-world financial datasets show our model outperforms standalone LLM or GNN in accuracy, recall, and NDCG, with strong interpretability. This work offers new insights for personalized financial recommendations and cross-modal fusion in broader recommendation tasks.

Graph-based recommendation systems use higher-order user and item embeddings for next-item predictions. Dynamically adding collaborative signals from neighbors helps to use similar users' preferences during learning. While item-item correlations and their impact on recommendations have been studied, the efficacy of temporal item sequences for recommendations is much less explored. In this paper, we examine temporal item sequence (sequel-aware) embeddings along with higher-order user embeddings and show that sequel-aware Graph Neural Networks have better (or comparable) recommendation performance than graph-based recommendation systems that do not consider sequel information. Extensive empirical results comparing Heterogeneous Sequel-aware Graph Neural Networks (HSAL-GNNs) to other algorithms for sequential learning (such as transformers, graph neural networks, auto-encoders) are presented on three synthetic and three real-world datasets. Our results indicate that the incorporation of sequence information from items greatly enhances recommendations.

Recent calls for pluralistic alignment of Large Language Models (LLMs) encourage adapting models to diverse user preferences. However, most prior work on personalized reward models heavily rely on additional identity information, such as demographic details or a predefined set of preference categories. To this end, we introduce SynthesizeMe, an approach to inducing synthetic user personas from user interactions for personalized reward modeling. SynthesizeMe first generates and verifies reasoning to explain user preferences, then induces synthetic user personas from that reasoning, and finally filters to informative prior user interactions in order to build personalized prompts for a particular user. We show that using SynthesizeMe induced prompts improves personalized LLM-as-a-judge accuracy by 4.4% on Chatbot Arena. Combining SynthesizeMe derived prompts with a reward model achieves top performance on PersonalRewardBench: a new curation of user-stratified interactions with chatbots collected from 854 users of Chatbot Arena and PRISM.

Effective teamwork is essential across diverse domains. During the team formation stage, a key challenge is forming teams that effectively balance user preferences with task objectives to enhance overall team satisfaction. In the team performing stage, maintaining cohesion and engagement is critical for sustaining high team performance. However, existing computational tools and algorithms for team optimization often rely on static data inputs, narrow algorithmic objectives, or solutions tailored for specific contexts, failing to account for the dynamic interplay of team members personalities, evolving goals, and changing individual preferences. Therefore, teams may encounter member dissatisfaction, as purely algorithmic assignments can reduce members commitment to team goals or experience suboptimal engagement due to the absence of timely, personalized guidance to help members adjust their behaviors and interactions as team dynamics evolve. Ultimately, these challenges can lead to reduced overall team performance. My Ph.D. dissertation aims to develop AI-augmented team optimization frameworks and practical systems that enhance team satisfaction, engagement, and performance. First, I propose a team formation framework that leverages a multi-armed bandit algorithm to iteratively refine team composition based on user preferences, ensuring alignment between individual needs and collective team goals to enhance team satisfaction. Second, I introduce tAIfa (Team AI Feedback Assistant), an AI-powered system that utilizes large language models (LLMs) to deliver immediate, personalized feedback to both teams and individual members, enhancing cohesion and engagement. Finally, I present PuppeteerLLM, an LLM-based simulation framework that simulates multi-agent teams to model complex team dynamics within realistic environments, incorporating task-driven collaboration and long-term coordination.

Of all the egomaniacal lions who ruled Hollywood during the 20th century gatekeeper era, very few made a brilliant pivot to the internet. The exception is Barry Diller. After leading programming at ABC, running Paramount, and supercharging Fox by launching its broadcast network in the late 1980s, Diller no longer wanted to work for anyone else. Either you are or you aren't, he said of independence. As a free agent he quickly grasped the power of interactivity and built an empire that includes Expedia Group, almost the entire online dating sector (Tinder, Match, OkCupid), and an online media lineup that includes People, which wrote a hit piece on him early in his career titled "Failing Upwards."

Recommender systems are pivotal in delivering personalized experiences across industries, yet their adoption and scalability remain hindered by the need for extensive dataset- and task-specific configurations. Existing systems often require significant manual intervention, domain expertise, and engineering effort to adapt to new datasets or tasks, creating barriers to entry and limiting reusability. In contrast, recent advancements in large language models (LLMs) have demonstrated the transformative potential of reusable systems, where a single model can handle diverse tasks without significant reconfiguration. Inspired by this paradigm, we propose the Dataset- and Task-Independent Recommender System (DTIRS), a framework aimed at maximizing the reusability of recommender systems while minimizing barriers to entry. Unlike LLMs, which achieve task generalization directly, DTIRS focuses on eliminating the need to rebuild or reconfigure recommendation pipelines for every new dataset or task, even though models may still need retraining on new data. By leveraging the novel Dataset Description Language (DsDL), DTIRS enables standardized dataset descriptions and explicit task definitions, allowing autonomous feature engineering, model selection, and optimization. This paper introduces the concept of DTIRS and establishes a roadmap for transitioning from Level-1 automation (dataset-agnostic but task-specific systems) to Level-2 automation (fully dataset- and task-independent systems). Achieving this paradigm would maximize code reusability and lower barriers to adoption. We discuss key challenges, including the trade-offs between generalization and specialization, computational overhead, and scalability, while presenting DsDL as a foundational tool for this vision.

Nearest neighbor (NN) methods have re-emerged as competitive tools for matrix completion, offering strong empirical performance and recent theoretical guarantees, including entry-wise error bounds, confidence intervals, and minimax optimality. Despite their simplicity, recent work has shown that NN approaches are robust to a range of missingness patterns and effective across diverse applications. This paper introduces N$^2$, a unified Python package and testbed that consolidates a broad class of NN-based methods through a modular, extensible interface. Built for both researchers and practitioners, N$^2$ supports rapid experimentation and benchmarking. Using this framework, we introduce a new NN variant that achieves state-of-the-art results in several settings. We also release a benchmark suite of real-world datasets, from healthcare and recommender systems to causal inference and LLM evaluation, designed to stress-test matrix completion methods beyond synthetic scenarios. Our experiments demonstrate that while classical methods excel on idealized data, NN-based techniques consistently outperform them in real-world settings.