In 2025, it will be commonplace to talk with a personal AI agent that knows your schedule, your circle of friends, the places you go. This will be sold as a convenience equivalent to having a personal, unpaid assistant. These anthropomorphic agents are designed to support and charm us so that we fold them into every part of our lives, giving them deep access to our thoughts and actions. With voice-enabled interaction, that intimacy will feel even closer. This story is from the WIRED World in 2025, our annual trends briefing.

Document similarity assessment plays an important role in various natural language processing (NLP) applications, such as information retrieval, plagiarism detection, recommendation systems, and question answering [11, 19]. For instance, in recommendation systems, document similarity helps personalise suggestions by finding content that closely matches user preference. These tasks rely on accurate measurements of how similar documents are in terms of their structure, content, and meaning, which depends on the way the document is represented computationally. This representation is usually done in vector format and is obtained via document embedding methods. V arious methodologies can be employed to obtain document-level embeddings, and the choice of method directly impacts the accuracy and usefulness of the similarity scores calculated [14, 19].

The item cold-start problem is crucial for online recommender systems, as the success of the cold-start phase determines whether items can transition into popular ones. Prompt learning, a powerful technique used in natural language processing (NLP) to address zero- or few-shot problems, has been adapted for recommender systems to tackle similar challenges. However, existing methods typically rely on content-based properties or text descriptions for prompting, which we argue may be suboptimal for cold-start recommendations due to 1) semantic gaps with recommender tasks, 2) model bias caused by warm-up items contribute most of the positive feedback to the model, which is the core of the cold-start problem that hinders the recommender quality on cold-start items. We propose to leverage high-value positive feedback, termed pinnacle feedback as prompt information, to simultaneously resolve the above two problems. We experimentally prove that compared to the content description proposed in existing works, the positive feedback is more suitable to serve as prompt information by bridging the semantic gaps. Besides, we propose item-wise personalized prompt networks to encode pinnaclce feedback to relieve the model bias by the positive feedback dominance problem. Extensive experiments on four real-world datasets demonstrate the superiority of our model over state-of-the-art methods. Moreover, PROMO has been successfully deployed on a popular short-video sharing platform, a billion-user scale commercial short-video application, achieving remarkable performance gains across various commercial metrics within cold-start scenarios

Bundle recommendation aims to suggest a set of interconnected items to users. However, diverse interaction types and sparse interaction matrices often pose challenges for previous approaches in accurately predicting user-bundle adoptions. Inspired by the distant supervision strategy and generative paradigm, we propose BRIDGE, a novel framework for bundle recommendation. It consists of two main components namely the correlation-based item clustering and the pseudo bundle generation modules. Inspired by the distant supervision approach, the former is to generate more auxiliary information, e.g., instructive item clusters, for training without using external data. This information is subsequently aggregated with collaborative signals from user historical interactions to create pseudo `ideal' bundles. This capability allows BRIDGE to explore all aspects of bundles, rather than being limited to existing real-world bundles. It effectively bridging the gap between user imagination and predefined bundles, hence improving the bundle recommendation performance. Experimental results validate the superiority of our models over state-of-the-art ranking-based methods across five benchmark datasets.

In fact, according background in automated recommendations of personalized to a recent meta-survey (Leme et al. 2021), almost meals and then discuss our problem formulation, key solution 40% of the population across high and low-and mediumincome components including data (recipe representation and countries do not adhere to their national food-based format conversion) and meal recommendation, and their dietary guidelines, often prioritizing convenience over nutrition evaluation. We then describe a prototype implementation of needs. Previous studies have shown that adhering the solution in the BEACON system along with the supported to a provided meal plan instead of a self-selected one reduces use cases and conclude with a discussion of practical the risk for adverse health conditions (Metz et al. considerations and avenues for future extensions.

Recommender systems create enormous value for businesses and their consumers. They increase revenue for businesses while improving the consumer experience by recommending relevant products amidst huge product base. Product bundling is an exciting development in the field of product recommendations. It aims at generating new bundles and recommending exciting and relevant bundles to their consumers. Unlike traditional recommender systems that recommend single items to consumers, product bundling aims at targeting a bundle, or a set of items, to the consumers. While bundle recommendation has attracted significant research interest recently, extant literature on bundle generation is scarce. Moreover, metrics to identify if a bundle is popular or not is not well studied. In this work, we aim to fulfill this gap by introducing new bundle popularity metrics based on sales, consumer experience and item diversity in a bundle. We use these metrics in the methodology proposed in this paper to generate new bundles for mobile games using content aware and context aware embeddings. We use opensource Steam Games dataset for our analysis. Our experiments indicate that we can generate new bundles that can outperform the existing bundles on the popularity metrics by 32% - 44%. Our experiments are computationally efficient and the proposed methodology is generic that can be extended to other bundling problems e.g. product bundling, music bundling.

Recent advances in embodied agents with multimodal perception and reasoning capabilities based on large vision-language models (LVLMs), excel in autonomously interacting either real or cyber worlds, helping people make intelligent decisions in complex environments. However, the current works are normally optimized by golden action trajectories or ideal task-oriented solutions toward a definitive goal. This paradigm considers limited user-oriented factors, which could be the reason for their performance reduction in a wide range of personal assistant applications. To address this, we propose Chain-of-User-Thought (COUT), a novel embodied reasoning paradigm that takes a chain of thought from basic action thinking to explicit and implicit personalized preference thought to incorporate personalized factors into autonomous agent learning. To target COUT, we introduce SmartAgent, an agent framework perceiving cyber environments and reasoning personalized requirements as 1) interacting with GUI to access an item pool, 2) generating users' explicit requirements implied by previous actions, and 3) recommending items to fulfill users' implicit requirements. To demonstrate SmartAgent's capabilities, we also create a brand-new dataset SmartSpot that offers a full-stage personalized action-involved environment. To our best knowledge, our work is the first to formulate the COUT process, serving as a preliminary attempt towards embodied personalized agent learning. Our extensive experiments on SmartSpot illuminate SmartAgent's functionality among a series of embodied and personalized sub-tasks. We will release code and data upon paper notification at https://github.com/tsinghua-fib-lab/SmartAgent.

Recommender systems are widely used in various real-world applications, but they often encounter the persistent challenge of the user cold-start problem. Cross-domain recommendation (CDR), which leverages user interactions from one domain to improve prediction performance in another, has emerged as a promising solution. However, users with similar preferences in the source domain may exhibit different interests in the target domain. Therefore, directly transferring embeddings may introduce irrelevant source-domain collaborative information. In this paper, we propose a novel graph-based disentangled contrastive learning framework to capture fine-grained user intent and filter out irrelevant collaborative information, thereby avoiding negative transfer. Specifically, for each domain, we use a multi-channel graph encoder to capture diverse user intents. We then construct the affinity graph in the embedding space and perform multi-step random walks to capture high-order user similarity relationships. Treating one domain as the target, we propose a disentangled intent-wise contrastive learning approach, guided by user similarity, to refine the bridging of user intents across domains. Extensive experiments on four benchmark CDR datasets demonstrate that DisCo consistently outperforms existing state-of-the-art baselines, thereby validating the effectiveness of both DisCo and its components.

This study presents a data-driven analysis of COVID-19 discourse on YouTube, examining the sentiment, toxicity, and thematic patterns of video content published between January 2023 and October 2024. The analysis involved applying advanced natural language processing (NLP) techniques: sentiment analysis with VADER, toxicity detection with Detoxify, and topic modeling using Latent Dirichlet Allocation (LDA). The sentiment analysis revealed that 49.32% of video descriptions were positive, 36.63% were neutral, and 14.05% were negative, indicating a generally informative and supportive tone in pandemic-related content. Toxicity analysis identified only 0.91% of content as toxic, suggesting minimal exposure to toxic content. Topic modeling revealed two main themes, with 66.74% of the videos covering general health information and pandemic-related impacts and 33.26% focused on news and real-time updates, highlighting the dual informational role of YouTube. A recommendation system was also developed using TF-IDF vectorization and cosine similarity, refined by sentiment, toxicity, and topic filters to ensure relevant and context-aligned video recommendations. This system achieved 69% aggregate coverage, with monthly coverage rates consistently above 85%, demonstrating robust performance and adaptability over time. Evaluation across recommendation sizes showed coverage reaching 69% for five video recommendations and 79% for ten video recommendations per video. In summary, this work presents a framework for understanding COVID-19 discourse on YouTube and a recommendation system that supports user engagement while promoting responsible and relevant content related to COVID-19.

Generative recommendation systems, driven by large language models (LLMs), present an innovative approach to predicting user preferences by modeling items as token sequences and generating recommendations in a generative manner. A critical challenge in this approach is the effective tokenization of items, ensuring that they are represented in a form compatible with LLMs. Current item tokenization methods include using text descriptions, numerical strings, or sequences of discrete tokens. While text-based representations integrate seamlessly with LLM tokenization, they are often too lengthy, leading to inefficiencies and complicating accurate generation. Numerical strings, while concise, lack semantic depth and fail to capture meaningful item relationships. Tokenizing items as sequences of newly defined tokens has gained traction, but it often requires external models or algorithms for token assignment. These external processes may not align with the LLM's internal pretrained tokenization schema, leading to inconsistencies and reduced model performance. To address these limitations, we propose a self-improving item tokenization method that allows the LLM to refine its own item tokenizations during training process. Our approach starts with item tokenizations generated by any external model and periodically adjusts these tokenizations based on the LLM's learned patterns. Such alignment process ensures consistency between the tokenization and the LLM's internal understanding of the items, leading to more accurate recommendations. Furthermore, our method is simple to implement and can be integrated as a plug-and-play enhancement into existing generative recommendation systems. Experimental results on multiple datasets and using various initial tokenization strategies demonstrate the effectiveness of our method, with an average improvement of 8\% in recommendation performance.