When you purchase through links in our articles, we may earn a small commission. From Amazon's Echo Look to the Nest Secure security system, these doomed smart home products were destined for the dumpster. Imagine if that refrigerator you bought just five years ago suddenly up and died--and not because of some technical glitch, but because the manufacturer deliberately reached out and deactivated it, permanently. And you'd probably want a refund, too. As wild as that scenario sounds for a major appliance like a refrigerator or a TV, it happens more often than you'd think in the smart home world.

In an era where tool-augmented AI agents are becoming increasingly vital, our findings highlight the ability of Group Relative Policy Optimization (GRPO) to empower SLMs, which are traditionally constrained in tool use. The ability to use tools effectively has become a defining feature of Large Language Models (LLMs), allowing them to access external data and internal resources. As AI agents grow more sophisticated, tool-use capabilities have become indispensable. While LLMs have made significant progress in this area, Small Language Models (SLMs) still face challenges in accurately integrating tool use, especially in resource-constrained settings. This study investigates how Reinforcement Learning, specifically Group Relative Policy Optimization (GRPO), can enhance the tool-use accuracy of SLMs. By designing a well-defined reward system that reinforces structured JSON output, correct tool selection, and precise parameter usage, we demonstrate that GRPO enables SLMs to achieve significant improvements in tool-use capabilities (function calling/JSON output). Our approach provides a computationally efficient training method that enhances SLMs practical deployment in real-world AI applications.

We introduce a new convolutional AutoEncoder architecture for user modelling and recommendation tasks with several improvements over the state of the art. Firstly, our model has the flexibility to learn a set of associations and combinations between different interaction types in a way that carries over to each user and item. Secondly, our model is able to learn jointly from both the explicit ratings and the implicit information in the sampling pattern (which we refer to as `implicit feedback'). It can also make separate predictions for the probability of consuming content and the likelihood of granting it a high rating if observed. This not only allows the model to make predictions for both the implicit and explicit feedback, but also increases the informativeness of the predictions: in particular, our model can identify items which users would not have been likely to consume naturally, but would be likely to enjoy if exposed to them. Finally, we provide several generalization bounds for our model, which to the best of our knowledge, are among the first generalization bounds for auto-encoders in a Recommender Systems setting; we also show that optimizing our loss function guarantees the recovery of the exact sampling distribution over interactions up to a small error in total variation. In experiments on several real-life datasets, we achieve state-of-the-art performance on both the implicit and explicit feedback prediction tasks despite relying on a single model for both, and benefiting from additional interpretability in the form of individual predictions for the probabilities of each possible rating.

Recommender systems are widely used across a broad range of applications, with recommendation algorithms serving as their core. Among the myriad of algorithmic paradigms, recommendation models based on deep neural networks (commonly referred to as Neural Collaborative Filtering, or NCF [1]) have garnered significant traction within the industry due to their implementation simplicity and high efficiency in delivering effective results [1-8]. Traditionally, these recommendation algorithms follow the conventional deep learning paradigm, where models are trained on fixed datasets and then applied to unseen data under the assumption of a static data distribution. However, in many real-world applications, such as music streaming [9], news recommendation [10], Point-Of-Interest (POI) recommendation [11], movie recommendation [12], and e-commerce platforms [13], recommender systems operate in dynamic environments where user interaction data stream is continuously generated [14-16], reflecting the evolving nature of users' preferences. This implies that incoming streaming data, which has not been observed during training, may differ significantly from the original training data in terms of distribution. As a result, models previously trained in static environments, when deployed under dynamic conditions for extended periods, often experience a decline in predictive performance [17].

Personalized AI systems, from recommendation systems to chatbots, are a prevalent method for distributing content to users based on their learned preferences. However, there is growing concern about the adverse effects of these systems, including their potential tendency to expose users to sensitive or harmful material, negatively impacting overall well-being. To address this concern quantitatively, it is necessary to create datasets with relevant sensitivity labels for content, enabling researchers to evaluate personalized systems beyond mere engagement metrics. To this end, we introduce two novel datasets that include a taxonomy of sensitivity labels alongside user-content ratings: one that integrates MovieLens rating data with content warnings from the Does the Dog Die? community ratings website, and another that combines fan-fiction interaction data and user-generated warnings from Archive of Our Own.

We present a lightweight neuro-symbolic framework to mitigate over-personalization in LLM-based recommender systems by adapting user-side Knowledge Graphs (KGs) at inference time. Instead of retraining models or relying on opaque heuristics, our method restructures a user's Personalized Knowledge Graph (PKG) to suppress feature co-occurrence patterns that reinforce Personalized Information Environments (PIEs), i.e., algorithmically induced filter bubbles that constrain content diversity. These adapted PKGs are used to construct structured prompts that steer the language model toward more diverse, Out-PIE recommendations while preserving topical relevance. We introduce a family of symbolic adaptation strategies, including soft reweighting, hard inversion, and targeted removal of biased triples, and a client-side learning algorithm that optimizes their application per user. Experiments on a recipe recommendation benchmark show that personalized PKG adaptations significantly increase content novelty while maintaining recommendation quality, outperforming global adaptation and naive prompt-based methods.

Rockim Prowell, 34, faces murder charges for allegedly killing two men and attempting to murder another after meeting victims through an online dating app in California.

Is AI the New Frontier of Women's Oppression? In her new book, feminist author Laura Bates explores how sexbots, AI assistants, and deepfakes are reinventing misogyny and harming women. After spending her early twenties as a nanny in the UK, Laura Bates noticed that the young girls she was caring for were preoccupied by their bodies, spurred on by the marketing they were receiving. In 2012, Bates, a London-based feminist author and activist, started The Everyday Sexism Project, a website dedicated to documenting and combatting sexism, misogyny, and gendered violence around the world by highlighting insidious instances of it such as invisible labor, referring to women as girls and commenting on their attire in professional settings. The site was turned into a book in 2014.

Things to Do in L.A. Tap to enable a layout that focuses on the article. Online dating murder suspect lured men into brutal robberies, L.A. County prosecutors allege Rockim Prowell allegedly met his victims online. Above, a person uses a cellphone. Rockim Prowell, 44, fis accused of murder, attempted murder, carjacking and burglary. Prosecutors allege Prowell lured robbery victims using a dating site.

Spotify's Home page features a variety of content types, including music, podcasts, and audiobooks. However, historical data is heavily skewed toward music, making it challenging to deliver a balanced and personalized content mix. Moreover, users' preference towards different content types may vary depending on the time of day, the day of week, or even the device they use. We propose a calibration method that leverages contextual bandits to dynamically learn each user's optimal content type distribution based on their context and preferences. Unlike traditional calibration methods that rely on historical averages, our approach boosts engagement by adapting to how users interests in different content types varies across contexts. Both offline and online results demonstrate improved precision and user engagement with the Spotify Home page, in particular with under-represented content types such as podcasts.