The core task of recommender systems is to learn user preferences from historical user-item interactions. With the rapid development of large language models (LLMs), recent research has explored leveraging the reasoning capabilities of LLMs to enhance rating prediction tasks. However, existing distillation-based methods suffer from limitations such as the teacher model's insufficient recommendation capability, costly and static supervision, and superficial transfer of reasoning ability. To address these issues, this paper proposes RecZero, a reinforcement learning (RL)-based recommendation paradigm that abandons the traditional multi-model and multi-stage distillation approach. Instead, RecZero trains a single LLM through pure RL to autonomously develop reasoning capabilities for rating prediction. RecZero consists of two key components: (1) "Think-before-Recommendation" prompt construction, which employs a structured reasoning template to guide the model in step-wise analysis of user interests, item features, and user-item compatibility; and (2) rule-based reward modeling, which adopts group relative policy optimization (GRPO) to compute rewards for reasoning trajectories and optimize the LLM. Additionally, the paper explores a hybrid paradigm, RecOne, which combines supervised fine-tuning with RL, initializing the model with cold-start reasoning samples and further optimizing it with RL. Experimental results demonstrate that RecZero and RecOne significantly outperform existing baseline methods on multiple benchmark datasets, validating the superiority of the RL paradigm in achieving autonomous reasoning-enhanced recommender systems.

Industrial recommender systems usually hold data from multiple business scenarios and are expected to provide recommendation services for these scenarios simultaneously. In the retrieval step, the topK high-quality items selected from a large number of corpus usually need to be various for multiple scenarios. Take Alibaba display advertising system for example, not only because the behavior patterns of Taobao users are diverse, but also differentiated scenarios' bid prices assigned by advertisers vary significantly. Traditional methods either train models for each scenario separately, ignoring the cross-domain overlapping of user groups and items, or simply mix all samples and maintain a shared model which makes it difficult to capture significant diversities between scenarios. In this paper, we present Adaptive Domain Interest Network(ADIN) that adaptively handles the commonalities and diversities across scenarios, making full use of multi-scenarios data during training. Then the proposed method is able to improve the performance of each business domain by giving various topK candidates for different scenarios during online inference. Specifically, our proposed ADIN models the commonalities and diversities for different domains by shared networks and domain-specific networks, respectively. In addition, we apply the domain-specific batch normalization and design the domain interest adaptation layer for feature-level domain adaptation. A self training strategy is also incorporated to capture label-level connections across domains.ADIN has been deployed in the display advertising system of Alibaba, and obtains 1.8% improvement on advertising revenue.

Retrieving relevant targets from an extremely large target set under computational limits is a common challenge for information retrieval and recommendation systems. Tree models, which formulate targets as leaves of a tree with trainable node-wise scorers, have attracted a lot of interests in tackling this challenge due to their logarithmic computational complexity in both training and testing. Tree-based deep models (TDMs) and probabilistic label trees (PLTs) are two representative kinds of them. Though achieving many practical successes, existing tree models suffer from the training-testing discrepancy, where the retrieval performance deterioration caused by beam search in testing is not considered in training. This leads to an intrinsic gap between the most relevant targets and those retrieved by beam search with even the optimally trained node-wise scorers. We take a first step towards understanding and analyzing this problem theoretically, and develop the concept of Bayes optimality under beam search and calibration under beam search as general analyzing tools for this purpose. Moreover, to eliminate the discrepancy, we propose a novel algorithm for learning optimal tree models under beam search. Experiments on both synthetic and real data verify the rationality of our theoretical analysis and demonstrate the superiority of our algorithm compared to state-of-the-art methods.

Large-scale industrial recommender systems are usually confronted with computational problems due to the enormous corpus size. To retrieve and recommend the most relevant items to users under response time limits, resorting to an efficient index structure is an effective and practical solution. The previous work Tree-based Deep Model (TDM) \cite{zhu2018learning} greatly improves recommendation accuracy using tree index. By indexing items in a tree hierarchy and training a user-node preference prediction model satisfying a max-heap like property in the tree, TDM provides logarithmic computational complexity w.r.t. the corpus size, enabling the use of arbitrary advanced models in candidate retrieval and recommendation. In tree-based recommendation methods, the quality of both the tree index and the user-node preference prediction model determines the recommendation accuracy for the most part. We argue that the learning of tree index and preference model has interdependence. Our purpose, in this paper, is to develop a method to jointly learn the index structure and user preference prediction model. In our proposed joint optimization framework, the learning of index and user preference prediction model are carried out under a unified performance measure. Besides, we come up with a novel hierarchical user preference representation utilizing the tree index hierarchy. Experimental evaluations with two large-scale real-world datasets show that the proposed method improves recommendation accuracy significantly. Online A/B test results at a display advertising platform also demonstrate the effectiveness of the proposed method in production environments.

Predicting future frames in videos remains an unsolved but challenging problem. Mainstream recurrent models suffer from huge memory usage and computation cost, while convolutional models are unable to effectively capture the temporal dependencies between consecutive video frames. To tackle this problem, we introduce an entirely CNN-based architecture, PredCNN, that models the dependencies between the next frame and the sequential video inputs. Inspired by the core idea of recurrent models that previous states have more transition operations than future states, we design a cascade multiplicative unit (CMU) that provides relatively more operations for previous video frames. This newly proposed unit enables PredCNN to predict future spatiotemporal data without any recurrent chain structures, which eases gradient propagation and enables a fully paralleled optimization. We show that PredCNN outperforms the state-of-the-art recurrent models for video prediction on the standard Moving MNIST dataset and two challenging crowd flow prediction datasets, and achieves a faster training speed and lower memory footprint.