Large Language Model (LLM) agents trained with reinforcement learning (RL) show great promise for solving complex, multi-step tasks. However, their performance is often crippled by ''Context Explosion'', where the accumulation of long text outputs overwhelms the model's context window and leads to reasoning failures. To address this, we introduce CoDA, a Context-Decoupled hierarchical Agent, a simple but effective reinforcement learning framework that decouples high-level planning from low-level execution. It employs a single, shared LLM backbone that learns to operate in two distinct, contextually isolated roles: a high-level Planner that decomposes tasks within a concise strategic context, and a low-level Executor that handles tool interactions in an ephemeral, isolated workspace. We train this unified agent end-to-end using PECO (Planner-Executor Co-Optimization), a reinforcement learning methodology that applies a trajectory-level reward to jointly optimize both roles, fostering seamless collaboration through context-dependent policy updates. Extensive experiments demonstrate that CoDA achieves significant performance improvements over state-of-the-art baselines on complex multi-hop question-answering benchmarks, and it exhibits strong robustness in long-context scenarios, maintaining stable performance while all other baselines suffer severe degradation, thus further validating the effectiveness of our hierarchical design in mitigating context overload. Our code is available at https://github.com/liuxuanzhang718/CoDA.

Traditional conversion rate prediction models suffer from suboptimal performance due to sharing the same network parameters for all instances, failing to capture heterogeneous underlying distributions across instances. Recent parameter personalized network based models address this by grouping instances and adjust parameters for each group. However, existing parameter personalization methods face challenges: (1) taking prior information features as grouping condition for model parameter personalization leads to suboptimal performance due to human's limited understanding of data distribution, or (2) using all the features for both parameter generation module and deep neural network (DNN) of conversion prediction tasks causes gradient conflicts during backpropagation. A better approach is to automatically select features as grouping condition based on data distribution through iterative learning. Therefore, we propose Automatic Feature Partitioning-Based Parameter Personalized Network (APPNet), which consists of two components: Automatic Feature Partitioning (AFP) and Parameter Personalized Network (PPNet). The AFP module automatically partitions all the features into two parts: one part for DNN of conversion prediction tasks, and the other part for PPNet module to generate weights to adjust DNN parameters of conversion prediction tasks. Specifically, we implemented two versions of AFP: feature-wise AFP and bit-wise AFP. The feature-wise AFP partitions features at the feature field granularity, while the bit-wise AFP partitions each bit of the feature embeddings. The PPNet module adjusts model parameters of conversion prediction task for each group of instances by applying element-wise multiplication to the DNN parameters of conversion tasks. Extensive offline experiments demonstrate APPNet outperforms previous parameter personalized models. Furthermore, online A/B testing in production system achieved a 1.09% improvement on conversion rate, validating its practical effectiveness.

Personalized product search provides significant benefits to e-commerce platforms by extracting more accurate user preferences from historical behaviors. Previous studies largely focused on the user factors when personalizing the search query, while ignoring the item perspective, which leads to the following two challenges that we summarize in this paper: First, previous approaches relying only on co-occurrence frequency tend to overestimate the conversion rates for popular items and underestimate those for long-tail items, resulting in inaccurate item similarities; Second, user purchasing propensity is highly heterogeneous according to the popularity of the target item: it is less correlated with the user's historical behavior for a popular item and more correlated for a long-tail item. To address these challenges, in this paper we propose NAM, a Normalization Attention Model, which optimizes ''when to personalize'' by utilizing Inverse Item Frequency (IIF) and employing a gating mechanism, as well as optimizes ''how to personalize'' by normalizing the attention mechanism from a global perspective. Through comprehensive experiments, we demonstrate that our proposed NAM model significantly outperforms state-of-the-art baseline models. Furthermore, we conducted an online A/B test at Fliggy, and obtained a significant improvement of 0.8% over the latest production system in conversion rate.

Static user and item features constitute important information to be taken into account in the recommendation process. However, as these features are usually sparse and of large-vocabulary, existing deep learning-based methods typically construct large tables of high-dimensional feature embeddings, which is inefficient in terms of memory storage and is computationally problematic. On the other hand, while product quantization-based methods have been proposed to compress latent embeddings, they usually come at the cost of compromising recommendation performance due to the restrictive expressive power, as feature correlations and user-item interactions are not properly captured in the compression process. To address these issues, we propose a novel Dual Contrastive Learning method to generate low-dimensional discrete static feature representations that significantly reduce memory storage and computational complexity, while simultaneously producing superior recommendation performance. Extensive offline experiments on three large-scale industrial datasets demonstrate that our proposed model significantly outperforms the selected baselines. In addition, we conducted an online A/B test at Alibaba and show that the proposed model significantly improves the average video streaming time, while reducing the size of the feature embedding table by 90% over the currently deployed system.

Cross domain recommender system constitutes a powerful method to tackle the cold-start and sparsity problem by aggregating and transferring user preferences across multiple category domains. Therefore, it has great potential to improve click-through-rate prediction performance in online commerce platforms having many domains of products. While several cross domain sequential recommendation models have been proposed to leverage information from a source domain to improve CTR predictions in a target domain, they did not take into account bidirectional latent relations of user preferences across source-target domain pairs. As such, they cannot provide enhanced cross-domain CTR predictions for both domains simultaneously. In this paper, we propose a novel approach to cross-domain sequential recommendations based on the dual learning mechanism that simultaneously transfers information between two related domains in an iterative manner until the learning process stabilizes. In particular, the proposed Dual Attentive Sequential Learning (DASL) model consists of two novel components Dual Embedding and Dual Attention, which jointly establish the two-stage learning process: we first construct dual latent embeddings that extract user preferences in both domains simultaneously, and subsequently provide cross-domain recommendations by matching the extracted latent embeddings with candidate items through dual-attention learning mechanism. We conduct extensive offline experiments on three real-world datasets to demonstrate the superiority of our proposed model, which significantly and consistently outperforms several state-of-the-art baselines across all experimental settings. We also conduct an online A/B test at a major video streaming platform Alibaba-Youku, where our proposed model significantly improves business performance over the latest production system in the company.

Classical recommender system methods typically face the filter bubble problem when users only receive recommendations of their familiar items, making them bored and dissatisfied. To address the filter bubble problem, unexpected recommendations have been proposed to recommend items significantly deviating from user’s prior expectations and thus surprising them by presenting ”fresh” and previously unexplored items to the users. In this paper, we describe a novel Personalized Unexpected Recommender System (PURS) model that incorporates unexpectedness into the recommendation process by providing multi-cluster modeling of user interests in the latent space and personalized unexpectedness via the self-attention mechanism and via selection of an appropriate unexpected activation function. Extensive offline experiments on three real-world datasets illustrate that the proposed PURS model significantly outperforms the state-of-the-art baseline approaches in terms of both accuracy and unexpectedness measures. In addition, we conduct an online A/B test at a major video platform Alibaba-Youku, where our model achieves over 3% increase in the average video view per user metric. The proposed model is in the process of being deployed by the company.