MetaStrategy: Generative Ranking with Executable LLM Strategies

Industrial recommender systems rank heterogeneous content under coupled user, business, commercial, and experience objectives. Existing generative ranking methods typically construct item sequences directly, making them difficult to integrate with mature predictive models, operational rules, and field-level guardrails. We present MetaStrategy, a framework that instead generates a structured, executable ranking strategy. Conditioned on request context, a large language model (LLM) policy emits a typed JSON bundle controlling objective weights, content and category preferences, experience constraints, and position policies. A deterministic validator and compiler instantiate an isolated Generator that competes atomically with incumbents under the list-level Evaluator of the Generator-Evaluator (GE) architecture. We train the policy in a production-path replay environment that re-executes logged requests through the current re-ranking stack without user exposure. The method combines selection, relative-rank, and baseline-lift rewards, a self-competitive curriculum that feeds frequent strategies back as competitors, and Evaluator-routed reward-augmented on-policy distillation that transfers complementary 4B-parameter Teachers into a compact 0.8B-parameter Student. We deploy MetaStrategy in Taobao Homepage Guess You Like through diff-triggered nearline generation; LLM inference remains outside synchronous ranking, with no observable increase in response time (RT). In a seven-day user-randomized online A/B test, MetaStrategy wins 27.93% of treatment-side GE calls and significantly improves click page views (click PV) by 2.11%, item-detail page views (IPV) by 3.12%, and transaction amount by 2.83%.

Interest Changes: Considering User Interest Life Cycle in Recommendation System

In recommendation systems, user interests are always in a state of constant flux. Typically, a user interest experiences a emergent phase, a stable phase, and a declining phase, which are referred to as the "user interest life-cycle". Recent papers on user interest modeling have primarily focused on how to compute the correlation between the target item and user's historical behaviors, without thoroughly considering the life-cycle features of user interest. In this paper, we propose an effective method called Deep Interest Life-cycle Network (DILN), which not only captures the interest life-cycle features efficiently, but can also be easily integrated to existing ranking models. DILN contains two key components: Interest Life-cycle Encoder Module constructs historical activity histograms of the user interest and then encodes them into dense representation. Interest Life-cycle Fusion Module injects the encoded dense representation into multiple expert networks, with the aim of enabling the specific phase of interest life-cycle to activate distinct experts. Online A/B testing reveals that DILN achieves significant improvements of +0.38% in CTR, +1.04% in CVR and +0.25% in duration per user, which demonstrates its effectiveness. In addition, DILN inherently increase the exposure of users' emergent and stable interests while decreasing the exposure of declining interests. DILN has been deployed on the Lofter App.

Represent Items by Items: An Enhanced Representation of the Target Item for Recommendation

Item-based collaborative filtering (ICF) has been widely used in industrial applications such as recommender system and online advertising. It models users' preference on target items by the items they have interacted with. Recent models use methods such as attention mechanism and deep neural network to learn the user representation and scoring function more accurately. However, despite their effectiveness, such models still overlook a problem that performance of ICF methods heavily depends on the quality of item representation especially the target item representation. In fact, due to the long-tail distribution in the recommendation, most item embeddings can not represent the semantics of items accurately and thus degrade the performance of current ICF methods. In this paper, we propose an enhanced representation of the target item which distills relevant information from the co-occurrence items. We design sampling strategies to sample fix number of co-occurrence items for the sake of noise reduction and computational cost. Considering the different importance of sampled items to the target item, we apply attention mechanism to selectively adopt the semantic information of the sampled items. Our proposed Co-occurrence based Enhanced Representation model (CER) learns the scoring function by a deep neural network with the attentive user representation and fusion of raw representation and enhanced representation of target item as input. With the enhanced representation, CER has stronger representation power for the tail items compared to the state-of-the-art ICF methods. Extensive experiments on two public benchmarks demonstrate the effectiveness of CER.