arXiv subjects

Yinjiang Cai

Publications and source records attributed to Yinjiang Cai.

5 recordsLinked to original sources

arXiv2026

RecGPT-Mobile-V2 Technical Report

Personalized Query prediction maps implicit behavioral signals---clicks, favorites, purchases, and post-purchase exploration---to explicit retrieval intent. On-device deployment makes this task particularly challenging: behavioral trajectories are noisy and multi-scale, multiple Queries may be valid for a single trajectory, and a uniform reasoning policy either expends unnecessary computation on simple instances or allocates insufficient capacity to complex ones. We introduce RecGPT-Mobile-V2, an end-to-end framework that treats intent quality and execution efficiency as coupled objectives within a staged design. The framework transforms heterogeneous interactions into an evidence-preserving trajectory, establishes a recommendation-native foundation through domain adaptation and supervised alignment, and applies reasoning-cost optimization only after grouped rollouts meet grounding and utility criteria. The resulting teacher is distilled into a compact student deployed with low-bit execution, structured compression, and budget-aware device--cloud routing. In an aligned CoT ablation, an evidence-focused short rationale increases ROUGE-L from 0.228 to 0.315 and Jaccard from 0.174 to 0.248, while slightly outperforming the full five-stage rationale. In the controlled RL comparison, the complete reward formulation improves Query quality from 73.2% under quality-only RL to 78.6%, lowers the hard-failure rate from 3.6% to 1.6%, and reduces the median CoT length from 62 to 14 tokens. Online retrieval analysis further indicates that the Query recall channel retrieves inventory complementary to that surfaced by established recall channels. Collectively, these findings support sufficiency-oriented rather than uniformly short reasoning: retain decision-relevant evidence and allocate additional computation only when it is likely to improve the predicted Query.

cs.IR↗

arXiv2026

PILOT Technical Report

Existing agentic approaches for recommendation system optimization remain fundamentally reactive: they adjust parameters in response to observed metric changes but lack the ability to proactively design controlled experiments, personalize strategies at the user-segment level, or accumulate reusable experimental methodology across tasks. We present PILOT (Proactive Insight Learner for Online Tree-Experiments), an LLM-agent framework that organizes three roles within a constrained control loop where deterministic services enforce all safety, statistical, and permission boundaries: (1) an Experiment Manager that drives the full experiment lifecycle -- task intake, observation governance, anomaly recovery, and postmortem -- by selecting only from a rule-generated legal-command envelope; (2) a Search Planner that proposes candidate decision trees for user-segment-level personalization, invoked only when the Manager requests planning; and (3) a Memory Curator that asynchronously distills experiment outcomes into strategy-level domain knowledge and provenance-tracked methodology, failure-isolated from the main loop. The Manager makes the agent proactive, the Planner enables population-level personalization beyond global tuning, and the Curator turns every completed task into a learning opportunity for the next. Deployed on Taobao's platform with 5 experimental buckets, PILOT is compared against ROAM(Reactive Optimization with Agent-driven Moves), a free-exploration agent without lifecycle governance or structured hypothesis testing. PILOT achieves up to +1.40% IPV, +1.60% Core IPV, +0.96% transaction count, and +1.50% transaction amount, improving over ROAM's best results (+1.00% IPV, +0.90% Core IPV, +0.60% transaction count, +1.13% transaction amount) while raising search efficiency from 53.3% to 93.3% (+40 pp), with no human intervention throughout the experimental cycle.

cs.IR↗

arXiv2026

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%.

cs.IR↗

arXiv2025

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.

cs.IR↗

arXiv2021

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.

cs.IR↗