The paper introduces Lightweight Ranking Heads (Light Heads), a framework that allows new prediction tasks to be added to large multi-task recommender systems without retraining the backbone model. By using stop‑gradients and stateless daily training, Light Heads isolate new tasks, preventing conflicts with existing ones. Deployed at YouTube scale, the approach cuts multi‑task experimentation cycles from weeks to days, enabling faster A/B testing and deployment of new ranking tasks.
arXiv:2609.35783v1 Announce Type: cross Abstract: Large-scale recommender systems, particularly short-form video platforms, are often bottlenecked by massive popularity feedback loops. In such enviro...
CORAL is an LLM‑native harness that automates continual optimization of production recommender systems. It operates in a closed loop: an agent observes system signals, reasons over past decisions, and uses tools—including a numerical optimizer—to reconfigure the recommender while staying within a fixed operating budget. In A/B experiments on two large social platforms, CORAL improved engagement without extra serving cost on one platform and reduced serving cost without harming engagement on the other, demonstrating that a single agentic loop can replace manual engineering for ongoing system tuning.
arXiv:2606. 00422v1 Announce Type: cross Abstract: Modern recommendation systems predominantly train retrieval and ranking as separate models despite both increasingly relying on large transformers encoding the same user behavior data, duplicating parameters, compute, and serving cost.
DeGRe is a dense‑supervised generative reranking framework designed to improve multi‑stage recommender systems by addressing label bias and credit assignment issues. It uses an offline Lookahead Evaluator with beam search to generate dense supervision signals, which are distilled into a lightweight Online Generator that can perform efficient greedy decoding at inference time. Experiments show that DeGRe outperforms baselines on public benchmarks and industrial datasets, and it has been successfully deployed on Taobao Flash Shopping to enhance online recommendations.
arXiv:2607. 27744v1 Announce Type: new Abstract: Modern recommendation models gain prediction quality by scaling feature-interaction and sequence modules, but production cost constraints cap how far systems can scale.
arXiv:2607. 27577v1 Announce Type: cross Abstract: Heterogeneous recommendation feeds present complex challenges that extend beyond those found in highly homogeneous environments (e.
arXiv:2606. 28117v1 Announce Type: new Abstract: Low-Rank Adaptation (LoRA) has become the standard tool for parameter-efficient fine-tuning of large pretrained models.
SequenceO1 is an end‑to‑end framework that enables ultra‑long (up to 100K interactions) sequence modeling for recommendation systems. It compresses raw user histories into a fixed‑size sketch using Sketch Attention and then models short‑term and long‑term interests with Target‑to‑History Cross Attention. The system incorporates low‑rank caching, batching, pipeline lift, and a FlashSA kernel to keep training and inference efficient, achieving consistent offline and online performance gains when deployed at full traffic on Douyin.
arXiv:2605. 20803v2 Announce Type: replace-cross Abstract: Continual learning (CL) aims to train models sequentially on multiple tasks while mitigating catastrophic forgetting of previously learned knowledge.
The paper presents a method for fine‑tuning a large language model (LLM) recommender to generate personalized, non‑harmful explanations for its recommendations. By training two LLM‑judge reward models and using constrained GRPO, the authors achieve a significant increase in the PASS rate for all three criteria, from 0.649 to 0.956 on their own judges and from 0.677 to 0.931 on an independent judge. The fine‑tuned model maintains its original recommendation performance, demonstrating that LLM‑based recommenders can be adapted to complex tasks without loss of effectiveness.
arXiv:2607. 24845v1 Announce Type: cross Abstract: Large language models (LLMs) have been applied to sequential recommendation by formulating it as a natural language task.
arXiv:2608. 09016v1 Announce Type: cross Abstract: Node ranking is a fundamental problem in graph information retrieval, measuring the relative importance of nodes and supporting a wide range of applications such as influence analysis, recommendation, and graph-based retrieval augmented generation.