OnePiece: Bringing Context Engineering and Reasoning to Industrial Cascade Ranking System

Despite the growing interest in replicating the scaled success of large language models (LLMs) in industrial search and recommender systems, most existing industrial efforts remain limited to transplanting Transformer architectures, yielding only marginal gains over strong Deep Learning Recommendation Models (DLRMs).From a first principle perspective, the breakthroughs of LLMs stem not only from their architectures but also from two complementary mechanisms: context engineering, which enriches raw input queries with contextual cues to better elicit model capabilities, and multi-step reasoning, which iteratively refines outputs through intermediate reasoning paths. However, these mechanisms remain largely underexplored in industrial ranking systems. In this paper, we propose OnePiece, a unified framework that seamlessly integrates LLM-style context engineering and reasoning into both retrieval and ranking models of industrial cascaded pipelines. OnePiece is built on a pure Transformer backbone and further introduces three key innovations: (1) structured context engineering, which augments interaction history with preference and scenario signals and unifies them into a tokenized input sequence for both retrieval and ranking; (2) block-wise latent reasoning, which enables multi-step refinement of representations and scales reasoning bandwidth via block size; (3) progressive multi-task training, which leverages user feedback chains to effectively supervise reasoning steps during training. Extensive offline experiments verify the effectiveness of each core design and show that OnePiece continues to improve with larger training spans. OnePiece has been deployed in the main personalized search scenario of Shopee and achieves +1.80% GMV/UU and a +3.33% increase in advertising revenue.