arXiv · 2611.22503
From Relevance to Utility: Rubric Alignment in Yuanbao Search
Abstract
Agentic search demands that a search engine move beyond per document relevance ranking to assemble document sets optimized for downstream LLM reasoning. Prior work addresses this either by improving individual pipeline stages in isolation or by applying RL based selection on top of relevance trained upstream modules, leaving the full stack unaligned to utility for reasoning. We propose rubric aligned search, a framework that unifies the traditional search pipeline under a single supervision surface. For each query, we derive a rubric from coarse to fine, specifying weighted positive criteria that the document set must satisfy and negative criteria that it must avoid. From this rubric we derive two training signals. First, a lightweight labeler distills rubric grounded judgments into per document utility labels, which supervise a contrastive dual encoder for retrieval and a multi task ranker trained with four rubric aligned scoring heads. Second, a rubric conditioned evaluator produces a set level reward that drives a dual branch RL selector, combining GRPO with best rollout distillation to resolve credit assignment in subset optimization. Deployed in Yuanbao Search, the pipeline improves end to end answer quality by 8.52% over the online production baseline.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Yu Lu, Lixin Zou, Yangqi Chen, Hui Xu, Qiaolin Xia, Hao Wang, Qianwen Ma, Reed Li, Shuang Zeng, Haijin Liang, Haibo Shi. 2026-11-17. From Relevance to Utility: Rubric Alignment in Yuanbao Search. https://searcharxiv.com/abs/2611.22503
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Searcharxiv by Indiciae: BibTeX · RIS.