Training Documents Reranker with Search Rubrics for Deep Research Agent
Retrieval systems help deep research agents generate high-quality answers by providing relevant documents. However, existing retrievers typically select documents through relevance matching, while individually well-matched top-$k$ documents may not form a \textit{set} that satisfies the complex information needs of an agent query (\eg, diverse, concise and authoritative documents). In this paper, we propose search-oriented rubrics that \textit{explicitly} define the requirements that high-quality document sets should satisfy for each agent query. Our search rubrics are organized into a hierarchical structure and synthesized using a powerful LLM. Based on these search rubrics, we further train a document reranker \textbf{RubricRanker} to select a high-quality subset from retrieved documents. We design a two-stage training framework that consists of rubrics-guided supervised fine-tuning and rubric-based reinforcement learning. Extensive experiments demonstrate that RubricRanker outperforms the strongest baseline by 2.6 points on four deep research benchmarks and generalizes well to five RAG benchmarks.
Code (0)
등록된 구현이 없습니다.
Tasks
Reinforcement LearningSimilar Papers 제목 키워드 기반
Drowning in Documents: Consequences of Scaling Reranker Inference
Rerankers, typically cross-encoders, are often used to re-score the documents retrieved by cheaper initial IR systems. This is because, though expensive, rerankers are assumed to be more effective. We challenge this assu…
RerankingRetrievalBeyond Sequential Reranking: Reranker-Guided Search Improves Reasoning Intensive Retrieval
The widely used retrieve-and-rerank pipeline faces two critical limitations: they are constrained by the initial retrieval quality of the top-k documents, and the growing computational demands of LLM-based rerankers rest…
Beyond Relevance-Centric Retrieval: Rubric-Oriented Document Set Selection and Ranking
As large language models and AI agents become the primary consumers of search results, document set quality determines the upper bound of downstream generation. Yet existing evaluation systems remain confined to scoring …
Gumbel Reranking: Differentiable End-to-End Reranker Optimization
RAG systems rely on rerankers to identify relevant documents. However, fine-tuning these models remains challenging due to the scarcity of annotated query-document pairs. Existing distillation-based approaches suffer fro…
RAGRerankingGuiding Retrieval using LLM-based Listwise Rankers
Large Language Models (LLMs) have shown strong promise as rerankers, especially in ``listwise'' settings where an LLM is prompted to rerank several search results at once. However, this ``cascading'' retrieve-and-rerank …
Retrieval