analiza aiqbench
This paper introduces RubricRanker, a document reranker trained on LLM-synthesized search rubrics to ensure retrieved sets meet specific quality criteria like diversity and authority for deep research agents. By combining supervised fine-tuning with reinforcement learning guided by these explicit requirements, the model significantly outperforms standard relevance-matching baselines in generating high-quality answer subsets. The work advances retrieval systems specifically tailored for complex agent workflows rather than generic search tasks.
Training Documents Reranker with Search Rubrics for Deep Research Agent
arXiv:2608.03527v1 Announce Type: cross Abstract: 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.
Abstract: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.
Information Retrieval (cs.IR); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
arXiv:2608.03527 [cs.IR]
(or arXiv:2608.03527v1 [cs.IR] for this version)
https://doi.org/10.48550/arXiv.2608.03527 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 246 cuvinte
Subiecte conexe
[AINews] Opus 5.5 is good at explainer videos
Latent Space · 29 sept. 2026
[AINews] The Future of Latent Space
Latent Space · 25 sept. 2026
AdaTutoRank: Learning to Rerank Document Sets via Adaptive Tutoring Optimization for RAG and Deep Research
arXiv · 29 sept. 2026
[AINews] Agents disprove Polysemanticity; greatly improve Interpretability & Alignment
Latent Space · 16 oct. 2026