Metraipolis › archive › dc_aede163c7543
Training Documents Reranker with Search Rubrics for Deep Research Agent — arXiv:2608.03527
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.03527
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-31T12:19:27.267Z
- SHA-256 of the archived text
82dccb67813f42c630564edee0f1e43973ea5051f867d5b6444d96f7b6e726e0- Stable URL of this page
https://metraipolis.com/documento/dc_aede163c7543
How to cite
Training Documents Reranker with Search Rubrics for Deep Research Agent — arXiv:2608.03527 — arXiv (en), https://arxiv.org/abs/2608.03527 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_aede163c7543 (Metraipolis archive dc_aede163c7543, sha256 82dccb67813f42c630564edee0f1e43973ea5051f867d5b6444d96f7b6e726e0)
BibTeX
@misc{dcaede163c7543,
title = {Training Documents Reranker with Search Rubrics for Deep Research Agent — arXiv:2608.03527},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.03527},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_aede163c7543; sha256 82dccb67813f42c630564edee0f1e43973ea5051f867d5b6444d96f7b6e726e0},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.03527. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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.
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-05 in cs.AI).
Categorie arXiv: Information Retrieval (cs.IR) ; Artificial Intelligence (cs.AI); Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2608.03527 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-31T12:05:53.059Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).