RubricRanker is a reranker trained with LLM-generated search rubrics and reinforcement learning to select high-quality document sets, outperforming baselines on deep research and RAG benchmarks.
set_level_rubrics
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
method 1
citation-polarity summary
fields
cs.IR 1years
2026 1verdicts
CONDITIONAL 1roles
method 1polarities
use method 1representative citing papers
citing papers explorer
-
Training Documents Reranker with Search Rubrics for Deep Research Agent
RubricRanker is a reranker trained with LLM-generated search rubrics and reinforcement learning to select high-quality document sets, outperforming baselines on deep research and RAG benchmarks.