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.
Your job: - First analyze the query, the query intent, and the reference answer
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2026 1verdicts
CONDITIONAL 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.