A New Role for Relevance: Guiding Corpus Interaction in Agentic Search

Published
Source
arXiv
Paper number
742
Field
LLMs / NLP
arXiv ID
2607.24223

Key points

  • It redefines relevance as the order in which grep explores the corpus, rather than as a top-k document selection problem.
  • Document ranking provides global relevance, while match reranking provides local relevance.
  • It seeds the retrieval start points with question-matched passages so that decisive evidence is found earlier.
  • On GPT-5.4-mini, it reaches 84 percent accuracy with only 23.9 tool calls, which is far fewer calls than competing methods.
  • It retains 79 percent accuracy even when scaled to one million documents, showing only a mild performance drop.

Paper links

External research summaries. These are not HDATF publications or measured product results.

Read original (opens in a new tab)