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

Page: https://stenobird.com/podcast/daily-paper-cast-7079649/a-new-role-for-relevance-guiding-corpus-interaction-in-agentic-search
Text version: https://stenobird.com/podcast/daily-paper-cast-7079649/a-new-role-for-relevance-guiding-corpus-interaction-in-agentic-search.md
Podcast: [Daily Paper Cast](https://stenobird.com/podcast/daily-paper-cast-7079649)
Published: 2026-07-30T03:55:53+00:00
Episode link: https://share.transistor.fm/s/d5b82491
Audio file: https://media.transistor.fm/d5b82491/f937812b.mp3
Processing state: not_requested
JSON: https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/a-new-role-for-relevance-guiding-corpus-interaction-in-agentic-search
Duration seconds: 1199

## Resource

🤗 Upvotes: 85 | cs.CL Authors: Jiangnan Li, Yuqing Li, Mo Yu, Jinchao Zhang, Jie Zhou Title: A New Role for Relevance: Guiding Corpus Interaction in Agentic Search Arxiv: http://arxiv.org/abs/2607.24223v1 Abstract: Relevance is a query-dependent estimate of whether a document or excerpt contains useful evidence. Existing retrieval agents use relevance to select top-$k$ content, but document relevance alone cannot localize, compose, or verify the evidence required by complex questions. Direct Corpus Interaction (DCI) enables such fine-grained operations through grep-style exploration, but its relevance-agnostic search can expose useful clues late and delay convergence. Recent advances use relevance to narrow the corpus into a working space for interaction. Once interaction begins, however, relevance still does not directly guide which documents grep searches first or distinguish informative excerpts from a broad set of matches to let LLMs see them first. We introduce the Relevance-Aware RipGrep Search Agent (RARG), which turns relevance into an execution prior for corpus interaction. RARG provides coarse-to-fine relevance guidance: it orders documents for sequential 'ripgrep' traversal to expose globally relevant clues earlier, initializes promising entry points with query-relevant paragraphs, and reranks grep matches to surface informative excerpts that document-level ranking may otherwise obscure. Across challenging browse question answering and reasoning-intensive retrieval, RARG improves the accuracy--efficiency frontier over retrieval-based and direct-interaction agents. These results demonstrate that relevance-aware interaction enables faster and more reliable search convergence.

## Actions

- request_transcript: `POST https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/a-new-role-for-relevance-guiding-corpus-interaction-in-agentic-search/transcription-requests` — Idempotently request low-priority transcript generation for this episode.
- read_markdown: `GET https://stenobird.com/podcast/daily-paper-cast-7079649/a-new-role-for-relevance-guiding-corpus-interaction-in-agentic-search.md` — Read the agent-friendly Markdown representation of this episode resource.

A page view does not enqueue transcription. Agents should invoke `request_transcript` explicitly when they need this episode processed.

## Transcript

Full transcripts are not published on public pages unless there is a clear rights basis.