Episode
A New Role for Relevance: Guiding Corpus Interaction in Agentic Search
- Podcast
- Daily Paper Cast
- Published
- Jul 30, 2026
- Duration seconds
- 1199
- Processing state
not_requested- Canonical source
- https://share.transistor.fm/s/d5b82491
Actions
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.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.
Summary
🤗 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.