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

Hugging Face Daily Papers Papers
agentic-search retrieval-agents relevance-ranking question-answering reasoning corpus-interaction

Summary

This paper introduces the Relevance-Aware RipGrep Search Agent (RARG), which uses relevance as an execution prior for corpus interaction in agentic search, improving accuracy and efficiency over existing methods.

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.
Original Article
View Cached Full Text

Cached at: 07/29/26, 03:50 AM

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

Source: https://huggingface.co/papers/2607.24223

Abstract

Relevanceisaquery-dependentestimateofwhetheradocumentorexcerptcontainsusefulevidence.Existingretrievalagentsuserelevancetoselecttop-kcontent,butdocumentrelevancealonecannotlocalize,compose,orverifytheevidencerequiredbycomplexquestions.DirectCorpusInteraction(DCI)enablessuchfine-grainedoperationsthroughgrep-styleexploration,butitsrelevance-agnosticsearchcanexposeusefulclueslateanddelayconvergence.Recentadvancesuserelevancetonarrowthecorpusintoaworkingspaceforinteraction.Onceinteractionbegins,however,relevancestilldoesnotdirectlyguidewhichdocumentsgrepsearchesfirstordistinguishinformativeexcerptsfromabroadsetofmatchestoletLLMsseethemfirst.WeintroducetheRelevance-AwareRipGrepSearchAgent(RARG),whichturnsrelevanceintoanexecutionpriorforcorpusinteraction.RARGprovidescoarse-to-finerelevanceguidance:itordersdocumentsforsequential’ripgrep’traversaltoexposegloballyrelevantcluesearlier,initializespromisingentrypointswithquery-relevantparagraphs,andreranksgrepmatchestosurfaceinformativeexcerptsthatdocument-levelrankingmayotherwiseobscure.Acrosschallengingbrowsequestionansweringandreasoning-intensiveretrieval,RARGimprovestheaccuracy--efficiencyfrontieroverretrieval-basedanddirect-interactionagents.Theseresultsdemonstratethatrelevance-awareinteractionenablesfasterandmorereliablesearchconvergence.

View arXiv pageView PDFProject pageGitHub23Add to collection

Get this paper in your agent:

hf papers read 2607\.24223

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2607.24223 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2607.24223 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2607.24223 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction

Hugging Face Daily Papers

The paper introduces Direct Corpus Interaction (DCI), a novel approach allowing AI agents to query raw text directly using standard terminal tools instead of traditional embedding-based retrieval. By bypassing fixed similarity interfaces and offline indexing, DCI significantly outperforms conventional sparse, dense, and reranking baselines across multiple IR and agentic search benchmarks.

GrepSeek: Training Search Agents for Direct Corpus Interaction

arXiv cs.CL

GrepSeek trains LLM search agents to directly interact with a text corpus using shell commands like grep, using a two-stage training pipeline with cold-start dataset construction and GRPO refinement, achieving strong F1 and Exact Match on open-domain QA benchmarks.

GRASP: GRanularity-Aware Search Policy for Agentic RAG

Hugging Face Daily Papers

Introduces GRASP, a reinforcement learning framework that trains agents to adaptively coordinate semantic search, keyword search, and paragraph reading during multi-step reasoning, improving retrieval recall and question answering performance on multi-hop benchmarks.