Verbal-R3: Verbal Reranker as the Missing Bridge between Retrieval and Reasoning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Park, Sangkwon, Kang, Donghun, Mok, Jisoo, Yoon, Sungroh
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913083550597120
author Park, Sangkwon
Kang, Donghun
Mok, Jisoo
Yoon, Sungroh
author_facet Park, Sangkwon
Kang, Donghun
Mok, Jisoo
Yoon, Sungroh
contents The conventional Retrieval-Augmented Generation (RAG) paradigm of injecting raw retrieved texts into the Large Language Model (LLM)'s context often results in suboptimal integration of retrieved information. This paper proposes to bridge retrieval results and the LLM's reasoning ability through Verbal Annotations, analytic narratives that explicitly articulate the logical connection between a search query and retrieved contexts. Our empirical investigation reveals the potential of Verbal Annotations to substantially enhance the LLM's ability to generate accurate, contextually-grounded responses. Motivated by this finding, we introduce Verbal-R3, a novel agentic RAG framework that consists of a Generator and a Verbal Reranker. The Generator performs iterative retrieval and reasoning, while the Verbal Reranker returns relevance scores and Verbal Annotations to guide the reasoning and answering process of the Generator. The inference process of Verbal-R3 is further refined through relevance-guided test-time scaling, which efficiently allocates test-time compute for effective trajectory expansion. Verbal-R3 achieves state-of-the-art performance on complex Question Answering benchmarks, validating the effectiveness of the proposed framework.
format Preprint
id arxiv_https___arxiv_org_abs_2605_01399
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Verbal-R3: Verbal Reranker as the Missing Bridge between Retrieval and Reasoning
Park, Sangkwon
Kang, Donghun
Mok, Jisoo
Yoon, Sungroh
Computation and Language
Artificial Intelligence
Information Retrieval
The conventional Retrieval-Augmented Generation (RAG) paradigm of injecting raw retrieved texts into the Large Language Model (LLM)'s context often results in suboptimal integration of retrieved information. This paper proposes to bridge retrieval results and the LLM's reasoning ability through Verbal Annotations, analytic narratives that explicitly articulate the logical connection between a search query and retrieved contexts. Our empirical investigation reveals the potential of Verbal Annotations to substantially enhance the LLM's ability to generate accurate, contextually-grounded responses. Motivated by this finding, we introduce Verbal-R3, a novel agentic RAG framework that consists of a Generator and a Verbal Reranker. The Generator performs iterative retrieval and reasoning, while the Verbal Reranker returns relevance scores and Verbal Annotations to guide the reasoning and answering process of the Generator. The inference process of Verbal-R3 is further refined through relevance-guided test-time scaling, which efficiently allocates test-time compute for effective trajectory expansion. Verbal-R3 achieves state-of-the-art performance on complex Question Answering benchmarks, validating the effectiveness of the proposed framework.
title Verbal-R3: Verbal Reranker as the Missing Bridge between Retrieval and Reasoning
topic Computation and Language
Artificial Intelligence
Information Retrieval
url https://arxiv.org/abs/2605.01399