Careful Queries, Credible Results: Teaching RAG Models Advanced Web Search Tools with Reinforcement Learning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Dai, Yuqin, Yang, Shuo, Wang, Guoqing, Deng, Yong, Zhang, Zhanwei, Yin, Jun, Zeng, Pengyu, Ying, Zhenzhe, Meng, Changhua, Yi, Can, Zhou, Yuchen, Wang, Weiqiang, Lu, Shuai
Format:	Preprint
Published:	2025
Subjects:	Information Retrieval
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

_version_	1866911533181698048
author	Dai, Yuqin Yang, Shuo Wang, Guoqing Deng, Yong Zhang, Zhanwei Yin, Jun Zeng, Pengyu Ying, Zhenzhe Meng, Changhua Yi, Can Zhou, Yuchen Wang, Weiqiang Lu, Shuai
author_facet	Dai, Yuqin Yang, Shuo Wang, Guoqing Deng, Yong Zhang, Zhanwei Yin, Jun Zeng, Pengyu Ying, Zhenzhe Meng, Changhua Yi, Can Zhou, Yuchen Wang, Weiqiang Lu, Shuai
contents	Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by integrating up-to-date external knowledge, yet real-world web environments present unique challenges. These limitations manifest as two key challenges: pervasive misinformation in the web environment, which introduces unreliable or misleading content that can degrade retrieval accuracy, and the underutilization of web tools, which, if effectively employed, could enhance query precision and help mitigate this noise, ultimately improving the retrieval results in RAG systems. To address these issues, we propose WebFilter, a novel RAG framework that generates source-restricted queries and filters out unreliable content. This approach combines a retrieval filtering mechanism with a behavior- and outcome-driven reward strategy, optimizing both query formulation and retrieval outcomes. Extensive experiments demonstrate that WebFilter improves answer quality and retrieval precision, outperforming existing RAG methods on both in-domain and out-of-domain benchmarks.
format	Preprint
id	arxiv_https___arxiv_org_abs_2508_07956
institution	arXiv
publishDate	2025
record_format	arxiv
spellingShingle	Careful Queries, Credible Results: Teaching RAG Models Advanced Web Search Tools with Reinforcement Learning Dai, Yuqin Yang, Shuo Wang, Guoqing Deng, Yong Zhang, Zhanwei Yin, Jun Zeng, Pengyu Ying, Zhenzhe Meng, Changhua Yi, Can Zhou, Yuchen Wang, Weiqiang Lu, Shuai Information Retrieval Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by integrating up-to-date external knowledge, yet real-world web environments present unique challenges. These limitations manifest as two key challenges: pervasive misinformation in the web environment, which introduces unreliable or misleading content that can degrade retrieval accuracy, and the underutilization of web tools, which, if effectively employed, could enhance query precision and help mitigate this noise, ultimately improving the retrieval results in RAG systems. To address these issues, we propose WebFilter, a novel RAG framework that generates source-restricted queries and filters out unreliable content. This approach combines a retrieval filtering mechanism with a behavior- and outcome-driven reward strategy, optimizing both query formulation and retrieval outcomes. Extensive experiments demonstrate that WebFilter improves answer quality and retrieval precision, outperforming existing RAG methods on both in-domain and out-of-domain benchmarks.
title	Careful Queries, Credible Results: Teaching RAG Models Advanced Web Search Tools with Reinforcement Learning
topic	Information Retrieval
url	https://arxiv.org/abs/2508.07956