Agentic-R: Learning to Retrieve for Agentic Search
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917213933404160 |
|---|---|
| author | Liu, Wenhan Ma, Xinyu Zhu, Yutao Li, Yuchen Shi, Daiting Yin, Dawei Dou, Zhicheng |
| author_facet | Liu, Wenhan Ma, Xinyu Zhu, Yutao Li, Yuchen Shi, Daiting Yin, Dawei Dou, Zhicheng |
| contents | Agentic search has recently emerged as a powerful paradigm, where an agent interleaves multi-step reasoning with on-demand retrieval to solve complex questions. Despite its success, how to design a retriever for agentic search remains largely underexplored. Existing search agents typically rely on similarity-based retrievers, while similar passages are not always useful for final answer generation. In this paper, we propose a novel retriever training framework tailored for agentic search. Unlike retrievers designed for single-turn retrieval-augmented generation (RAG) that only rely on local passage utility, we propose to use both local query-passage relevance and global answer correctness to measure passage utility in a multi-turn agentic search. We further introduce an iterative training strategy, where the search agent and the retriever are optimized bidirectionally and iteratively. Different from RAG retrievers that are only trained once with fixed questions, our retriever is continuously improved using evolving and higher-quality queries from the agent. Extensive experiments on seven single-hop and multi-hop QA benchmarks demonstrate that our retriever, termed \ours{}, consistently outperforms strong baselines across different search agents. Our codes are available at: https://github.com/8421BCD/Agentic-R. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_11888 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Agentic-R: Learning to Retrieve for Agentic Search Liu, Wenhan Ma, Xinyu Zhu, Yutao Li, Yuchen Shi, Daiting Yin, Dawei Dou, Zhicheng Information Retrieval Computation and Language Agentic search has recently emerged as a powerful paradigm, where an agent interleaves multi-step reasoning with on-demand retrieval to solve complex questions. Despite its success, how to design a retriever for agentic search remains largely underexplored. Existing search agents typically rely on similarity-based retrievers, while similar passages are not always useful for final answer generation. In this paper, we propose a novel retriever training framework tailored for agentic search. Unlike retrievers designed for single-turn retrieval-augmented generation (RAG) that only rely on local passage utility, we propose to use both local query-passage relevance and global answer correctness to measure passage utility in a multi-turn agentic search. We further introduce an iterative training strategy, where the search agent and the retriever are optimized bidirectionally and iteratively. Different from RAG retrievers that are only trained once with fixed questions, our retriever is continuously improved using evolving and higher-quality queries from the agent. Extensive experiments on seven single-hop and multi-hop QA benchmarks demonstrate that our retriever, termed \ours{}, consistently outperforms strong baselines across different search agents. Our codes are available at: https://github.com/8421BCD/Agentic-R. |
| title | Agentic-R: Learning to Retrieve for Agentic Search |
| topic | Information Retrieval Computation and Language |
| url | https://arxiv.org/abs/2601.11888 |