@inproceedings{zhang-etal-2025-rearank,
title = "{REARANK}: Reasoning Re-ranking Agent via Reinforcement Learning",
author = "Zhang, Le and
Wang, Bo and
Qiu, Xipeng and
Reddy, Siva and
Agrawal, Aishwarya",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.emnlp-main.125/",
pages = "2458--2471",
ISBN = "979-8-89176-332-6",
abstract = "We present REARANK, a large language model (LLM)-based listwise reasoning rerank- ing agent. REARANK explicitly reasons be- fore reranking, significantly improving both performance and interpretability. Leveraging reinforcement learning and data augmentation, REARANK achieves substantial improvements over baseline models across popular informa- tion retrieval benchmarks, notably requiring only 179 annotated samples. Built on top of Qwen2.5-7B, our REARANK-7B demonstrates performance comparable to GPT-4 on both in- domain and out-of-domain benchmarks and even surpasses GPT-4 on reasoning-intensive BRIGHT benchmarks. These results under- score the effectiveness of our approach and highlight how reinforcement learning can en- hance LLM reasoning capabilities in reranking."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2025-rearank">
<titleInfo>
<title>REARANK: Reasoning Re-ranking Agent via Reinforcement Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Le</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bo</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xipeng</namePart>
<namePart type="family">Qiu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siva</namePart>
<namePart type="family">Reddy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aishwarya</namePart>
<namePart type="family">Agrawal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-332-6</identifier>
</relatedItem>
<abstract>We present REARANK, a large language model (LLM)-based listwise reasoning rerank- ing agent. REARANK explicitly reasons be- fore reranking, significantly improving both performance and interpretability. Leveraging reinforcement learning and data augmentation, REARANK achieves substantial improvements over baseline models across popular informa- tion retrieval benchmarks, notably requiring only 179 annotated samples. Built on top of Qwen2.5-7B, our REARANK-7B demonstrates performance comparable to GPT-4 on both in- domain and out-of-domain benchmarks and even surpasses GPT-4 on reasoning-intensive BRIGHT benchmarks. These results under- score the effectiveness of our approach and highlight how reinforcement learning can en- hance LLM reasoning capabilities in reranking.</abstract>
<identifier type="citekey">zhang-etal-2025-rearank</identifier>
<location>
<url>https://aclanthology.org/2025.emnlp-main.125/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>2458</start>
<end>2471</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T REARANK: Reasoning Re-ranking Agent via Reinforcement Learning
%A Zhang, Le
%A Wang, Bo
%A Qiu, Xipeng
%A Reddy, Siva
%A Agrawal, Aishwarya
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-332-6
%F zhang-etal-2025-rearank
%X We present REARANK, a large language model (LLM)-based listwise reasoning rerank- ing agent. REARANK explicitly reasons be- fore reranking, significantly improving both performance and interpretability. Leveraging reinforcement learning and data augmentation, REARANK achieves substantial improvements over baseline models across popular informa- tion retrieval benchmarks, notably requiring only 179 annotated samples. Built on top of Qwen2.5-7B, our REARANK-7B demonstrates performance comparable to GPT-4 on both in- domain and out-of-domain benchmarks and even surpasses GPT-4 on reasoning-intensive BRIGHT benchmarks. These results under- score the effectiveness of our approach and highlight how reinforcement learning can en- hance LLM reasoning capabilities in reranking.
%U https://aclanthology.org/2025.emnlp-main.125/
%P 2458-2471
Markdown (Informal)
[REARANK: Reasoning Re-ranking Agent via Reinforcement Learning](https://aclanthology.org/2025.emnlp-main.125/) (Zhang et al., EMNLP 2025)
ACL