@inproceedings{liu-etal-2026-prompt,
title = "Prompt-R1: Collaborative Automatic Prompting Framework via End-to-end Reinforcement Learning",
author = "Liu, Wenjin and
Luo, Haoran and
Lin, Xueyuan and
Liu, Haoming and
Shen, Tiesunlong and
Wang, Jiapu and
Mao, Rui and
Cambria, Erik",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-acl.799/",
pages = "16260--16280",
ISBN = "979-8-89176-395-1",
abstract = "Recently, various excellent and powerful large language models (LLMs) have been utilized to solve a wide range of human problems. However, when faced with complex problems, most users are often unable to provide accurate and effective prompts to interact with LLMs, thus limiting their performance. To address this challenge, we propose Prompt-R1, an end-to-end reinforcement learning framework that utilizes a small-scale LLM (as \textit{agent}) to collaborate with large-scale LLMs (as \textit{environment}), replacing users to interact better. This collaboration is presented as a multi-turn interaction, where the small-scale LLM thinks and generates prompts, and the large-scale LLM performs complex reasoning. A double-constrained reward is designed to optimize correctness and quality of generation. Prompt-R1 provides a plug-and-play framework that supports both inference and training with various large-scale LLMs. Experimental results on twelve datasets show that Prompt-R1 significantly outperforms baseline LLMs across various tasks.Our code is available at https://github.com/QwenQKing/Prompt-R1."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2026-prompt">
<titleInfo>
<title>Prompt-R1: Collaborative Automatic Prompting Framework via End-to-end Reinforcement Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wenjin</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haoran</namePart>
<namePart type="family">Luo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xueyuan</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haoming</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tiesunlong</namePart>
<namePart type="family">Shen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiapu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rui</namePart>
<namePart type="family">Mao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Erik</namePart>
<namePart type="family">Cambria</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-395-1</identifier>
</relatedItem>
<abstract>Recently, various excellent and powerful large language models (LLMs) have been utilized to solve a wide range of human problems. However, when faced with complex problems, most users are often unable to provide accurate and effective prompts to interact with LLMs, thus limiting their performance. To address this challenge, we propose Prompt-R1, an end-to-end reinforcement learning framework that utilizes a small-scale LLM (as agent) to collaborate with large-scale LLMs (as environment), replacing users to interact better. This collaboration is presented as a multi-turn interaction, where the small-scale LLM thinks and generates prompts, and the large-scale LLM performs complex reasoning. A double-constrained reward is designed to optimize correctness and quality of generation. Prompt-R1 provides a plug-and-play framework that supports both inference and training with various large-scale LLMs. Experimental results on twelve datasets show that Prompt-R1 significantly outperforms baseline LLMs across various tasks.Our code is available at https://github.com/QwenQKing/Prompt-R1.</abstract>
<identifier type="citekey">liu-etal-2026-prompt</identifier>
<location>
<url>https://aclanthology.org/2026.findings-acl.799/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>16260</start>
<end>16280</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Prompt-R1: Collaborative Automatic Prompting Framework via End-to-end Reinforcement Learning
%A Liu, Wenjin
%A Luo, Haoran
%A Lin, Xueyuan
%A Liu, Haoming
%A Shen, Tiesunlong
%A Wang, Jiapu
%A Mao, Rui
%A Cambria, Erik
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Findings of the Association for Computational Linguistics: ACL 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-395-1
%F liu-etal-2026-prompt
%X Recently, various excellent and powerful large language models (LLMs) have been utilized to solve a wide range of human problems. However, when faced with complex problems, most users are often unable to provide accurate and effective prompts to interact with LLMs, thus limiting their performance. To address this challenge, we propose Prompt-R1, an end-to-end reinforcement learning framework that utilizes a small-scale LLM (as agent) to collaborate with large-scale LLMs (as environment), replacing users to interact better. This collaboration is presented as a multi-turn interaction, where the small-scale LLM thinks and generates prompts, and the large-scale LLM performs complex reasoning. A double-constrained reward is designed to optimize correctness and quality of generation. Prompt-R1 provides a plug-and-play framework that supports both inference and training with various large-scale LLMs. Experimental results on twelve datasets show that Prompt-R1 significantly outperforms baseline LLMs across various tasks.Our code is available at https://github.com/QwenQKing/Prompt-R1.
%U https://aclanthology.org/2026.findings-acl.799/
%P 16260-16280
Markdown (Informal)
[Prompt-R1: Collaborative Automatic Prompting Framework via End-to-end Reinforcement Learning](https://aclanthology.org/2026.findings-acl.799/) (Liu et al., Findings 2026)
ACL
- Wenjin Liu, Haoran Luo, Xueyuan Lin, Haoming Liu, Tiesunlong Shen, Jiapu Wang, Rui Mao, and Erik Cambria. 2026. Prompt-R1: Collaborative Automatic Prompting Framework via End-to-end Reinforcement Learning. In Findings of the Association for Computational Linguistics: ACL 2026, pages 16260–16280, San Diego, California, United States. Association for Computational Linguistics.