@inproceedings{batorski-etal-2026-prl,
title = "{PRL}: Prompts from Reinforcement Learning",
author = "Batorski, Pawe{\l} and
Kosmala, Adrian and
Swoboda, Paul",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.6/",
pages = "95--114",
ISBN = "979-8-89176-462-0",
abstract = "Effective prompt engineering remains a central challenge in fully harnessing the capabilities of LLMs. While well-designed prompts can dramatically enhance performance, crafting them typically demands expert intuition and a nuanced understanding of the task. Moreover, the most impactful prompts often hinge on subtle semantic cues, ones that may elude human perception but are crucial for guiding LLM behavior. In this paper, we introduce PRL (Prompts from Reinforcement Learning), a novel RL-based approach for automatic prompt generation. Unlike most prior methods, PRL can also generate novel few-shot demonstrations rather than selecting only from examples seen during training. Empirically, our approach achieves state-of-the-art performance across a diverse set of benchmarks, including text classification, text simplification, and mathematical reasoning, while remaining competitive on text summarization. Our code is available at https://github.com/Batorskq/prl."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="batorski-etal-2026-prl">
<titleInfo>
<title>PRL: Prompts from Reinforcement Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Paweł</namePart>
<namePart type="family">Batorski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adrian</namePart>
<namePart type="family">Kosmala</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Swoboda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>Effective prompt engineering remains a central challenge in fully harnessing the capabilities of LLMs. While well-designed prompts can dramatically enhance performance, crafting them typically demands expert intuition and a nuanced understanding of the task. Moreover, the most impactful prompts often hinge on subtle semantic cues, ones that may elude human perception but are crucial for guiding LLM behavior. In this paper, we introduce PRL (Prompts from Reinforcement Learning), a novel RL-based approach for automatic prompt generation. Unlike most prior methods, PRL can also generate novel few-shot demonstrations rather than selecting only from examples seen during training. Empirically, our approach achieves state-of-the-art performance across a diverse set of benchmarks, including text classification, text simplification, and mathematical reasoning, while remaining competitive on text summarization. Our code is available at https://github.com/Batorskq/prl.</abstract>
<identifier type="citekey">batorski-etal-2026-prl</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.6/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>95</start>
<end>114</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PRL: Prompts from Reinforcement Learning
%A Batorski, Paweł
%A Kosmala, Adrian
%A Swoboda, Paul
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F batorski-etal-2026-prl
%X Effective prompt engineering remains a central challenge in fully harnessing the capabilities of LLMs. While well-designed prompts can dramatically enhance performance, crafting them typically demands expert intuition and a nuanced understanding of the task. Moreover, the most impactful prompts often hinge on subtle semantic cues, ones that may elude human perception but are crucial for guiding LLM behavior. In this paper, we introduce PRL (Prompts from Reinforcement Learning), a novel RL-based approach for automatic prompt generation. Unlike most prior methods, PRL can also generate novel few-shot demonstrations rather than selecting only from examples seen during training. Empirically, our approach achieves state-of-the-art performance across a diverse set of benchmarks, including text classification, text simplification, and mathematical reasoning, while remaining competitive on text summarization. Our code is available at https://github.com/Batorskq/prl.
%U https://aclanthology.org/2026.findings-emnlp.6/
%P 95-114
Markdown (Informal)
[PRL: Prompts from Reinforcement Learning](https://aclanthology.org/2026.findings-emnlp.6/) (Batorski et al., Findings 2026)
ACL
- Paweł Batorski, Adrian Kosmala, and Paul Swoboda. 2026. PRL: Prompts from Reinforcement Learning. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 95–114, Budapest, Hungary. Association for Computational Linguistics.