@inproceedings{liu-etal-2025-epo,
title = "{EPO}: Explicit Policy Optimization for Strategic Reasoning in {LLM}s via Reinforcement Learning",
author = "Liu, Xiaoqian and
Wang, Ke and
Li, Yongbin and
Wu, Yuchuan and
Ma, Wentao and
Kong, Aobo and
Huang, Fei and
Jiao, Jianbin and
Zhang, Junge",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-long.747/",
doi = "10.18653/v1/2025.acl-long.747",
pages = "15371--15396",
ISBN = "979-8-89176-251-0",
abstract = "Large Language Models (LLMs) have shown impressive reasoning capabilities in well-defined problems with clear solutions, such as mathematics and coding. However, they still struggle with complex real-world scenarios like business negotiations, which require strategic reasoning{---}an ability to navigate dynamic environments and align long-term goals amidst uncertainty.Existing methods for strategic reasoning face challenges in adaptability, scalability, and transferring strategies to new contexts.To address these issues, we propose explicit policy optimization (*EPO*) for strategic reasoning, featuring an LLM that provides strategies in open-ended action space and can be plugged into arbitrary LLM agents to motivate goal-directed behavior.To improve adaptability and policy transferability, we train the strategic reasoning model via multi-turn reinforcement learning (RL), utilizing process rewards and iterative self-play.Experiments across social and physical domains demonstrate *EPO*{'}s ability of long-term goal alignment through enhanced strategic reasoning, achieving state-of-the-art performance on social dialogue and web navigation tasks. Our findings reveal various collaborative reasoning mechanisms emergent in *EPO* and its effectiveness in generating novel strategies, underscoring its potential for strategic reasoning in real-world applications. Code and data are available at [https://github.com/lxqpku/EPO](https://github.com/lxqpku/EPO)."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2025-epo">
<titleInfo>
<title>EPO: Explicit Policy Optimization for Strategic Reasoning in LLMs via Reinforcement Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xiaoqian</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ke</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yongbin</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuchuan</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wentao</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aobo</namePart>
<namePart type="family">Kong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jianbin</namePart>
<namePart type="family">Jiao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junge</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-251-0</identifier>
</relatedItem>
<abstract>Large Language Models (LLMs) have shown impressive reasoning capabilities in well-defined problems with clear solutions, such as mathematics and coding. However, they still struggle with complex real-world scenarios like business negotiations, which require strategic reasoning—an ability to navigate dynamic environments and align long-term goals amidst uncertainty.Existing methods for strategic reasoning face challenges in adaptability, scalability, and transferring strategies to new contexts.To address these issues, we propose explicit policy optimization (*EPO*) for strategic reasoning, featuring an LLM that provides strategies in open-ended action space and can be plugged into arbitrary LLM agents to motivate goal-directed behavior.To improve adaptability and policy transferability, we train the strategic reasoning model via multi-turn reinforcement learning (RL), utilizing process rewards and iterative self-play.Experiments across social and physical domains demonstrate *EPO*’s ability of long-term goal alignment through enhanced strategic reasoning, achieving state-of-the-art performance on social dialogue and web navigation tasks. Our findings reveal various collaborative reasoning mechanisms emergent in *EPO* and its effectiveness in generating novel strategies, underscoring its potential for strategic reasoning in real-world applications. Code and data are available at [https://github.com/lxqpku/EPO](https://github.com/lxqpku/EPO).</abstract>
<identifier type="citekey">liu-etal-2025-epo</identifier>
<identifier type="doi">10.18653/v1/2025.acl-long.747</identifier>
<location>
<url>https://aclanthology.org/2025.acl-long.747/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>15371</start>
<end>15396</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T EPO: Explicit Policy Optimization for Strategic Reasoning in LLMs via Reinforcement Learning
%A Liu, Xiaoqian
%A Wang, Ke
%A Li, Yongbin
%A Wu, Yuchuan
%A Ma, Wentao
%A Kong, Aobo
%A Huang, Fei
%A Jiao, Jianbin
%A Zhang, Junge
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-251-0
%F liu-etal-2025-epo
%X Large Language Models (LLMs) have shown impressive reasoning capabilities in well-defined problems with clear solutions, such as mathematics and coding. However, they still struggle with complex real-world scenarios like business negotiations, which require strategic reasoning—an ability to navigate dynamic environments and align long-term goals amidst uncertainty.Existing methods for strategic reasoning face challenges in adaptability, scalability, and transferring strategies to new contexts.To address these issues, we propose explicit policy optimization (*EPO*) for strategic reasoning, featuring an LLM that provides strategies in open-ended action space and can be plugged into arbitrary LLM agents to motivate goal-directed behavior.To improve adaptability and policy transferability, we train the strategic reasoning model via multi-turn reinforcement learning (RL), utilizing process rewards and iterative self-play.Experiments across social and physical domains demonstrate *EPO*’s ability of long-term goal alignment through enhanced strategic reasoning, achieving state-of-the-art performance on social dialogue and web navigation tasks. Our findings reveal various collaborative reasoning mechanisms emergent in *EPO* and its effectiveness in generating novel strategies, underscoring its potential for strategic reasoning in real-world applications. Code and data are available at [https://github.com/lxqpku/EPO](https://github.com/lxqpku/EPO).
%R 10.18653/v1/2025.acl-long.747
%U https://aclanthology.org/2025.acl-long.747/
%U https://doi.org/10.18653/v1/2025.acl-long.747
%P 15371-15396
Markdown (Informal)
[EPO: Explicit Policy Optimization for Strategic Reasoning in LLMs via Reinforcement Learning](https://aclanthology.org/2025.acl-long.747/) (Liu et al., ACL 2025)
ACL
- Xiaoqian Liu, Ke Wang, Yongbin Li, Yuchuan Wu, Wentao Ma, Aobo Kong, Fei Huang, Jianbin Jiao, and Junge Zhang. 2025. EPO: Explicit Policy Optimization for Strategic Reasoning in LLMs via Reinforcement Learning. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 15371–15396, Vienna, Austria. Association for Computational Linguistics.