@inproceedings{rezaei-etal-2025-interactive,
title = "Interactive Text Games: Lookahead Is All You Need!",
author = "Rezaei, Hosein and
Walker, James Alfred and
Soboczenski, Frank",
editor = "Zhao, Jin and
Wang, Mingyang and
Liu, Zhu",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-srw.41/",
doi = "10.18653/v1/2025.acl-srw.41",
pages = "657--664",
ISBN = "979-8-89176-254-1",
abstract = "The cross-modal grounding of LLMs has recently garnered significant attention, while grounding them in textual interactions has been less explored. As the first of its kind, the GLAM framework utilises LLMs as agents in interactive text-based games to investigate their grounding capabilities. However, it faces the challenge of low computational efficiency, which hinders further experiments. This paper proposes the use of Lookahead models for action selection, demonstrating through empirical results that the approach can substantially improve training speed, achieving performance gains relative to the size of the action space."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rezaei-etal-2025-interactive">
<titleInfo>
<title>Interactive Text Games: Lookahead Is All You Need!</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hosein</namePart>
<namePart type="family">Rezaei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="given">Alfred</namePart>
<namePart type="family">Walker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frank</namePart>
<namePart type="family">Soboczenski</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 4: Student Research Workshop)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jin</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mingyang</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhu</namePart>
<namePart type="family">Liu</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">979-8-89176-254-1</identifier>
</relatedItem>
<abstract>The cross-modal grounding of LLMs has recently garnered significant attention, while grounding them in textual interactions has been less explored. As the first of its kind, the GLAM framework utilises LLMs as agents in interactive text-based games to investigate their grounding capabilities. However, it faces the challenge of low computational efficiency, which hinders further experiments. This paper proposes the use of Lookahead models for action selection, demonstrating through empirical results that the approach can substantially improve training speed, achieving performance gains relative to the size of the action space.</abstract>
<identifier type="citekey">rezaei-etal-2025-interactive</identifier>
<identifier type="doi">10.18653/v1/2025.acl-srw.41</identifier>
<location>
<url>https://aclanthology.org/2025.acl-srw.41/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>657</start>
<end>664</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Interactive Text Games: Lookahead Is All You Need!
%A Rezaei, Hosein
%A Walker, James Alfred
%A Soboczenski, Frank
%Y Zhao, Jin
%Y Wang, Mingyang
%Y Liu, Zhu
%S Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-254-1
%F rezaei-etal-2025-interactive
%X The cross-modal grounding of LLMs has recently garnered significant attention, while grounding them in textual interactions has been less explored. As the first of its kind, the GLAM framework utilises LLMs as agents in interactive text-based games to investigate their grounding capabilities. However, it faces the challenge of low computational efficiency, which hinders further experiments. This paper proposes the use of Lookahead models for action selection, demonstrating through empirical results that the approach can substantially improve training speed, achieving performance gains relative to the size of the action space.
%R 10.18653/v1/2025.acl-srw.41
%U https://aclanthology.org/2025.acl-srw.41/
%U https://doi.org/10.18653/v1/2025.acl-srw.41
%P 657-664
Markdown (Informal)
[Interactive Text Games: Lookahead Is All You Need!](https://aclanthology.org/2025.acl-srw.41/) (Rezaei et al., ACL 2025)
ACL
- Hosein Rezaei, James Alfred Walker, and Frank Soboczenski. 2025. Interactive Text Games: Lookahead Is All You Need!. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop), pages 657–664, Vienna, Austria. Association for Computational Linguistics.