@inproceedings{li-etal-2026-word,
title = "From Word to World: Can Large Language Models be Implicit Text-based World Models?",
author = "Li, Yixia and
Wang, Hongru and
Qiu, Jiahao and
Yin, Zhenfei and
Zhang, Dongdong and
Qian, Cheng and
Li, Zeping and
Ma, Xiaoteng and
Chen, Guanhua and
Ji, Heng",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-long.366/",
pages = "8084--8111",
ISBN = "979-8-89176-390-6",
abstract = "Agentic learning increasingly hinges on interaction, yet real-world experience is expensive, limited, and often irreversible at inference time. World models promise to mitigate these limitations, but it remains unclear whether large language models can actually serve as reliable world models, and deliver concrete benefits to downstream agents. We investigate these questions in text-based environments, a controlled testbed that reframes language modeling as next-state prediction under interaction. We propose a three-level framework to evaluate LLM-based world models: (i) fidelity and consistency, (ii) scalability and robustness, and (iii) agent utility. Across five representative environments, we show that sufficiently trained world models capture coherent environment dynamics, scale predictably with data and model capacity, and unlock tangible agent improvements{---}for example, action verification boosts GPT-4o by 5.5{\%} on WebShop, and warm-started RL achieves a 15{\%} gain on SciWorld. Crucially, these benefits hinge on behavioral coverage and environment complexity, sharply characterizing when world modeling meaningfully advances agent learning."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2026-word">
<titleInfo>
<title>From Word to World: Can Large Language Models be Implicit Text-based World Models?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yixia</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongru</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiahao</namePart>
<namePart type="family">Qiu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhenfei</namePart>
<namePart type="family">Yin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dongdong</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cheng</namePart>
<namePart type="family">Qian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zeping</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaoteng</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guanhua</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</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>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</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">979-8-89176-390-6</identifier>
</relatedItem>
<abstract>Agentic learning increasingly hinges on interaction, yet real-world experience is expensive, limited, and often irreversible at inference time. World models promise to mitigate these limitations, but it remains unclear whether large language models can actually serve as reliable world models, and deliver concrete benefits to downstream agents. We investigate these questions in text-based environments, a controlled testbed that reframes language modeling as next-state prediction under interaction. We propose a three-level framework to evaluate LLM-based world models: (i) fidelity and consistency, (ii) scalability and robustness, and (iii) agent utility. Across five representative environments, we show that sufficiently trained world models capture coherent environment dynamics, scale predictably with data and model capacity, and unlock tangible agent improvements—for example, action verification boosts GPT-4o by 5.5% on WebShop, and warm-started RL achieves a 15% gain on SciWorld. Crucially, these benefits hinge on behavioral coverage and environment complexity, sharply characterizing when world modeling meaningfully advances agent learning.</abstract>
<identifier type="citekey">li-etal-2026-word</identifier>
<location>
<url>https://aclanthology.org/2026.acl-long.366/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>8084</start>
<end>8111</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T From Word to World: Can Large Language Models be Implicit Text-based World Models?
%A Li, Yixia
%A Wang, Hongru
%A Qiu, Jiahao
%A Yin, Zhenfei
%A Zhang, Dongdong
%A Qian, Cheng
%A Li, Zeping
%A Ma, Xiaoteng
%A Chen, Guanhua
%A Ji, Heng
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-390-6
%F li-etal-2026-word
%X Agentic learning increasingly hinges on interaction, yet real-world experience is expensive, limited, and often irreversible at inference time. World models promise to mitigate these limitations, but it remains unclear whether large language models can actually serve as reliable world models, and deliver concrete benefits to downstream agents. We investigate these questions in text-based environments, a controlled testbed that reframes language modeling as next-state prediction under interaction. We propose a three-level framework to evaluate LLM-based world models: (i) fidelity and consistency, (ii) scalability and robustness, and (iii) agent utility. Across five representative environments, we show that sufficiently trained world models capture coherent environment dynamics, scale predictably with data and model capacity, and unlock tangible agent improvements—for example, action verification boosts GPT-4o by 5.5% on WebShop, and warm-started RL achieves a 15% gain on SciWorld. Crucially, these benefits hinge on behavioral coverage and environment complexity, sharply characterizing when world modeling meaningfully advances agent learning.
%U https://aclanthology.org/2026.acl-long.366/
%P 8084-8111
Markdown (Informal)
[From Word to World: Can Large Language Models be Implicit Text-based World Models?](https://aclanthology.org/2026.acl-long.366/) (Li et al., ACL 2026)
ACL
- Yixia Li, Hongru Wang, Jiahao Qiu, Zhenfei Yin, Dongdong Zhang, Cheng Qian, Zeping Li, Xiaoteng Ma, Guanhua Chen, and Heng Ji. 2026. From Word to World: Can Large Language Models be Implicit Text-based World Models?. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 8084–8111, San Diego, California, United States. Association for Computational Linguistics.