@inproceedings{jia-etal-2024-langsuit,
title = "{L}ang{S}uit{\mbox{$\cdot$}}{E}: Planning, Controlling and Interacting with Large Language Models in Embodied Text Environments",
author = "Jia, Zixia and
Wang, Mengmeng and
Tong, Baichen and
Zhu, Song-Chun and
Zheng, Zilong",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Findings of the Association for Computational Linguistics ACL 2024",
month = aug,
year = "2024",
address = "Bangkok, Thailand and virtual meeting",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-acl.879",
pages = "14778--14814",
abstract = "Recent advances in Large Language Models (LLMs) have shown inspiring achievements in constructing autonomous agents that rely onlanguage descriptions as inputs. However, it remains unclear how well LLMs can function as few-shot or zero-shot embodied agents in dynamic interactive environments. To address this gap, we introduce LangSuit{\mbox{$\cdot$}}E, a versatile and simulation-free testbed featuring 6 representative embodied tasks in textual embodied worlds. Compared with previous LLM-based testbeds, LangSuit{\mbox{$\cdot$}}E (i) offers adaptability to diverse environments without multiple simulation engines, (ii) evaluates agents{'} capacity to develop {``}internalized world knowledge{''} with embodied observations, and (iii) allows easy customization of communication and action strategies. To address the embodiment challenge, we devise a novel chain-of-thought (CoT) schema, EmMem, which summarizes embodied states w.r.t. history information. Comprehensive benchmark results illustrate challenges and insights of embodied planning. LangSuit{\mbox{$\cdot$}}E represents a significant step toward building embodied generalists in the context of language models.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jia-etal-2024-langsuit">
<titleInfo>
<title>LangSuit·E: Planning, Controlling and Interacting with Large Language Models in Embodied Text Environments</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zixia</namePart>
<namePart type="family">Jia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mengmeng</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Baichen</namePart>
<namePart type="family">Tong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Song-Chun</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zilong</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics ACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand and virtual meeting</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recent advances in Large Language Models (LLMs) have shown inspiring achievements in constructing autonomous agents that rely onlanguage descriptions as inputs. However, it remains unclear how well LLMs can function as few-shot or zero-shot embodied agents in dynamic interactive environments. To address this gap, we introduce LangSuit·E, a versatile and simulation-free testbed featuring 6 representative embodied tasks in textual embodied worlds. Compared with previous LLM-based testbeds, LangSuit·E (i) offers adaptability to diverse environments without multiple simulation engines, (ii) evaluates agents’ capacity to develop “internalized world knowledge” with embodied observations, and (iii) allows easy customization of communication and action strategies. To address the embodiment challenge, we devise a novel chain-of-thought (CoT) schema, EmMem, which summarizes embodied states w.r.t. history information. Comprehensive benchmark results illustrate challenges and insights of embodied planning. LangSuit·E represents a significant step toward building embodied generalists in the context of language models.</abstract>
<identifier type="citekey">jia-etal-2024-langsuit</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.879</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>14778</start>
<end>14814</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LangSuit·E: Planning, Controlling and Interacting with Large Language Models in Embodied Text Environments
%A Jia, Zixia
%A Wang, Mengmeng
%A Tong, Baichen
%A Zhu, Song-Chun
%A Zheng, Zilong
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Findings of the Association for Computational Linguistics ACL 2024
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand and virtual meeting
%F jia-etal-2024-langsuit
%X Recent advances in Large Language Models (LLMs) have shown inspiring achievements in constructing autonomous agents that rely onlanguage descriptions as inputs. However, it remains unclear how well LLMs can function as few-shot or zero-shot embodied agents in dynamic interactive environments. To address this gap, we introduce LangSuit·E, a versatile and simulation-free testbed featuring 6 representative embodied tasks in textual embodied worlds. Compared with previous LLM-based testbeds, LangSuit·E (i) offers adaptability to diverse environments without multiple simulation engines, (ii) evaluates agents’ capacity to develop “internalized world knowledge” with embodied observations, and (iii) allows easy customization of communication and action strategies. To address the embodiment challenge, we devise a novel chain-of-thought (CoT) schema, EmMem, which summarizes embodied states w.r.t. history information. Comprehensive benchmark results illustrate challenges and insights of embodied planning. LangSuit·E represents a significant step toward building embodied generalists in the context of language models.
%U https://aclanthology.org/2024.findings-acl.879
%P 14778-14814
Markdown (Informal)
[LangSuit·E: Planning, Controlling and Interacting with Large Language Models in Embodied Text Environments](https://aclanthology.org/2024.findings-acl.879) (Jia et al., Findings 2024)
ACL