@inproceedings{zhang-etal-2024-pddlego,
title = "{PDDLEGO}: Iterative Planning in Textual Environments",
author = "Zhang, Li and
Jansen, Peter and
Zhang, Tianyi and
Clark, Peter and
Callison-Burch, Chris and
Tandon, Niket",
editor = "Bollegala, Danushka and
Shwartz, Vered",
booktitle = "Proceedings of the 13th Joint Conference on Lexical and Computational Semantics (*SEM 2024)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "http://aclanthology.org/2024.starsem-1.17/",
doi = "10.18653/v1/2024.starsem-1.17",
pages = "212--221",
abstract = "Planning in textual environments have been shown to be a long-standing challenge even for current models. A recent, promising line of work uses LLMs to generate a formal representation of the environment that can be solved by a symbolic planner. However, existing methods rely on a fully-observed environment where all entity states are initially known, so a one-off representation can be constructed, leading to a complete plan. In contrast, we tackle partially-observed environments where there is initially no sufficient information to plan for the end-goal. We propose PDDLEGO that iteratively construct a planning representation that can lead to a partial plan for a given sub-goal. By accomplishing the sub-goal, more information is acquired to augment the representation, eventually achieving the end-goal. We show that plans produced by few-shot PDDLEGO are 43{\%} more efficient than generating plans end-to-end on the Coin Collector simulation, with strong performance (98{\%}) on the more complex Cooking World simulation where end-to-end LLMs fail to generate coherent plans (4{\%})."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2024-pddlego">
<titleInfo>
<title>PDDLEGO: Iterative Planning in Textual Environments</title>
</titleInfo>
<name type="personal">
<namePart type="given">Li</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peter</namePart>
<namePart type="family">Jansen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tianyi</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peter</namePart>
<namePart type="family">Clark</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">Callison-Burch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Niket</namePart>
<namePart type="family">Tandon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 13th Joint Conference on Lexical and Computational Semantics (*SEM 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Danushka</namePart>
<namePart type="family">Bollegala</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vered</namePart>
<namePart type="family">Shwartz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Planning in textual environments have been shown to be a long-standing challenge even for current models. A recent, promising line of work uses LLMs to generate a formal representation of the environment that can be solved by a symbolic planner. However, existing methods rely on a fully-observed environment where all entity states are initially known, so a one-off representation can be constructed, leading to a complete plan. In contrast, we tackle partially-observed environments where there is initially no sufficient information to plan for the end-goal. We propose PDDLEGO that iteratively construct a planning representation that can lead to a partial plan for a given sub-goal. By accomplishing the sub-goal, more information is acquired to augment the representation, eventually achieving the end-goal. We show that plans produced by few-shot PDDLEGO are 43% more efficient than generating plans end-to-end on the Coin Collector simulation, with strong performance (98%) on the more complex Cooking World simulation where end-to-end LLMs fail to generate coherent plans (4%).</abstract>
<identifier type="citekey">zhang-etal-2024-pddlego</identifier>
<identifier type="doi">10.18653/v1/2024.starsem-1.17</identifier>
<location>
<url>http://aclanthology.org/2024.starsem-1.17/</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>212</start>
<end>221</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PDDLEGO: Iterative Planning in Textual Environments
%A Zhang, Li
%A Jansen, Peter
%A Zhang, Tianyi
%A Clark, Peter
%A Callison-Burch, Chris
%A Tandon, Niket
%Y Bollegala, Danushka
%Y Shwartz, Vered
%S Proceedings of the 13th Joint Conference on Lexical and Computational Semantics (*SEM 2024)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F zhang-etal-2024-pddlego
%X Planning in textual environments have been shown to be a long-standing challenge even for current models. A recent, promising line of work uses LLMs to generate a formal representation of the environment that can be solved by a symbolic planner. However, existing methods rely on a fully-observed environment where all entity states are initially known, so a one-off representation can be constructed, leading to a complete plan. In contrast, we tackle partially-observed environments where there is initially no sufficient information to plan for the end-goal. We propose PDDLEGO that iteratively construct a planning representation that can lead to a partial plan for a given sub-goal. By accomplishing the sub-goal, more information is acquired to augment the representation, eventually achieving the end-goal. We show that plans produced by few-shot PDDLEGO are 43% more efficient than generating plans end-to-end on the Coin Collector simulation, with strong performance (98%) on the more complex Cooking World simulation where end-to-end LLMs fail to generate coherent plans (4%).
%R 10.18653/v1/2024.starsem-1.17
%U http://aclanthology.org/2024.starsem-1.17/
%U http://doi.org/10.18653/v1/2024.starsem-1.17
%P 212-221
Markdown (Informal)
[PDDLEGO: Iterative Planning in Textual Environments](http://aclanthology.org/2024.starsem-1.17/) (Zhang et al., *SEM 2024)
ACL
- Li Zhang, Peter Jansen, Tianyi Zhang, Peter Clark, Chris Callison-Burch, and Niket Tandon. 2024. PDDLEGO: Iterative Planning in Textual Environments. In Proceedings of the 13th Joint Conference on Lexical and Computational Semantics (*SEM 2024), pages 212–221, Mexico City, Mexico. Association for Computational Linguistics.