GenGPT: A Systematic Way to Generate Synthetic Goal-Plan Trees

Yuan Yao; Di Wu

doi:10.1007/978-3-030-97457-2_21

GenGPT: A Systematic Way to Generate Synthetic Goal-Plan Trees

Yuan Yao, Di Wu

School of Computer Science

Research output: Chapter in Book/Conference proceeding › Book Chapter › peer-review

Abstract

Deciding “what to do next” is a key problem for BDI agents with multiple goals, which is termed the intention progression problem (IPP). A number of approaches to solving the IPP have been proposed in the literature, however, their evaluations are all taken in different forms. The lack of standard benchmarks and testbeds for evaluating the IPP makes it difficult for researchers to contribute to this topic. To foster research around the IPP and BDI agents, this paper proposes a way to generate test cases in the form of goal-plan trees which can be used to represent the agent’s intentions in various agent languages and platforms.

Original language	English
Title of host publication	Engineering Multi-Agent Systems - 9th International Workshop, EMAS 2021, Revised Selected Papers
Editors	Natasha Alechina, Matteo Baldoni, Brian Logan
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	373-380
Number of pages	8
Volume	13190
ISBN (Print)	9783030974565
DOIs	https://doi.org/10.1007/978-3-030-97457-2_21
Publication status	Published - 2022
Event	9th International Workshop on Engineering Multi-Agent Systems, EMAS 2021 - London, United Kingdom Duration: 3 May 2021 → 4 May 2021

Publication series

Name	Lecture Notes in Artificial Intelligence

Conference

Conference	9th International Workshop on Engineering Multi-Agent Systems, EMAS 2021
Country/Territory	United Kingdom
City	London
Period	3/05/21 → 4/05/21

Keywords

BDI Agents
Goal-plan tree generator
Intention progression problem

ASJC Scopus subject areas

Theoretical Computer Science
General Computer Science

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1007/978-3-030-97457-2_21

Cite this

Yao, Y., & Wu, D. (2022). GenGPT: A Systematic Way to Generate Synthetic Goal-Plan Trees. In N. Alechina, M. Baldoni, & B. Logan (Eds.), Engineering Multi-Agent Systems - 9th International Workshop, EMAS 2021, Revised Selected Papers (Vol. 13190, pp. 373-380). (Lecture Notes in Artificial Intelligence). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-030-97457-2_21

@inbook{55d1649c13b9484287eebef4ed9a2ffe,

title = "GenGPT: A Systematic Way to Generate Synthetic Goal-Plan Trees",

abstract = "Deciding “what to do next” is a key problem for BDI agents with multiple goals, which is termed the intention progression problem (IPP). A number of approaches to solving the IPP have been proposed in the literature, however, their evaluations are all taken in different forms. The lack of standard benchmarks and testbeds for evaluating the IPP makes it difficult for researchers to contribute to this topic. To foster research around the IPP and BDI agents, this paper proposes a way to generate test cases in the form of goal-plan trees which can be used to represent the agent{\textquoteright}s intentions in various agent languages and platforms.",

keywords = "BDI Agents, Goal-plan tree generator, Intention progression problem",

author = "Yuan Yao and Di Wu",

note = "Publisher Copyright: {\textcopyright} 2022, Springer Nature Switzerland AG.; 9th International Workshop on Engineering Multi-Agent Systems, EMAS 2021 ; Conference date: 03-05-2021 Through 04-05-2021",

year = "2022",

doi = "10.1007/978-3-030-97457-2_21",

language = "English",

isbn = "9783030974565",

volume = "13190",

series = "Lecture Notes in Artificial Intelligence",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "373--380",

editor = "Natasha Alechina and Matteo Baldoni and Brian Logan",

booktitle = "Engineering Multi-Agent Systems - 9th International Workshop, EMAS 2021, Revised Selected Papers",

address = "Germany",

}

Yao, Y & Wu, D 2022, GenGPT: A Systematic Way to Generate Synthetic Goal-Plan Trees. in N Alechina, M Baldoni & B Logan (eds), Engineering Multi-Agent Systems - 9th International Workshop, EMAS 2021, Revised Selected Papers. vol. 13190, Lecture Notes in Artificial Intelligence, Springer Science and Business Media Deutschland GmbH, pp. 373-380, 9th International Workshop on Engineering Multi-Agent Systems, EMAS 2021, London, United Kingdom, 3/05/21. https://doi.org/10.1007/978-3-030-97457-2_21

GenGPT: A Systematic Way to Generate Synthetic Goal-Plan Trees. / Yao, Yuan; Wu, Di.
Engineering Multi-Agent Systems - 9th International Workshop, EMAS 2021, Revised Selected Papers. ed. / Natasha Alechina; Matteo Baldoni; Brian Logan. Vol. 13190 Springer Science and Business Media Deutschland GmbH, 2022. p. 373-380 (Lecture Notes in Artificial Intelligence).

Research output: Chapter in Book/Conference proceeding › Book Chapter › peer-review

TY - CHAP

T1 - GenGPT

T2 - 9th International Workshop on Engineering Multi-Agent Systems, EMAS 2021

AU - Yao, Yuan

AU - Wu, Di

PY - 2022

Y1 - 2022

N2 - Deciding “what to do next” is a key problem for BDI agents with multiple goals, which is termed the intention progression problem (IPP). A number of approaches to solving the IPP have been proposed in the literature, however, their evaluations are all taken in different forms. The lack of standard benchmarks and testbeds for evaluating the IPP makes it difficult for researchers to contribute to this topic. To foster research around the IPP and BDI agents, this paper proposes a way to generate test cases in the form of goal-plan trees which can be used to represent the agent’s intentions in various agent languages and platforms.

AB - Deciding “what to do next” is a key problem for BDI agents with multiple goals, which is termed the intention progression problem (IPP). A number of approaches to solving the IPP have been proposed in the literature, however, their evaluations are all taken in different forms. The lack of standard benchmarks and testbeds for evaluating the IPP makes it difficult for researchers to contribute to this topic. To foster research around the IPP and BDI agents, this paper proposes a way to generate test cases in the form of goal-plan trees which can be used to represent the agent’s intentions in various agent languages and platforms.

KW - BDI Agents

KW - Goal-plan tree generator

KW - Intention progression problem

UR - http://www.scopus.com/inward/record.url?scp=85127020649&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-97457-2_21

DO - 10.1007/978-3-030-97457-2_21

M3 - Book Chapter

AN - SCOPUS:85127020649

SN - 9783030974565

VL - 13190

T3 - Lecture Notes in Artificial Intelligence

SP - 373

EP - 380

BT - Engineering Multi-Agent Systems - 9th International Workshop, EMAS 2021, Revised Selected Papers

A2 - Alechina, Natasha

A2 - Baldoni, Matteo

A2 - Logan, Brian

PB - Springer Science and Business Media Deutschland GmbH

Y2 - 3 May 2021 through 4 May 2021

ER -

Yao Y, Wu D. GenGPT: A Systematic Way to Generate Synthetic Goal-Plan Trees. In Alechina N, Baldoni M, Logan B, editors, Engineering Multi-Agent Systems - 9th International Workshop, EMAS 2021, Revised Selected Papers. Vol. 13190. Springer Science and Business Media Deutschland GmbH. 2022. p. 373-380. (Lecture Notes in Artificial Intelligence). doi: 10.1007/978-3-030-97457-2_21

GenGPT: A Systematic Way to Generate Synthetic Goal-Plan Trees

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this