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

Yuan Yao, Di Wu

Research output: Chapter in Book/Conference proceedingBook Chapterpeer-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 languageEnglish
Title of host publicationEngineering Multi-Agent Systems - 9th International Workshop, EMAS 2021, Revised Selected Papers
EditorsNatasha Alechina, Matteo Baldoni, Brian Logan
PublisherSpringer Science and Business Media Deutschland GmbH
Pages373-380
Number of pages8
Volume13190
ISBN (Print)9783030974565
DOIs
Publication statusPublished - 2022
Event9th International Workshop on Engineering Multi-Agent Systems, EMAS 2021 - London, United Kingdom
Duration: 3 May 20214 May 2021

Publication series

NameLecture Notes in Artificial Intelligence

Conference

Conference9th International Workshop on Engineering Multi-Agent Systems, EMAS 2021
Country/TerritoryUnited Kingdom
CityLondon
Period3/05/214/05/21

Keywords

  • BDI Agents
  • Goal-plan tree generator
  • Intention progression problem

ASJC Scopus subject areas

  • Theoretical Computer Science
  • Computer Science (all)

Fingerprint

Dive into the research topics of 'GenGPT: A Systematic Way to Generate Synthetic Goal-Plan Trees'. Together they form a unique fingerprint.

Cite this