2026-08-04T08:24:34Z https://drops.dagstuhl.de/oai

oai:drops-oai.dagstuhl.de:14424 2024-03-06T10:31:31Z ddc:004 open_access

MUAHAH: Taking the Most out of Simple Conversational Agents Llansol, Leonor Santos, João Duarte, Luís Santos, José Gaspar, Mariana Alves, Ana Gonçalo Oliveira, Hugo Coheur, Luísa Dialog systems question answering information retrieval multi-agent Dialog engines based on multi-agent architectures usually select a single agent, deemed to be the most suitable for a given scenario or for responding to a specific request, and disregard the answers from all of the other available agents. In this work, we present a multi-agent plug-and-play architecture that: (i) enables the integration of different agents; (ii) includes a decision maker module, responsible for selecting a suitable answer out of the responses of different agents. As usual, a single agent can be chosen to provide the final answer, but the latter can also be obtained from the responses of several agents, according to a voting scheme. We also describe three case studies in which we test several agents and decision making strategies; and show how new agents and a new decision strategy can be easily plugged in and take advantage of this platform in different ways. Experimentation also confirms that considering several agents contributes to better responses. Schloss Dagstuhl – Leibniz-Zentrum für Informatik Leonor Llansol and João Santos and Luís Duarte and José Santos and Mariana Gaspar and Ana Alves and Hugo Gonçalo Oliveira and Luísa Coheur 2021 Is Part Of OASIcs, Volume 94, 10th Symposium on Languages, Applications and Technologies (SLATE 2021) InProceedings Text doc-type:ResearchArticle publishedVersion application/pdf doi:10.4230/OASIcs.SLATE.2021.7 urn:nbn:de:0030-drops-144248 https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.SLATE.2021.7 eng https://creativecommons.org/licenses/by/4.0/legalcode