Studying Consensus and Disagreement during Problem Solving in Teams through Learning and Response Generation Agents Model

Alex Doboli and Daniel-Ioan Curiac ()
Additional contact information
Alex Doboli: Department of Electrical and Computer Engineering, Stony Brook University, Stony Brook, NY 11794-2350, USA
Daniel-Ioan Curiac: Department of Automation and Applied Informatics, Politehnica University of Timisoara, V. Parvan 2, 300223 Timisoara, Romania

Mathematics, 2023, vol. 11, issue 12, 1-28

Abstract: Understanding the process of reaching consensus or disagreement between the members of a team is critical in many situations. Consensus and disagreement can refer to various aspects, such as requirements that are collectively perceived to be important, shared goals, and solutions that are jointly considered to be realistic and effective. Getting insight on how the end result of the interaction process is influenced by parameters such as the similarity of the participants’ experience and behavior (e.g., their available concepts, the produced responses and their utility, the preferred response generation method, and so on) is important for optimizing team performance and for devising novel applications, i.e., systems for tutoring or self-improvement and smart human computer interfaces. However, understanding the process of reaching consensus or disagreement in teams raises a number of challenges as participants interact with each other through verbal communications that express new ideas created based on their experience, goals, and input from other participants. Social and emotional cues during interaction are important too. This paper presents a new model, called Learning and Response Generating Agents, for studying the interaction process during problem solving in small teams. As compared to similar work, the model, grounded in work in psychology and sociology, studies consensus and disagreement formation when agents interact with each other through symbolic, dynamically-produced responses with clauses of different types, ambiguity, multiple abstraction levels, and associated emotional intensity and utility.

Keywords: agent models; problem solving; symbolic representations; optimized teams (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2023
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/11/12/2602/pdf (application/pdf)
https://www.mdpi.com/2227-7390/11/12/2602/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:11:y:2023:i:12:p:2602-:d:1165696

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().