Questions as cognitive filters

TL;DR

This paper introduces a formal logico-algebraic framework for modeling decision-making in multi-agent systems, focusing on how agents' cognitive stances influence deliberation and outcomes.

Contribution

It develops a novel formal structure for representing interrogative agendas and their interactions, advancing understanding of decision processes in multi-agent settings.

Findings

Characterizes relevant interrogative agendas using lattice substructures.

Models agent interactions with a two-sorted logico-algebraic structure.

Analyzes which interaction conditions are definable within the framework.

Abstract

In this paper, we develop a logico-algebraic framework for modeling decision-making through deliberation in multi-agent settings. The central concept in this framework is that of interrogative agendas, which represent the cognitive stances of agents regarding which features should be considered relevant in the final decision. We formalize an agent's interrogative agenda as an equivalence relation that identifies outcomes differing only in aspects the agent deems irrelevant. Moreover, we characterize the sublattices of the resulting lattice that correspond to relevant interrogative agendas for deliberation scenarios governed by different ``winning rules." We then introduce a two-sorted logico-algebraic structure-comprising the lattice of relevant interrogative agendas and the Boolean algebras of agent coalitions-to model the interaction between agents and agendas during deliberation. Finally, we discuss which interaction conditions can and cannot be defined within this framework.