Agent-Mediated Social Choice
This addresses the challenge of implementing direct democracy for citizens in complex modern societies, but it is incremental as it builds on existing theoretical research.
The paper tackles the problem of direct democracy being impractical due to the cognitive burden on voters in large societies by proposing voting avatars as autonomous agents that debate and vote on behalf of citizens, drawing on AI techniques like multiagent systems and computational social choice.
Direct democracy is often proposed as a possible solution to the 21st-century problems of democracy. However, this suggestion clashes with the size and complexity of 21st-century societies, entailing an excessive cognitive burden on voters, who would have to submit informed opinions on an excessive number of issues. In this paper I argue for the development of voting avatars, autonomous agents debating and voting on behalf of each citizen. Theoretical research from artificial intelligence, and in particular multiagent systems and computational social choice, proposes 21st-century techniques for this purpose, from the compact representation of a voter's preferences and values, to the development of voting procedures for autonomous agents use only.