Coalition Formation Demo

Given agents with differing policy positions, this algorithm finds a majority coalition that agrees on an AI-generated compromise. Read the paper

How it works: Each agent has an ideal policy sentence. Starting from a status quo, the algorithm iterates: (1) agents vote yes if the current proposal is closer to their ideal than the status quo (measured by cosine dissimilarity of sentence embeddings); (2) if a majority coalition is reached, the proposal wins; (3) otherwise, two agents are selected and an LLM generates a compromise sentence as the next proposal. The algorithm guarantees that every agent in the winning coalition genuinely prefers the result over the status quo.

Status Quo

The current policy that agents want to improve on.

Agents

Each agent has a name and an ideal policy sentence. Sentences of 5–15 words work best.

Advanced Options