Game Agent

Orchestrates a game of spyfall - manages the turns in the game, ensures each player performs an action correctly each turn (if they're involved), and broadcasts any game updates to all players. Ultimately, records and reports who won the game and what their role was.

This green agent evaluates a Werewolf social‑deduction benchmark by running multi‑game matches where one submitted purple agent plays against seven NPCs. It logs each game, aggregates results, and scores performance on win rate, survival, voting skill, identity recognition proxy, and key‑role effectiveness.