Receive a weekly summary and discussion of the top papers of the week by leading researchers in the field.

Human-level play in the game of Diplomacy by combining language models with strategic reasoning.

In Science (New York, N.Y.)

Despite much progress in training AI systems to imitate human language, building agents that use language to communicate intentionally with humans in interactive environments remains a major challenge. We introduce Cicero, the first AI agent to achieve human-level performance in Diplomacy, a strategy game involving both cooperation and competition that emphasizes natural language negotiation and tactical coordination between seven players. Cicero integrates a language model with planning and reinforcement learning algorithms by inferring players' beliefs and intentions from its conversations and generating dialogue in pursuit of its plans. Across 40 games of an anonymous online Diplomacy league, Cicero achieved more than double the average score of the human players and ranked in the top 10% of participants who played more than one game.

Bakhtin Anton, Brown Noam, Dinan Emily, Farina Gabriele, Flaherty Colin, Fried Daniel, Goff Andrew, Gray Jonathan, Hu Hengyuan, Jacob Athul Paul, Komeili Mojtaba, Konath Karthik, Kwon Minae, Lerer Adam, Lewis Mike, Miller Alexander H, Mitts Sasha, Renduchintala Adithya, Roller Stephen, Rowe Dirk, Shi Weiyan, Spisak Joe, Wei Alexander, Wu David, Zhang Hugh, Zijlstra Markus

2022-Nov-22