PeopleofSuperintelligence

Researcher

Gabriele Farina

Gabriele Farina is an MIT computer scientist who develops algorithms for strategic decision-making in multi-agent AI. He wrote code for a board-game solver as a teenager, studied automation and control engineering at Politecnico di Milano, and completed a computer science PhD at Carnegie Mellon in 2023. His work spans the NeurIPS 2020 Best Paper on no-regret learning, Meta’s Cicero agent for Diplomacy, and The Consensus Game, an ICLR 2024 Spotlight on language generation; his human-regularized Diplomacy paper also received an ICLR 2023 Outstanding Paper Honorable Mention. Now an assistant professor at MIT, he received the 2025 NSF CAREER Award, and his team beat Stratego’s all-time best player in 2026.

Timeline

  1. 2020

    No-regret learning dynamics

    He grows up in a small town in northern Italy and, at 16, writes code to solve a board game. He studies automation and control engineering at Politecnico di Milano under advisor Nicola Gatti. In 2020, he coauthors “No-Regret Learning Dynamics for Extensive-Form Correlated Equilibrium,” which wins a NeurIPS Best Paper Award for showing no-regret dynamics that converge to extensive-form correlated equilibria.

  2. 2022

    Cicero at Meta

    While completing his doctorate, he works for a year as a research scientist at Meta’s Fundamental AI Research Labs and helps develop Cicero, a human-level Diplomacy agent combining strategic reasoning with natural language. In 2022, he coauthors the Science paper “Human-level play in the game of Diplomacy by combining language models with strategic reasoning.”

  3. 2023

    A PhD and an ICLR honor

    In May 2023, he completes a computer science PhD at Carnegie Mellon under advisor Tuomas Sandholm; his dissertation studies learning and equilibrium computation in imperfect-information games. His ICLR 2023 paper “Mastering the Game of No-Press Diplomacy via Human-Regularized Reinforcement Learning and Planning” receives an Outstanding Paper Honorable Mention.

  4. 2024

    The Consensus Game

    At ICLR in 2024, he coauthors “The Consensus Game: Language Model Generation via Equilibrium Search,” a game-theoretic decoding method that pairs a generator with a discriminator to find a coherent answer. The method improves accuracy across reading comprehension, math, and dialogue tasks.

  5. 2025

    An NSF CAREER Award

    In 2025, he receives the National Science Foundation CAREER Award.

  6. Since September 2023

    Assistant professor at MIT

    In September 2023, he joins MIT as an assistant professor in the Faculty of Artificial Intelligence and Decision-Making in EECS. He is also an assistant professor in EECS and LIDS, affiliated with the Operations Research Center. In May 2026, his team uses new algorithms and training costing less than $10,000 to beat Stratego’s all-time best player, with 15 wins, four draws, and one loss.

  1. Google had the most people shaping AI every year from 2014 to 2025Our estimates of which organizations employed the most people shaping AI from 1961 to 2025, with a year-by-year chart.
  2. The United States employs an estimated 53% of people in our data with a known employment countryOur estimates of where AI careers are concentrated now and how countries’ shares of dated positions changed over time.
  3. 46% of living people in our data with known birth and employment countries work outside their birth countryOur estimate of cross-border careers in AI, from country of birth and the country of each current organization.
  4. More people shaping AI studied at Massachusetts Institute of Technology than at any other institutionOur estimates of where the people shaping AI studied and where their careers led, from education records in cited biographies.

Sources and credits

Photo: We have no published photo of Gabriele Farina yet. Send us a free-licensed photo.

  1. Games people — and machines — play: Untangling strategic reasoning to advance AI computing.mit.edu. Checked 19 October 2026.
  2. Announcing the NeurIPS 2020 award recipients blog.neurips.cc. Checked 19 October 2026.
  3. Gabriele Farina - About me mit.edu. Checked 19 October 2026.
  4. Papers lingo.csail.mit.edu. Checked 19 October 2026.
  5. Gabriele Farina | Carnegie Mellon University Computer Science Department csd.cmu.edu. Checked 19 October 2026.
  6. Using ideas from game theory to improve the reliability of language models | MIT News news.mit.edu. Checked 19 October 2026.
  7. New Faculty (2022-2023) - MIT Schwarzman College of Computing computing.mit.edu. Checked 19 October 2026.