Game theory & mechanism design

Strategic interaction, and the design of rules under which honest, cooperative behavior is the rational choice.

Corresponding Researcher
Andrew Koh
Relevant for
8 cells in the AGI institutions grid
Contact
mechanism-design@agi-institutions.org

Selected papers

1
  1. Mechanism Design for Alignment and Control
    Dirk Bergemann, Andrew Koh, Stephen Morris2026 · Preprint

    Extends mechanism design to AI agents whose preferences and capabilities are unknown, characterizing when they can be made both honest and obedient on our behalf.

Work in the field

17
  1. Mechanism Design Is Not Enough: Prosocial Agents for Cooperative AI
    Xuanqiang Angelo Huang, Charlie Tharas, Samuele Marro et al.2026 · ICML · Workshop paper
  2. Racing to Ruin
    Drew Fudenberg, Andrew Koh2026 · Preprint
  3. Emergent Alignment via Competition
    Natalie Collina, Surbhi Goel, Aaron Roth et al.2025 · ICML · Peer-reviewed
  4. Streamlining Equal Shares
    Sonja Kraiczy, Isaac Robinson, Edith Elkind2025 · COMSOC · Workshop paper
  5. Cooperation and Control in Delegation Games
    Oliver Sourbut, Lewis Hammond, Harriet Wood2024 · IJCAI · Peer-reviewed
  6. Foundations of Cooperative AI
    Vincent Conitzer, Caspar Oesterheld2024 · AAAI · Peer-reviewed
  7. Representative Social Choice: From Learning Theory to AI Alignment
    Tianyi Qiu2024 · Journal of Artificial Intelligence Research · Peer-reviewed
  8. Robust Technology Regulation
    Andrew Koh, Sivakorn Sanguanmoo2024 · EC · Peer-reviewed
  9. Social Choice Should Guide AI Alignment in Dealing with Diverse Human Feedback
    Vincent Conitzer, Rachel Freedman, Jobst Heitzig et al.2024 · ICML · Peer-reviewed
  10. Steering Language Models with Game-Theoretic Solvers
    Ian Gemp, Roma Patel, Yoram Bachrach et al.2024 · ICML · Workshop paper
  11. Generative Social Choice
    Sara Fish, Paul Gölz, David C. Parkes et al.2023 · EC · Peer-reviewed
  12. Formal Contracts Mitigate Social Dilemmas in Multi-Agent RL
    Andreas A. Haupt, Phillip J.K. Christoffersen, Mehul Damani et al.2022 · AAMAS · Peer-reviewed
  13. Human-centred mechanism design with Democratic AI
    Raphael Koster, Jan Balaguer, Andrea Tacchetti et al.2022 · Nature Human Behaviour · Peer-reviewed
  14. Split Cycle: A New Condorcet Consistent Voting Method Independent of Clones and Immune to Spoilers
    Wesley H. Holliday, Eric Pacuit2020 · Public Choice · Peer-reviewed
  15. Aggregating extended preferences
    Hilary Greaves, Harvey Lederman2017 · Philosophical Studies · Peer-reviewed
  16. Ethics and market design
    Shengwu Li2017 · Oxford Review of Economic Policy · Peer-reviewed
  17. Obviously Strategy-Proof Mechanisms
    Shengwu Li2017 · American Economic Review · Peer-reviewed

Background work

4

Older work the field builds on, often from outside it.

  1. Non-Cooperative Games
    John Nash1951 · Annals of Mathematics
  2. Social Choice and Individual Values
    Kenneth Arrow1951 · Book
  3. Collective Choice and Social Welfare
    Amartya Sen1970 · Book
  4. The Economist as Engineer
    Alvin Roth2002 · Econometrica