I. Gemp

Most-cited papers

1. Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities

   Gheorghe Comanici, E. Bieber, Mike Schaekermann, Ice Pasupat +496 more

   2025arXiv.org4,452 citations

   Semantic Scholar

   Save

2. Social Diversity and Social Preferences in Mixed-Motive Reinforcement Learning

   Kevin R. McKee, I. Gemp, B. McWilliams, Edgar A. Duéñez-Guzmán +2 more

   2020Adaptive Agents and Multi-Agent Systems108 citations Open access

   Semantic Scholar

   Save

3. EigenGame: PCA as a Nash Equilibrium

   I. Gemp, B. McWilliams, Claire Vernade, T. Graepel

   2020International Conference on Learning Representations60 citations

   Semantic Scholar

   Save

4. Negotiation and honesty in artificial intelligence methods for the board game of Diplomacy

   János Kramár, Tom Eccles, I. Gemp, Andrea Tacchetti +4 more

   2022Nature Communications59 citations Open access

   Semantic Scholar

   Save

5. Learning to Play No-Press Diplomacy with Best Response Policy Iteration

   Thomas W. Anthony, Tom Eccles, Andrea Tacchetti, J'anos Kram'ar +10 more

   2020Neural Information Processing Systems50 citations

   Semantic Scholar

   Save

6. Steering Language Models with Game-Theoretic Solvers

   I. Gemp, Roma Patel, Yoram Bachrach, Marc Lanctot +5 more

   202445 citations

   Semantic Scholar

   Save

7. Feature Likelihood Divergence: Evaluating the Generalization of Generative Models Using Samples

   Yoram Bachrach, Joey Bose, I. Gemp, G. Gidel +2 more

   2023Advances in Neural Information Processing Systems 3635 citations Open access

   Semantic Scholar

   Save

8. Code World Models for General Game Playing

   Wolfgang Lehrach, Daniel Hennes, Miguel Lázaro-Gredilla, Xinghua Lou +12 more

   2025arXiv.org31 citations

   Semantic Scholar

   Save

9. Sample-based Approximation of Nash in Large Many-Player Games via Gradient Descent

   I. Gemp, Rahul Savani, Marc Lanctot, Yoram Bachrach +5 more

   2021Adaptive Agents and Multi-Agent Systems26 citations

   Semantic Scholar

   Save

10. D3C: Reducing the Price of Anarchy in Multi-Agent Learning

    I. Gemp, Kevin R. McKee, Richard Everett, Edgar A. Duéñez-Guzmán +3 more

    2020Adaptive Agents and Multi-Agent Systems24 citations

    Semantic Scholar

    Save

11. Turbocharging Solution Concepts: Solving NEs, CEs and CCEs with Neural Equilibrium Solvers

    Luke Marris, I. Gemp, Thomas W. Anthony, Andrea Tacchetti +2 more

    2022Neural Information Processing Systems22 citations Open access

    Semantic Scholar

    Save

12. Game-theoretic Vocabulary Selection via the Shapley Value and Banzhaf Index

    Roma Patel, M. Garnelo, I. Gemp, Chris Dyer +1 more

    2021North American Chapter of the Association for Computational Linguistics21 citations Open access

    Semantic Scholar

    Save

13. Approximating Nash Equilibria in Normal-Form Games via Stochastic Optimization

    I. Gemp, Luke Marris, G. Piliouras

    2023International Conference on Learning Representations18 citations Open access

    Semantic Scholar

    Save

14. Combining Tree-Search, Generative Models, and Nash Bargaining Concepts in Game-Theoretic Reinforcement Learning

    Zun Li, Marc Lanctot, Kevin R. McKee, Luke Marris +6 more

    2023International Joint Conference on Artificial Intelligence16 citations Open access

    Semantic Scholar

    Save

15. EigenGame Unloaded: When playing games is better than optimizing

    I. Gemp, B. McWilliams, Claire Vernade, T. Graepel

    2021International Conference on Learning Representations16 citations

    Semantic Scholar

    Save

16. Smooth markets: A basic mechanism for organizing gradient-based learners

    David Balduzzi, W. Czarnecki, Thomas W. Anthony, I. Gemp +4 more

    2020International Conference on Learning Representations15 citations

    Semantic Scholar

    Save

17. Re-evaluating Open-ended Evaluation of Large Language Models

    Siqi Liu, I. Gemp, Luke Marris, Georgios Piliouras +2 more

    2025International Conference on Learning Representations12 citations

    Semantic Scholar

    Save

18. Game of Thoughts: Iterative Reasoning in Game-Theoretic Domains with Large Language Models

    Benjamin Kempinski, I. Gemp, Kate Larson, Marc Lanctot +2 more

    2025Adaptive Agents and Multi-Agent Systems12 citations

    Semantic Scholar

    Save

19. Designing all-pay auctions using deep learning and multi-agent simulation

    I. Gemp, Thomas W. Anthony, János Kramár, Tom Eccles +2 more

    2022Scientific Reports11 citations Open access

    Semantic Scholar

    Save

20. Generative Adversarial Equilibrium Solvers

    Denizalp Goktas, D. Parkes, I. Gemp, Luke Marris +4 more

    2023International Conference on Learning Representations10 citations Open access

    Semantic Scholar

    Save

21. Soft Condorcet Optimization for Ranking of General Agents

    Marc Lanctot, Kate Larson, Michael Kaisers, Quentin Berthet +6 more

    2024Adaptive Agents and Multi-Agent Systems9 citations

    Semantic Scholar

    Save

22. Equilibrium-Invariant Embedding, Metric Space, and Fundamental Set of 2×2 Normal-Form Games

    Luke Marris, I. Gemp, G. Piliouras

    2023arXiv.org8 citations Open access

    Semantic Scholar

    Save

23. Charting the Shapes of Stories with Game Theory

    C. Daskalakis, I. Gemp, Yan-Chen Jiang, R. P. Leme +2 more

    2024arXiv.org7 citations

    Semantic Scholar

    Save

24. Deviation Ratings: A General, Clone-Invariant Rating Method

    Luke Marris, Siqi Liu, I. Gemp, Georgios Piliouras +1 more

    2025arXiv.org6 citations

    Semantic Scholar

    Save

25. Approximating the Core via Iterative Coalition Sampling

    I. Gemp, Marc Lanctot, Luke Marris, Yiran Mao +10 more

    2024Adaptive Agents and Multi-Agent Systems6 citations

    Semantic Scholar

    Save

26. Convex Markov Games: A New Frontier for Multi-Agent Reinforcement Learning

    I. Gemp, Andreas A. Haupt, Luke Marris, Siqi Liu +1 more

    2024International Conference on Machine Learning6 citations

    Semantic Scholar

    Save

27. Solving Zero-Sum Convex Markov Games

    Fivos Kalogiannis, Emmanouil-Vasileios Vlatakis-Gkaragkounis, I. Gemp, Georgios Piliouras

    2025International Conference on Machine Learning5 citations

    Semantic Scholar

    Save

28. Auto-Aligning Multiagent Incentives with Global Objectives

    Minae Kwon, J. Agapiou, Edgar A. Duéñez-Guzmán, R. Élie +3 more

    20235 citations

    Semantic Scholar

    Save

29. Search-Improved Game-Theoretic Multiagent Reinforcement Learning in General and Negotiation Games

    Zun Li, Marc Lanctot, Kevin R. McKee, Luke Marris +6 more

    2023Adaptive Agents and Multi-Agent Systems5 citations

    Semantic Scholar

    Save

30. The Generalized Eigenvalue Problem as a Nash Equilibrium

    I. Gemp, Chen Chen, B. McWilliams

    2022arXiv.org5 citations Open access

    Semantic Scholar

    Save

31. LLM-Mediated Guidance of MARL Systems

    P. D. Siedler, I. Gemp

    2025arXiv.org4 citations

    Semantic Scholar

    Save

32. Developing, evaluating and scaling learning agents in multi-agent environments

    I. Gemp, Thomas W. Anthony, Yoram Bachrach, Avishkar Bhoopchand +23 more

    2022AI Communications4 citations Open access

    Semantic Scholar

    Save

33. Game Theoretic Rating in N-player general-sum games with Equilibria

    Luke Marris, Marc Lanctot, I. Gemp, Shayegan Omidshafiei +4 more

    2022arXiv.org4 citations Open access

    Semantic Scholar

    Save

34. A Neural Network Auction For Group Decision Making Over a Continuous Space

    Yoram Bachrach, I. Gemp, M. Garnelo, János Kramár +3 more

    2021International Joint Conference on Artificial Intelligence3 citations Open access

    Semantic Scholar

    Save

35. Active Evaluation of General Agents: Problem Definition and Comparison of Baseline Algorithms

    Marc Lanctot, Kate Larson, I. Gemp, Michael Kaisers

    2026Proceedings of the 25th International Conference on Autonomous Agents and Multiagent Systems2 citations

    Semantic Scholar

    Save

36. NfgTransformer: Equivariant Representation Learning for Normal-form Games

    Siqi Liu, Luke Marris, Georgios Piliouras, I. Gemp +1 more

    2024International Conference on Learning Representations2 citations

    Semantic Scholar

    Save

37. Nash without Numbers: A Social Choice Approach to Mixed Equilibria in Context-Ordinal Games

    I. Gemp, Crystal Qian, Marc Lanctot, Kate Larson

    2026arXiv.org1 citations

    Semantic Scholar

    Save

38. Price of Anarchy of First-Price Auctions in Agentic Markets

    Shubhendu Trivedi, Jacob Eisenstein, Alekh Agarwal, I. Gemp +2 more

    20261 citations

    Semantic Scholar

    Save

39. Game Arena: Strategic LLM Evaluation in Competitive Environments

    Bovard Doerschuk-Tiberi, Yao Yan, Justin Chiu, Han-Dong Wang +58 more

    20261 citations

    Semantic Scholar

    Save

40. Chaos in Autobidding Auctions

    Ioannis Anagnostides, I. Gemp, Georgios Piliouras, Kelly Spendlove

    2026arXiv.org1 citations

    Semantic Scholar

    Save

41. Visualizing 2x2 Normal-Form Games: twoxtwogame LaTeX Package

    Luke Marris, I. Gemp, Siqi Liu, J. Leibo +1 more

    2024arXiv.org1 citations

    Semantic Scholar

    Save

42. Convex Markov Games: A Framework for Fairness, Imitation, and Creativity in Multi-Agent Learning

    I. Gemp, Andreas A. Haupt, Luke Marris, Siqi Liu +1 more

    2024arXiv.org1 citations

    Semantic Scholar

    Save

43. The Symmetric Generalized Eigenvalue Problem as a Nash Equilibrium

    I. Gemp, Chen Chen, B. McWilliams

    2022International Conference on Learning Representations1 citations

    Semantic Scholar

    Save

44. Calibration Transfer in LIBS and Raman Spectroscopy for Planetary Applications

    M. Dyar, B. Thomas, M. Parente, I. Gemp +1 more

    20171 citations

    Semantic Scholar

    Save

45. Paradoxes of Game Theoretic Equilibria and Price of Anarchy

    Georgios Piliouras, I. Gemp, Siqi Liu, Luke Marris

    2026arXiv.org0 citations

    Semantic Scholar

    Save

46. Decentralized LLM Workflows via Sequential Auctions

    I. Gemp, Shubhendu Trivedi, Adam Fisch, Fantine Huot +6 more

    20260 citations

    Semantic Scholar

    Save

47. Tight Inapproximability for Welfare-Maximizing Autobidding Equilibria

    Ioannis Anagnostides, I. Gemp, Georgios Piliouras, Kelly Spendlove

    2026arXiv.org0 citations

    Semantic Scholar

    Save

48. Teamwork Reinforcement Learning With Concave Utilities

    Zhengzheng Yu, Junyu Zhang, Zheng Wen, Andrea Tacchetti +2 more

    2024IEEE Transactions on Mobile Computing0 citations

    Semantic Scholar

    Save

49. Nash Equilibria via Stochastic Eigendecomposition

    I. Gemp

    2024arXiv.org0 citations

    Semantic Scholar

    Save

50. Stochastic Parallelizable Eigengap Dilation for Large Graph Clustering

    Elise van der Pol, I. Gemp, Yoram Bachrach, Richard Everett

    2022TAG-ML0 citations Open access

    Semantic Scholar

    Save