Theory · game theory papers, 2023–2026

Key findings

• Theory · game theory went from 34 papers in 2023 to 126 in 2026, roughly 3.7x in three years.
• NeurIPS publishes the most Theory · game theory work: 183 papers from 2023 to 2026, 48% of the four-venue total.
• The fastest-growing overlap is with Mechanism Design: papers tagged with both rose from 1 in 2023 to 19 in 2026.
• Among the 5 topics under Theory and Statistics, it ranks #4 by 2026 paper count; the fastest grower in the group, Theory · learning theory, is up 5.6x versus 3.7x here.

Representative papers

Spread across years and venues so every edition shows up

• NeurIPS 2026A Mechanistic Investigation of Theory of Mind in a Large Language Model
• ICML 2026(Doubly) Exponential Lower Bounds for Follow the Regularized Leader in Potential Games
• ICLR 2026Infinite Horizon Markov Economies
• CVPR 2026Tackling Model Bias via Game-theoretic Multi-agent Collaboration Framework for Hateful
• NeurIPS 2025AlphaBeta is not as good as you think: a simple random games model for a better analysis of deterministic game-solving algorithms
• ICML 2025A-PSRO: A Unified Strategy Learning Method with Advantage Metric for Normal-form Games
• ICLR 2025A Theory of Initialisation's Impact on Specialisation
• CVPR 2025Dynamic Stereotype Theory Induced Micro-expression Recognition with Oriented Deformation
• NeurIPS 2024Accelerated Regularized Learning in Finite N-Person Games
• ICML 2024A Statistical Theory of Regularization-Based Continual Learning
• ICLR 2024Generative Adversarial Equilibrium Solvers
• CVPR 2024GlitchBench: Can Large Multimodal Models Detect Video Game Glitches?
• NeurIPS 2023$\varepsilon$-fractional core stability in Hedonic Games.
• ICML 2023Auxiliary Learning as an Asymmetric Bargaining Game
• ICLR 2023Computational Language Acquisition with Theory of Mind
• CVPR 2023Improving Generalization With Domain Convex Game
• NeurIPS 2026Agentic AI Design Should be Mediated to Promote Social Welfare
• ICML 2026A Game-Theoretic Analysis of Attacks on Large Language Models via Compositional Skills
• ICLR 2026On Universality of Deep Equivariant Networks
• NeurIPS 2025Approximation theory for 1-Lipschitz ResNets

All Theory · game theory papers

117 papers, page 2 of 3

51. ICML 2025PDUDT: Provable Decentralized Unlearning under Dynamic Topologies
52. ICML 2025Position: Algebra Unveils Deep Learning - An Invitation to Neuroalgebraic Geometry
53. ICML 2025Preference-CFR: Beyond Nash Equilibrium for Better Game Strategies
54. ICML 2025Prices, Bids, Values: One ML-Powered Combinatorial Auction to Rule Them All
55. ICML 2025Procurement Auctions via Approximately Optimal Submodular Optimization
56. ICML 2025Provably Efficient Algorithm for Best Scoring Rule Identification in Online Principal-Agent Information Acquisition
57. ICML 2025Reducing Variance of Stochastic Optimization for Approximating Nash Equilibria in Normal-Form Games
58. ICML 2025Safely Learning Optimal Auctions: A Testable Learning Framework for Mechanism Design
59. ICML 2025Securing Equal Share: A Principled Approach for Learning Multiplayer Symmetric Games
60. ICML 2025Selective Response Strategies for GenAI
61. ICML 2025Self-Play $Q$-Learners Can Provably Collude in the Iterated Prisoner's Dilemma
62. ICML 2025Settling the Maximin Share Fairness for Scheduling among Groups of Machines
63. ICML 2025Should Decision-Makers Reveal Classifiers in Online Strategic Classification?
64. ICML 2025Solving Zero-Sum Convex Markov Games
65. ICML 2025SPMC: Self-Purifying Federated Backdoor Defense via Margin Contribution
66. ICML 2025The Harder Path: Last Iterate Convergence for Uncoupled Learning in Zero-Sum Games with Bandit Feedback
67. ICML 2025The impact of uncertainty on regularized learning in games
68. ICML 2025Towards a Formal Theory of Representational Compositionality
69. NeurIPS 2025Adaptive Prediction-Powered AutoEval with Reliability and Efficiency Guarantees
70. NeurIPS 2025AlphaBeta is not as good as you think: a simple random games model for a better analysis of deterministic game-solving algorithms
71. NeurIPS 2025Approximation theory for 1-Lipschitz ResNets
72. NeurIPS 2025Balancing Multimodal Training Through Game-Theoretic Regularization
73. NeurIPS 2025Benign Overfitting in Single-Head Attention
74. NeurIPS 2025Contextual Dynamic Pricing with Heterogeneous Buyers
75. NeurIPS 2025Cooperative Bargaining Games Without Utilities: Mediated Solutions from Direction Oracles
76. NeurIPS 2025Cyclic Counterfactuals under Shift–Scale Interventions
77. NeurIPS 2025Disentangling Hyperedges through the Lens of Category Theory
78. NeurIPS 2025Do Neural Networks Need Gradient Descent to Generalize? A Theoretical Study
79. NeurIPS 2025Efficient Kernelized Learning in Polyhedral Games beyond Full Information: From Colonel Blotto to Congestion Games
80. NeurIPS 2025Evolutionary Prediction Games
81. NeurIPS 2025Explaining the Law of Supply and Demand via Online Learning
82. NeurIPS 2025GUARD: Constructing Realistic Two-Player Matrix and Security Games for Benchmarking Game-Theoretic Algorithms
83. NeurIPS 2025How Particle System Theory Enhances Hypergraph Message Passing
84. NeurIPS 2025Incentivizing Time-Aware Fairness in Data Sharing
85. NeurIPS 2025Last Iterate Convergence in Monotone Mean Field Games
86. NeurIPS 2025Last-Iterate Convergence of Smooth Regret Matching$^+$ Variants in Learning Nash Equilibria
87. NeurIPS 2025Learning in Stackelberg Mean Field Games: A Non-Asymptotic Analysis
88. NeurIPS 2025Learning-Augmented Facility Location Mechanisms for the Envy Ratio Objective
89. NeurIPS 2025LLM Strategic Reasoning: Agentic Study through Behavioral Game Theory
90. NeurIPS 2025Machine Unlearning under Overparameterization
91. NeurIPS 2025Marginal-Nonuniform PAC Learnability
92. NeurIPS 2025Modeling the Economic Impacts of AI Openness Regulation
93. NeurIPS 2025Multi-Agent Learning under Uncertainty: Recurrence vs. Concentration
94. NeurIPS 2025Multiplayer Federated Learning: Reaching Equilibrium with Less Communication
95. NeurIPS 2025Non-Stationary Lipschitz Bandits
96. NeurIPS 2025On Universality Classes of Equivariant Networks
97. NeurIPS 2025Parsimonious Predictions for Strategyproof Scheduling
98. NeurIPS 2025Replicable Distribution Testing
99. NeurIPS 2025Robust Equilibria in Continuous Games: From Strategic to Dynamic Robustness
100. NeurIPS 2025Robustly Learning Monotone Single-Index Models

FAQ

How many Theory · game theory papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

384 in total: 34 in 2023, 107 in 2024, 117 in 2025, 126 in 2026.

How many Theory · game theory papers are at NeurIPS 2026?

NeurIPS 2026 has 44 Theory · game theory papers, versus 49 the year before.

How many Theory · game theory papers are at ICLR 2026?

ICLR 2026 has 20 Theory · game theory papers, versus 19 the year before.

How many Theory · game theory papers are at ICML 2026?

ICML 2026 has 61 Theory · game theory papers, versus 47 the year before.

How many Theory · game theory papers are at CVPR 2026?

CVPR 2026 has 1 Theory · game theory papers, versus 2 the year before.

Which conference publishes the most Theory · game theory papers?

NeurIPS, with 183 papers from 2023 to 2026.