理论 · game theory论文趋势 2023–2026

主要结论

• 理论 · game theory论文从 2023 年的 34 篇增长到 2026 年的 126 篇，三年间扩大到约 3.7 倍。
• NeurIPS 是发理论 · game theory论文最多的会议，2023–2026 年共 183 篇，占四个会议总量的 48%。
• 交叉方向里涨得最快的是机制设计：同时属于两个主题的论文从 2023 年的 1 篇增至 2026 年的 19 篇。
• 在「理论与统计」的 5 个主题里，它的 2026 年论文数排第 4；同组增长最快的理论 · learning theory是 5.6 倍，理论 · game theory是 3.7 倍。

代表论文

按年份和会议均匀挑选，方便快速看到每一届的样貌

• 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

全部理论 · game theory论文

共 69 篇，第 1 / 2 页

1. ICLR 2026Achieving Approximate Symmetry Is Exponentially Easier than Exact Symmetry
2. ICLR 2026Almost Bayesian: Dynamics of SGD Through Singular Learning Theory
3. ICLR 2026Characterizing the Discrete Geometry of ReLU Networks
4. ICLR 2026Differentially Private Equilibrium Finding in Polymatrix Games
5. ICLR 2026Diversified Multinomial Logit Contextual Bandits
6. ICLR 2026Expert Merging in Sparse Mixture of Experts with Nash Bargaining
7. ICLR 2026Group Representational Position Encoding
8. ICLR 2026Infinite Horizon Markov Economies
9. ICLR 2026Interactive Learning of Single-Index Models via Stochastic Gradient Descent
10. ICLR 2026Learning a Game by Paying the Agents
11. ICLR 2026Learning to Answer from Correct Demonstrations
12. ICLR 2026Learning to Play Multi-Follower Bayesian Stackelberg Games
13. ICLR 2026Learning to Recall with Transformers Beyond Orthogonal Embeddings
14. ICLR 2026Mean-Field Neural Differential Equations: A Game-Theoretic Approach to Sequence Prediction
15. ICLR 2026On Universality of Deep Equivariant Networks
16. ICLR 2026Pruning as a Cooperative Game: Surrogate-Assisted Layer Contribution Estimation for Large Language Models
17. ICLR 2026Quasi-Equivariant Metanetworks
18. ICLR 2026Solving Football by Exploiting Equilibrium Structure of 2p0s Differential Games with One-Sided Information
19. ICLR 2026The Imitation Game: Turing Machine Imitator is Length Generalizable Reasoner
20. ICLR 2026Tighter Performance Theory of FedExProx
21. ICLR 2025A Theory of Initialisation's Impact on Specialisation
22. ICLR 2025BANGS: Game-theoretic Node Selection for Graph Self-Training
23. ICLR 2025Computational Explorations of Total Variation Distance
24. ICLR 2025Decoding Game: On Minimax Optimality of Heuristic Text Generation Strategies
25. ICLR 2025Divergence-Regularized Discounted Aggregation: Equilibrium Finding in Multiplayer Partially Observable Stochastic Games
26. ICLR 2025Efficient Online Pruning and Abstraction for Imperfect Information Extensive-Form Games
27. ICLR 2025Exact Computation of Any-Order Shapley Interactions for Graph Neural Networks
28. ICLR 2025Exploring The Loss Landscape Of Regularized Neural Networks Via Convex Duality
29. ICLR 2025Lasso Bandit with Compatibility Condition on Optimal Arm
30. ICLR 2025Last-Iterate Convergence Properties of Regret-Matching Algorithms in Games
31. ICLR 2025MAST: model-agnostic sparsified training
32. ICLR 2025On the Convergence of No-Regret Dynamics in Information Retrieval Games with Proportional Ranking Functions
33. ICLR 2025On the Expressiveness of Rational ReLU Neural Networks With Bounded Depth
34. ICLR 2025Quality over Quantity in Attention Layers: When Adding More Heads Hurts
35. ICLR 2025Re-evaluating Open-ended Evaluation of Large Language Models
36. ICLR 2025Separation Power of Equivariant Neural Networks
37. ICLR 2025Strategic Classification With Externalities
38. ICLR 2025The Complexity of Two-Team Polymatrix Games with Independent Adversaries
39. ICLR 2025When LLMs Play the Telephone Game: Cultural Attractors as Conceptual Tools to Evaluate LLMs in Multi-turn Settings
40. ICLR 2024A ROBUST DIFFERENTIAL NEURAL ODE OPTIMIZER
41. ICLR 2024Adversarial Training Should Be Cast as a Non-Zero-Sum Game
42. ICLR 2024Approximating Nash Equilibria in Normal-Form Games via Stochastic Optimization
43. ICLR 2024Benign Oscillation of Stochastic Gradient Descent with Large Learning Rate
44. ICLR 2024Efficient Inverse Multiagent Learning
45. ICLR 2024Expected flow networks in stochastic environments and two-player zero-sum games
46. ICLR 2024Generative Adversarial Equilibrium Solvers
47. ICLR 2024How to Capture Higher-order Correlations? Generalizing Matrix Softmax Attention to Kronecker Computation
48. ICLR 2024NfgTransformer: Equivariant Representation Learning for Normal-form Games
49. ICLR 2024Noisy Interpolation Learning with Shallow Univariate ReLU Networks
50. ICLR 2024OPTIMAL ROBUST MEMORIZATION WITH RELU NEURAL NETWORKS

常见问题

2023–2026 年四大会议一共有多少篇理论 · game theory论文？

共 384 篇，按年份分别是 2023 年 34 篇、2024 年 107 篇、2025 年 117 篇、2026 年 126 篇。

NeurIPS 2026 有多少篇理论 · game theory论文？

NeurIPS 2026 有 44 篇理论 · game theory论文，上一届是 49 篇。

ICLR 2026 有多少篇理论 · game theory论文？

ICLR 2026 有 20 篇理论 · game theory论文，上一届是 19 篇。

ICML 2026 有多少篇理论 · game theory论文？

ICML 2026 有 61 篇理论 · game theory论文，上一届是 47 篇。

CVPR 2026 有多少篇理论 · game theory论文？

CVPR 2026 有 1 篇理论 · game theory论文，上一届是 2 篇。

哪个会议的理论 · game theory论文最多？

NeurIPS，2023–2026 年共 183 篇。