ICML 2026 Past Theory
New Frontiers in Game-Theoretic Learning - NExT-Game
ICML 2026 Workshop
- Submission deadline
- May 13, 2026, 12:00 UTC imported from OpenReview — check the website for extensions
- Submission portal
- OpenReview
- Notes
- Auto-imported from the OpenReview venue record on 2026-06-10 — please verify and enrich (topics are keyword-guessed).
Accepted papers (64)
Fetched from OpenReview (v2) on 2026-06-10.
-
A Causal Approach to Game Theory
-
A Minimal Decision Capacity Threshold Prevents Catastrophic Exploitation in Self-Play RL
-
Adversarial Training with Large Step Sizes: Implicit Bias and Evolution of Sharpness
-
AgentSociety: Incentivizing Agentic Social Intelligence
-
AlphaZero in Sparsely Rewarded Games: Limits and Auxiliary Supervision
-
Attention as Natural Gradient: In-Context Mirror Descent for Opponent Modelling
-
Bayesian Persuasion with a Risk-Conscious Receiver
-
Bellman-Local Lyapunov Barriers for Exact Stationary Nash Learning in Discounted Perfect-Information Stochastic Games
-
Beyond Scalar Rewards: Dense Feedback for LLM Policy Synthesis in Sequential Social Dilemmas
-
Beyond Task Success: Evaluating Cooperation in LLM-Based Multi Agent Systems
-
Bridging Game Theory and Transformer Routing: Mean Field Equilibria for Mixture of Experts
-
COMRAD: A Benchmark for Embodied Cooperative Multi-Agent Reinforcement Learning
-
Designing Training Objectives for Iterative Reasoning Agents: Dense Supervision as an Adaptive Mechanism
-
Do Prompted Strategic Personas Influence Decision Making in Large Language Models? A Chess-Based Experimental Study
-
Dynamics of Adversarial Attacks on Large Language Model-Based Search Engines
-
EMAgnet: Parameter-Space EMA Regularization for Policy Gradient Self-Play in Large Games
-
EngineLab: Evaluating Strategic Generalization Under Rule Shifts
-
Equilibrium Selection in Multi-Agent Policy Gradients via Opponent-Aware Basin Entry
-
Failure Modes in AI Retraining Dynamics
-
Fair Robust Strategic Classification under Decision-Dependent Cost Uncertainty
-
First-Order Efficiency for Probabilistic Value Estimation via A Statistical Viewpoint
-
From Risk Scoring to Risk Allocation: A Density-Driven Framework for Diverse Monitoring in Multi-Agent Systems
-
GT-HarmBench: Benchmarking AI Safety Risks Through the Lens of Game Theory
-
In-Context Credit Assignment via the Core
-
Incentive design in sequential statistical protocols
-
Kantian Equilibrium in the Age of Multi-Agent Systems
-
Learned Coordination Conventions in Cooperative MARL: Measuring the Translation Gap Between Theory-Informed Roles and Learned Routing
-
Learning Bidding Strategies for Karma Economies in Realistic Traffic Settings with Multi-Agent Reinforcement Learning
-
Learning to Diffuse: Mechanism Design in Social Networks with Information Propagation Costs
-
Learning to Mediate Equilibrium Selection in LLM Games
-
LERA: LLM-Enhanced RAG for Ad Auction in Generative Chatbots
-
MafiaPersona: A Multi-Agent Adversarial Benchmark for Evaluating Persona Persistence in Large Language Models
-
Markov Chain from Human Feedback
-
Mechanism Design for Multi-Agent Alpha Discovery: Optimizing Agent Distribution in Heterogeneous LLM Markets
-
Multi-Agent Reinforcement Learning of Karma Bidding Strategies
-
Nash Bargaining for Gate-Free Mixture-of-Experts
-
Neural Algorithmic Reasoning for Nash Equilibrium
-
No-Regret Learning in Bayesian Stackelberg Games with Unknown Follower Types
-
Non-Linear Strategic Classification Made Practical
-
Opponent Modeling and Value of Information in Deep Reinforcement Learning for the Iterated Prisoner’s Dilemma
-
Optimism as a Vulnerability: Deceptive Stackelberg Control of UCB Bandit Followers
-
PALS: Preference-guided Active Automata Learning for Symbolic Reinforcement Learning in Games
-
Parametric Open Source Games
-
Poker Arena: Multi-Axis Profiling of Strategic Reasoning and Memory in LLMs
-
PoolBench:Benchmarking Large Language Models on Continuous Physical Action Selection in Eight-Ball Pool
-
Position: Alignment Needs Rule-Class Routing Before Preference Learning
-
Power and Limitations of Aggregation in Compound AI Systems
-
Preference-Based Distributed Welfare Maximization: A Game-Theoretic Approach
-
Scaling Laws for Strategic Interactions
-
Seeing Through Distractions: Stable Attribution via the Core
-
Self-Play Reinforcement Learning under Imperfect Information in Big 2
-
Sequential Minimax Games as Stacked Martingale Optimal Transport
-
Signaling in Data Markets via Free Samples
-
Stackelberg Mean-Field Games for Adaptive Cancer Therapy
-
Strategic Testing in Games
-
Superhuman AI for Generals.io Using Self-Play Reinforcement Learning
-
The Clone Game: Strategic Ecology for Monoculture-Resistant AI Agents
-
The computational complexity of computing refunds
-
The Cost of Blind Confidence: Opponent Modeling under Imperfect Information
-
The Price of Over-Delegation: Stackelberg Liability Design for Agentic AI Handoffs
-
The Symmetry Trap: Parametric Equilibria and the Welfare Cost of Architectural Monoculture
-
Towards Learning Representations of Policies in Two-Player Zero-Sum Games
-
When Agents Lie: Premeditation, Persistence, and Exploitation in Repeated Games
-
Zero Shot Coordination for Sparse Reward Tasks with Diverse Reward Shapings