Best Paper Award:

• When Agents Lie: Premeditation, Persistence, and Exploitation in Repeated Games -- Jerick Shi, Terry Jingchen Zhang, Bernhard Schölkopf, Vincent Conitzer, Zhijing Jin

Spotlights:

• Failure Modes in AI Retraining Dynamics -- Kiarash Banihashem, Natalie Collina, Nicole Immorlica, Brendan Lucier, Aleksandrs Slivkins

• Strategic Testing in Games -- Angelos Korakitis, Christos Tzamos

• Towards Learning Representations of Policies in Two-Player Zero-Sum Games -- Kevin A. Wang, Kevin Yang, Arjun Prakash, Amy Greenwald

• The Price of Over-Delegation: Stackelberg Liability Design for Agentic AI Handoffs -- Tomoya Hoshino

Posters:

• Bellman-Local Lyapunov Barriers for Exact Stationary Nash Learning in Discounted Perfect-Information Stochastic Games -- Manoj Saravanan

• AlphaZero in Sparsely Rewarded Games: Limits and Auxiliary Supervision -- Brent Kong, Tejas Ram, Tony Yue YU

• Beyond Scalar Rewards: Dense Feedback for LLM Policy Synthesis in Sequential Social Dilemmas -- Victor Gallego

• Learning Bidding Strategies for Karma Economies in Realistic Traffic Settings with Multi-Agent Reinforcement Learning -- Anastasia Psarou, Kevin Riehl, Matej Jusup, Anastasios Kouvelas, Michail A. Makridis, Rafal Kucharski

• No-Regret Learning in Bayesian Stackelberg Games with Unknown Follower Types -- Matteo Bollini, Francesco Bacchiocchi, Samuel Coutts, Matteo Castiglioni, Alberto Marchesi

• Superhuman AI for Generals.io Using Self-Play Reinforcement Learning -- Matej Straka, Martin Schmid

• The Symmetry Trap: Parametric Equilibria and the Welfare Cost of Architectural Monoculture -- Siddharth Karuturi, Kaustubh S. Bukkapatnam, Soham Batra, Mithil Shah, Tanush Ajay Shastry, Akshath Sharma, Laksh Patel, Aarav Lala, Andrew Bae

• Zero Shot Coordination for Sparse Reward Tasks with Diverse Reward Shapings -- Keenan Powell, Peihong Yu, Pratap Tokekar

• A Minimal Decision Capacity Threshold Prevents Catastrophic Exploitation in Self-Play RL -- Arahan Kujur

• Neural Algorithmic Reasoning for Nash Equilibrium -- Mateusz Kuba Korytkowski, Dobrik Georgiev Georgiev, Davide Buffelli, Pietro Lio

• From Risk Scoring to Risk Allocation: A Density-Driven Framework for Diverse Monitoring in Multi-Agent Systems -- Zhaohui Geoffrey Wang

• Bridging Game Theory and Transformer Routing: Mean Field Equilibria for Mixture of Experts -- Nevroz Sen

• Parametric Open Source Games -- Aleksandar Todorov, Jesse ten Napel, Alexander Müller

• PoolBench:Benchmarking Large Language Models on Continuous Physical Action Selection in Eight-Ball Pool -- Prapti Patra, Dhruv Kumar

• The Clone Game: Strategic Ecology for Monoculture-Resistant AI Agents -- Muhammet Anil Yagiz

• Do Prompted Strategic Personas Influence Decision Making in Large Language Models? A Chess-Based Experimental Study -- AADIT SHAH, Yash Sinha

• Multi-Agent Reinforcement Learning of Karma Bidding Strategies -- Kevin Riehl, Anastasia Psarou, Robert Müller, Fan Wu, Patrick Langer, Robert Jakob, Gabor Hollbeck, Anastasios Kouvelas, Rafal Kucharski, Michail A. Makridis

• In-Context Credit Assignment via the Core -- Keegan Harris, Siddharth Prasad, Asher Trockman

• Learning to Mediate Equilibrium Selection in LLM Games -- Miao Liu, Matthew Riemer, Maria Chang, Murray Campbell, Djallel Bouneffouf

• The computational complexity of computing refunds -- Stelios Drakontaeidis, Christos Tzamos

• EMAgnet: Parameter-Space EMA Regularization for Policy Gradient Self-Play in Large Games -- Tristan Maidment, JB Lanier, Chase McDonald, Nathan Tsang, Eugene Vinitsky, Roy Fox, Albert Wang, Wesley N. Kerr

• Power and Limitations of Aggregation in Compound AI Systems -- Nivasini Ananthakrishnan, Meena Jagadeesan

• Opponent Modeling and Value of Information in Deep Reinforcement Learning for the Iterated Prisoner’s Dilemma -- Oleksii Ignatenko, Nazarii Tkach

• Beyond Task Success: Evaluating Cooperation in LLM-Based Multi Agent Systems -- Ashish Raj Shekhar, Saniya Mulla, Upasana Biswas, Priyanuj Bordoloi, Vivek Gupta

• Seeing Through Distractions: Stable Attribution via the Core -- Sai Ganesh Nagarajan, Toshinori Yamauchi, Hiroshi Kera

• Nash Bargaining for Gate-Free Mixture-of-Experts -- Abien Fred Agarap, Inigo Miguel Benavides, Sara Ann Venturina

• Self-Play Reinforcement Learning under Imperfect Information in Big 2 -- Aalok Patwa

• Stackelberg Mean-Field Games for Adaptive Cancer Therapy -- Arash Mehrjou

• Preference-Based Distributed Welfare Maximization: A Game-Theoretic Approach -- Antoine Bergerault, Anna Maria Maddux, Andreas Schlaginhaufen, Maryam Kamgarpour

• Optimism as a Vulnerability: Deceptive Stackelberg Control of UCB Bandit Followers -- Şuayp Talha Kocabay, Kerem Yalçın, Talha Rüzgar Akkuş

• Non-Linear Strategic Classification Made Practical -- Jack Geary, Henry Gouk

• Bayesian Persuasion with a Risk-Conscious Receiver -- Yujing Chen

• Adversarial Training with Large Step Sizes: Implicit Bias and Evolution of Sharpness -- Yi Feng, Andrea Paudice, Stratis Skoulakis

• The Cost of Blind Confidence: Opponent Modeling under Imperfect Information -- Andrea Menta, Francesca Maifredi, Matteo Papini

• Signaling in Data Markets via Free Samples -- Nivasini Ananthakrishnan, Alireza Fallah, Michael I. Jordan

• Markov Chain from Human Feedback -- Takuya Koriyama, Tengyuan Liang

• Fair Robust Strategic Classification under Decision-Dependent Cost Uncertainty -- Sura Alhanouti, Guzin Bayraksan, Parinaz Naghizadeh

• Mechanism Design for Multi-Agent Alpha Discovery: Optimizing Agent Distribution in Heterogeneous LLM Markets -- Ajitabh Kumar

• Learned Coordination Conventions in Cooperative MARL: Measuring the Translation Gap Between Theory-Informed Roles and Learned Routing -- Yoosung Hong

• Incentive design in sequential statistical protocols -- Drew T Nguyen, Alireza Fallah, Michael I. Jordan

• Sequential Minimax Games as Stacked Martingale Optimal Transport -- Ethan Chen

• AgentSociety: Incentivizing Agentic Social Intelligence -- Aditya Vema Reddy Kesari, Krishna Reddy Kesari

• EngineLab: Evaluating Strategic Generalization Under Rule Shifts -- Tianyi Evans Gu, Lucas Yuan

• A Causal Approach to Game Theory -- Aurghya Maiti, Prateek Jain, Elias Bareinboim

• LERA: LLM-Enhanced RAG for Ad Auction in Generative Chatbots -- Haoran Sun, Xinrui Song, Xinyu Zhang, Zhaohua Chen, Xu Chu, Zhilin Zhang, Chuan Yu, Jian Xu, Bo Zheng, Xiaotie Deng

• Attention as Natural Gradient: In-Context Mirror Descent for Opponent Modelling -- Alexander Chernyavskiy, Natalia Gusarova, Aleksandra Vatian

• Scaling Laws for Strategic Interactions -- Joie Zhang, Danqi Chen, Peter Henderson, Lewis Hammond

• First-Order Efficiency for Probabilistic Value Estimation via A Statistical Viewpoint -- Ziqi Liu, Kiljae Lee, Yuan Zhang, Weijing Tang

• Poker Arena: Multi-Axis Profiling of Strategic Reasoning and Memory in LLMs -- Pratham Singla, Shivank Garg, VIHAN SINGH

• MafiaPersona: A Multi-Agent Adversarial Benchmark for Evaluating Persona Persistence in Large Language Models -- Ojaswi Prakash, Dhruv Kumar, Murari Mandal, Mohan Kankanhalli, Yash Sinha

• PALS: Preference-guided Active Automata Learning for Symbolic Reinforcement Learning in Games -- William Peter Fishell, Sam Kouteili, Mark Paul Santolucito, Christian Scaff

• Position: Alignment Needs Rule-Class Routing Before Preference Learning -- Zezheng Lin, Jinhao Gan

• Equilibrium Selection in Multi-Agent Policy Gradients via Opponent-Aware Basin Entry -- Yevhen Shcherbinin, Arina Redina, Maxim Kalpin, Vlad Kochetov

• Kantian Equilibrium in the Age of Multi-Agent Systems -- Ivan Samoylenko

• Learning to Diffuse: Mechanism Design in Social Networks with Information Propagation Costs -- Sebastiano Messina, Tatjana Chavdarova

• GT-HarmBench: Benchmarking AI Safety Risks Through the Lens of Game Theory -- Pepijn Cobben, Xuanqiang Angelo Huang, Thao Amelia Pham, Isabel Dahlgren, Bernhard Schölkopf, Terry Jingchen Zhang, Zhijing Jin

• Designing Training Objectives for Iterative Reasoning Agents: Dense Supervision as an Adaptive Mechanism -- Bao N Nguyen Truong, Hoyeon Chang, Alexander Rubinstein, Seong Joon Oh

• Dynamics of Adversarial Attacks on Large Language Model-Based Search Engines -- Xiyang Hu

• COMRAD: A Benchmark for Embodied Cooperative Multi-Agent Reinforcement Learning -- Khoi H.B. Nguyen, Dimitar Zhivkov Zhekov, Tristan Tomilin