Congestion Games

Latest papers

10 papers1 paper in the last four weeks, with none the four weeks before. 0.0% of all new papers.

Warned alike, AI agents avoid the less-crowded road while people take it
Sep 25, 2026Takahiro Ezaki, Naoto Imura, Katsuhiro NishinariCongestion Games Multi-Agent Coordination
Research Center for Advanced Science and Technology, The University of Tokyo, 4-6-1 Komaba, Meguro-ku, Tokyo 153-8904, Japan · Department of Aeronautics and Astronautics, School of Engineering, The University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo 113-8656, Japan
Competitive mediator games and urban CAV routing markets
Aug 10, 2026Grzegorz JamrózMechanism Design Game Theory
Faculty of Mathematics and Computer Science, Jagiellonian University, Kraków, Poland
Natural Invariant Measures for Chaotic Game Dynamics: Finding Order in Chaos
Jul 23, 2026Jakub Bielawski, Thiparat Chotibut, Fryderyk Falniowski +2Dynamical Systems Game Theory
Department of Mathematics, Krakow University of Economics, Rakowicka 27, 31-510 Kraków, Poland · Chula Intelligent and Complex Systems Lab, Department of Physics, Faculty of Science, Chulalongkorn University,Bangkok 10330, Thailand · Department of Mathematical Sciences, Indiana University Indianapolis,402 N. Blackford Street, Indianapolis, Indiana 46202, USA +1
Paradoxes of Game Theoretic Equilibria and Price of Anarchy
Jul 13, 2026Georgios Piliouras, Ian Gemp, Siqi Liu +1Nash Equilibrium Game Theory
Google Deepmind, UK
The Price of Anarchy in Disaggregated Inference
Jun 11, 2026Athos GeorgiouLLM Inference Efficiency Game Theory
NCA
Three Phases of Expert Routing: How Load Balance Evolves During Mixture-of-Experts Training
Apr 5, 2026Charafeddine MouzouniCongestion Games Expert Load Balancing
OPIT – Open Institute of Technology, and Cohorte AI, Paris, France.
Strategic Infrastructure Design via Multi-Agent Congestion Games with Joint Placement and Pricing
Mar 23, 2026Niloofar Aminikalibar, Farzaneh Farhadi, Maria ChliCongestion Games Multi-Agent System Optimization
Aston University, Birmingham, UK, B4 7ET
Zeroth-Order Stackelberg Control in Combinatorial Congestion Games
Feb 26, 2026Saeed Masiha, Sepehr Elahi, Negar Kiyavash +1Frank-Wolfe Algorithms Stackelberg Games
EPFL School of Management of Technology · EPFL Department of Computer and Communications Sciences
Socially-Weighted Alignment: A Game-Theoretic Framework for Multi-Agent LLM Systems
Feb 16, 2026Furkan Mumcu, Yasin YilmazCongestion Games Multi-Agent LLM Systems
University of South Florida
Chaos persists in large-scale multi-agent learning despite adaptive learning rates
Jun 1, 2023Emmanouil-Vasileios Vlatakis-Gkaragkounis, Konstantinos Metaxas, Lampros Flokas +1Congestion Games Game-Theoretic RL
University of California, Berkeley. · Columbia University. · Singapore University of Technology and Design. +1

Sep 25, 2026J/K move · Enter open · S save

Warned alike, AI agents avoid the less-crowded road while people take it

Takahiro Ezaki, Naoto Imura, Katsuhiro Nishinari

Research Center for Advanced Science and Technology, The University of Tokyo, 4-6-1 Komaba, Meguro-ku, Tokyo 153-8904, Japan · Department of Aeronautics and Astronautics, School of Engineering, The University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo 113-8656, Japan

Congestion Games Multi-Agent Coordination Human-AI Interaction Emergent Behavior in Multi-Agent Systems Game Theory

Open paper AskPDF arXiv

AI agents built on a few shared models increasingly act for many people. A shared forecast about others can align their choices and change how scarce capacity is allocated. We tested this feedback in a two-road congestion game. Adding one sentence warning that others might follow a routing tip made populations of 50 GPT agents crowd one road while avoiding the nearly empty alternative. Average travel time rose from 64 to 95 min, although any crowded-road agent could have saved 69 min by switching alone. The warning discouraged the very move it predicted. The pattern persisted for 100 rounds. Two other model families shifted the same way without locking onto one road. Twelve all-human groups (240 participants) stayed near balance under numerical reports or the tip and warning. In 24 mixed groups with a further 240 participants, imbalance grew with the share of agents in the registered analysis, while people increasingly took the road the agents avoided. Collective costs stayed below the allagent reference, but with 15 agents and 5 humans, agent seats averaged 80 min, compared with 44 min for human seats. Shared forecasts can thus sustain collective inefficiency among similar agents. A better group average can also hide an unequal burden. Evaluations of AI agents that share resources should test populations, treat messages as interventions and report who bears the costs.