Research map / Multi-agent systems and games
Games and equilibria: research map
537 papers on Games and equilibria in Multi-agent systems and games, from ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR (2016–2026), grouped into 2 clusters and 7 approaches. The busiest year so far is 2025.
What it is
Learning in strategic settings with several players whose interests may conflict: Markov games, social dilemmas, opponent modelling, and agents that respond strategically to a learning system, such as people gaming a classifier.
Terms you will see on this page:
- Nash equilibrium
- a strategy profile where no player gains by changing alone.
- Markov game
- the multi-player generalisation of an MDP.
- Strategic classification
- classification when people change their features to get a better outcome.
Start reading with the most cited papers here:
- Mean Field Multi-Agent Reinforcement Learning (ICML 2018 · 313 citations)
- Training Agent for First-Person Shooter Game with Actor-Critic Curriculum Learning (ICLR 2017 · 127 citations)
Within Multi-agent systems and games, its share shrank from 20.2% in 2023–24 to 7.5% in 2025–26 (127 → 143 papers at ICML, NeurIPS, ICLR, CVPR and AAAI, the venues with data for all four years).
Explore Games and equilibria in the interactive map
Working on something in this topic? Describe your idea in scime atlas to see which approach it falls under, the closest papers by meaning and how crowded the spot has become.
What changed recently
Approaches whose share of the topic moved most between 2023–24 and 2025–26 (ICML, NeurIPS, ICLR, CVPR and AAAI):
- Cooperation and social dilemmas rising: 14% → 22% of the topic (18 → 32 papers)
- Strategic classification rising: 9% → 12% of the topic (12 → 17 papers)
- Opponent modeling in competitive games falling: 17% → 7% of the topic (21 → 10 papers)
- Fair division and coalition formation falling: 17% → 15% of the topic (21 → 21 papers)
Papers from 2025–2026 that are already cited most:
- Learning Nash Equilibrium of Markov Potential Games with a Shared Constraint via Primal-Dual Optimization (AAAI 2025 · 2 citations)
- Self-Play $Q$-Learners Can Provably Collude in the Iterated Prisoner's Dilemma (ICML 2025 · 2 citations)
- Bounded Rationality Equilibrium Learning in Mean Field Games (AAAI 2025 · 1 citations)
Approaches and key papers
Learning in games · 309 papers
Keywords: game, player, sum
Approaches in this cluster:
- Learning in Markov games (114 papers)
Proves convergence and hardness of decentralized policy learning in zero-sum and general-sum Markov games. - Cooperation and social dilemmas (95 papers)
Studies how learning agents cooperate or collude in dilemmas and sustain cooperation mechanisms. - Opponent modeling in competitive games (77 papers)
Shapes and adapts to opponents in two-player games via auto-curricula and strategy representations. - Mean-field game learning (23 papers)
Learns equilibria of mean-field games with reinforcement and imitation learning.
Most cited and most cited since 2024:
- Mean Field Multi-Agent Reinforcement Learning (ICML 2018 · 313 citations)
- Training Agent for First-Person Shooter Game with Actor-Critic Curriculum Learning (ICLR 2017 · 127 citations)
- Approximating the Shapley Value without Marginal Contributions (AAAI 2024 · 28 citations)
- Accelerate Multi-Agent Reinforcement Learning in Zero-Sum Games with Subgame Curriculum Learning (AAAI 2024 · 8 citations)
Strategic agents and welfare · 228 papers
Keywords: principal, strategic, welfare
Approaches in this cluster:
- Fair division and coalition formation (100 papers)
Analyzes complexity and fairness of allocating indivisible goods and forming coalitions. - Learning with strategic agents (76 papers)
Designs contracts, menus, and mechanisms for learning in principal-agent and strategic interactions. - Strategic classification (52 papers)
Models classifiers facing agents who adapt features, with incentives and causal analysis.
Most cited and most cited since 2024:
- Almost Full EFX Exists for Four Agents (AAAI 2022 · 40 citations)
- Signaling in Bayesian Network Congestion Games: the Subtle Power of Symmetry (AAAI 2021 · 33 citations)
- Contracting with a Learning Agent (NeurIPS 2024 · 5 citations)
- Stability in Online Coalition Formation (AAAI 2024 · 4 citations)
Related topics in Multi-agent systems and games
- LLM agents (1,294)
- Cooperative multi-agent RL (635)
- Human-AI and goal-conditioned (1,320)
