Research map

Multi-agent systems and games: research map

Multi-agent RL, equilibria, and LLM-based agents.

3,511 accepted papers at ICML, NeurIPS, ICLR, CVPR and AAAI (2016–2026), in 4 topics. Within all five venues, its share grew from 2.4% in 2023–24 to 4.2% in 2025–26 (629 → 1,914 papers at ICML, NeurIPS, CVPR and AAAI, the venues with data for all four years).

Explore Multi-agent systems and games in the interactive map

Topics

• LLM agents · 1,232 papers
  LLM multi-agent decision making, Self-evolving language agent learning, Robust and efficient agent execution
• Human-AI and goal-conditioned · 1,160 papers
  Human-AI coordination agents, Collaborative multi-agent perception, Boundedly rational agent modeling
• Cooperative multi-agent RL · 593 papers
  Cooperative MARL algorithms, MARL benchmarks and grouping, Learned inter-agent communication
• Games and equilibria · 526 papers
  Learning in Markov games, Cooperation and social dilemmas, Opponent modeling in competitive games

Most cited papers in Multi-agent systems and games

• Curiosity-driven Exploration by Self-supervised Prediction (ICML 2017 · 1,773 citations)
• SoPhie: An Attentive GAN for Predicting Paths Compliant to Social and Physical Constraints (CVPR 2019 · 1,115 citations)
• DESIRE: Distant Future Prediction in Dynamic Scenes With Interacting Agents (CVPR 2017 · 1,086 citations)
• Learning to Communicate with Deep Multi-Agent Reinforcement Learning (NeurIPS 2016 · 1,057 citations)
• Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments (NeurIPS 2017 · 1,002 citations)
• The Surprising Effectiveness of PPO in Cooperative Multi-Agent Games (NeurIPS 2022 · 597 citations)
• Noisy Networks For Exploration (ICLR 2018 · 571 citations)
• Reflexion: language agents with verbal reinforcement learning (NeurIPS 2023 · 559 citations)
• Stabilising Experience Replay for Deep Multi-Agent Reinforcement Learning (ICML 2017 · 420 citations)
• Mean Field Multi-Agent Reinforcement Learning (ICML 2018 · 313 citations)
• Learning Multiagent Communication with Backpropagation (NeurIPS 2016 · 276 citations)
• When2com: Multi-Agent Perception via Communication Graph Grouping (CVPR 2020 · 273 citations)