Research map / Multi-agent systems and games

LLM agents: research map

1,232 accepted papers on LLM agents in Multi-agent systems and games, from ICML, NeurIPS, ICLR, CVPR and AAAI (2016–2026), grouped into 2 clusters and 9 approaches. The busiest year so far is 2026.

Within Multi-agent systems and games, its share grew from 10.3% in 2023–24 to 60.4% in 2025–26 (65 → 1,157 papers at ICML, NeurIPS, CVPR and AAAI, the venues with data for all four years).

Explore LLM agents 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.

Approaches and key papers

gui · bench · software · 762 papers

Approaches in this cluster:

LLM multi-agent decision making (194 papers)
Designs collaboration, hierarchy, and credit assignment for LLM-based multi-agent teams.
Self-evolving language agent learning (188 papers)
Improves language agents via search, step-level value models, reinforcement learning, and self-distillation.
Robust and efficient agent execution (174 papers)
Benchmarks tool-using agent robustness and speeds execution with plan caching and compilation.
Agent data synthesis and behavior studies (108 papers)
Synthesizes agent training data and examines behavioral biases in interactive LLM agents.
Agent safety and attack benchmarks (98 papers)
Benchmarks multi-turn attacks, prompt injection, and malicious tool use against LLM agents.

Most cited and most cited since 2024:

Reflexion: language agents with verbal reinforcement learning (NeurIPS 2023 · 559 citations)
MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework (ICLR 2024 · 153 citations)
AgentBench: Evaluating LLMs as Agents (ICLR 2024 · 53 citations)
AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases (NeurIPS 2024 · 49 citations)

llm agents · llms · agent systems · 470 papers