Fields
Pick a domain and keep going deeper: field, subfield, topic. Every step lists the papers at that point or below it. The counts are papers that are accepted or in review; papers that were not accepted are in the full library.
Field
Multi-agent learning and systems
Multi-agent research studies several learning agents that cooperate, communicate or compete: cooperative multi-agent RL, emergent communication, systems of LLM agents, and game-theoretic learning including zero-shot coordination with unseen partners. Evaluation uses team return or win rate on shared benchmark suites, cross-play with held-out partners, exploitability in games, and for LLM systems task accuracy at a stated token cost.