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.
Subfield
LLM-based multi-agent systems
Benchmarks: GAIA, SWE-bench, HumanEval, GSM8K and others. Datasets: GSM8K, MMLU, HumanEval, GAIA and others. Baselines: Chain-of-thought (single agent), Self-consistency, Multiagent debate, AutoGen and others.