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
Code generation and LLM agents
Benchmarks: HumanEval, MBPP, EvalPlus (HumanEval+ / MBPP+), LiveCodeBench and others. Datasets: HumanEval, MBPP, SWE-bench, SWE-bench Verified and others. Baselines: ReAct, Reflexion, CodeAct, SWE-agent and others.