Benchmark Agent is an autonomous agentic system that constructs benchmarks for LLMs and MLLMs via query analysis, subtask design, annotation and quality control, yielding 15 benchmarks with minimal human input.
One-eval: An agentic system for automated and traceable llm evaluation.arXiv preprint arXiv:2603.09821, 2026
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Benchmark Everything Everywhere All at Once
Benchmark Agent is an autonomous agentic system that constructs benchmarks for LLMs and MLLMs via query analysis, subtask design, annotation and quality control, yielding 15 benchmarks with minimal human input.