A survey of evaluation methods for LLM-based agents from five perspectives, identifying trends toward realistic benchmarks and gaps in safety, cost-efficiency, and robustness.
Advances in Neural Information Processing Systems, 36:38975–38987
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Survey on Evaluation of LLM-based Agents
A survey of evaluation methods for LLM-based agents from five perspectives, identifying trends toward realistic benchmarks and gaps in safety, cost-efficiency, and robustness.