EvoProbe: Evaluation-Driven Benchmark Evolution for LLM Agents
Static benchmarks for large language model (LLM) agents face saturation and data contamination risks, motivating continual updates to evaluation tasks. However, aggregate scores and success rates offer limited insight into specific problem-solving bottlenecks and provide limited guidance for subsequent task design. We...
Qian-Wen Guo, Wei Xie, Xiao-Fang Cai et al.
· 0 citations