FlowEvo: Self-Evolving Agents through the Co-Evolution of Workflows and Executable Skills
Open paper
Benchmark
Model
Rank
Results
code-generation-on-humaneval
FlowEvo
#16
Pass@1: 95.1
code-generation-on-mbpp
FlowEvo
#35
Accuracy: 79.6
Rank counts only results with a code link.