Benchmark
NatureBench Lite
A streamlined version of a benchmark that evaluates the performance of agents on natural science research tasks.
Timeline (last 90 days)
Oct 19
The optimization capabilities learned by MLExpert can generalize to NatureBench Lite and algorithm optimization tasks.
Unverified50%
Oct 16
The paper reports improvements of MLExpert on NatureBench Lite, agent scaffold optimization and algorithm optimization, indicating that the model learns a transferable optimization capability.
Unverified50%
All Facts (2)
Unverified
The optimization capabilities learned by MLExpert can generalize to NatureBench Lite and algorithm optimization tasks.
50%UnverifiedThe paper reports improvements of MLExpert on NatureBench Lite, agent scaffold optimization and algorithm optimization, indicating that the model learns a transferable optimization capability.
50%