Accio-Lab/RealReplicaBench
RealReplicaBench: Benchmarking Long-Horizon Agents in High-Fidelity, Stateful, and Reproducible Replicas of Real Online Services
Language: HTML
Stars: 521 Issues: 0 Forks: 3
https://github.com/Accio-Lab/RealReplicaBench
Post #13619
1.51K