Accio-org/CommerceAgentBench
CommerceAgentBench: Benchmarking Long-Horizon Agents in High-Fidelity, Stateful, and Reproducible Replicas of Real Online Services
正在读取项目信息…
CommerceAgentBench: Benchmarking Long-Horizon Agents in High-Fidelity, Stateful, and Reproducible Replicas of Real Online Services