mohamed12ahmed/AgentForge-Bench download history
mohamed12ahmed/AgentForge-Bench is a reinforcement learning dataset on the Hugging Face Hub. In the last 30 days it was downloaded 325 times (120 in the last 7 days), and 325 times in total. It ranks #46,117 among datasets by monthly downloads.
AgentForge-Bench AgentForge-Bench is a benchmark suite for evaluating autonomous AI agents on realistic, multi-step terminal environments. The benchmark focuses on capabilities that become increasingly difficult as the interaction horizon grows: planning, state tracking, dependency re