Safactory: A Scalable Agentic Infrastructure for Training Trustworthy Autonomous Intelligence

As large models evolve from conversational assistants into autonomous agents, challenges increasingly arise from long-horizon decision making, tool use, and real environment interaction. Existing agenticinfrastructure remain fragmented across evaluation, data management, and agent evolution, making it difficult to discover risks systematically and improve models in a continuous closed loop. In this report, we present $\mathbf{\text{Safactory}}$, a scalable agent factory for trustworthy autonomous intelligence. Safactory integrates three tightly coupled platforms: a $\mathbf{\text{Parallel}}\mathbf{\text{Simulation}}\mathbf{\text{Platform}}$ for trajectory generation, a $\mathbf{\text{Trustworthy}}\mathbf{\text{Data}}\mathbf{\text{Platform}}$ for trajectory storage and experience extraction, and an $\mathbf{\text{Autonomous}}\mathbf{\text{Evolution}}\mathbf{\text{Platform}}$ for asynchronous reinforcement learning and on-policy distillation. As far as we know, Safactory is the first framework to propose a unified evolutionary pipeline for next-generation trustworthy autonomous intelligence.