Safactory: A Scalable Agentic Infrastructure for Training Trustworthy Autonomous Intelligence

TL;DR

Safactory is a comprehensive, scalable framework integrating simulation, data, and evolution platforms to develop trustworthy autonomous agents capable of complex decision-making and continuous improvement.

Contribution

It introduces the first unified evolutionary pipeline for trustworthy autonomous intelligence, combining simulation, data management, and reinforcement learning.

Findings

First unified framework for autonomous agent evolution.

Integrates simulation, data, and learning platforms.

Enables systematic risk discovery and continuous model improvement.

Abstract

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 \textbf{Safactory}, a scalable agent factory for trustworthy autonomous intelligence. Safactory integrates three tightly coupled platforms: a \textbf{Parallel Simulation Platform} for trajectory generation, a \textbf{Trustworthy Data Platform} for trajectory storage and experience extraction, and an \textbf{Autonomous Evolution 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.