Safactory: A Scalable Agentic Infrastructure for Training Trustworthy Autonomous Intelligence
On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks
Abstract (arXiv)
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 Safactory, a scalable agent factory for trustworthy autonomous intelligence. Safactory integrates three tightly coupled platforms: a Parallel Simulation Platform for trajectory generation, a Trustworthy Data Platform for trajectory storage and experience extraction, and an 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.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 39 of its 101 references that are in the map. First posted on arXiv 7 May 2026.
Builds on
39 of 101 references.
Closest ancestors · 3
Same direction, newest first
- 2025Scaling Agents via Continual Pre-training16 Sep
- 2025GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models8 Aug
- 2025Kimi K2: Open Agentic Intelligence28 Jul
Other references · 36
- 2023GPT-4 Technical Reportcited by 18,132
- 2025Qwen3 Technical Reportcited by 8,195
- 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,146
- 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,634
- 2022Constitutional AI: Harmlessness from AI Feedbackcited by 2,950
- 2024Qwen2 Technical Reportcited by 2,076
- 2021DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharingcited by 1,219
- 2025Kimi k1.5: Scaling Reinforcement Learning with LLMscited by 1,193
- 2023Instruction-Following Evaluation for Large Language Modelscited by 1,143
- 2023Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversationscited by 1,124
- 2024DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Modelcited by 1,093
- 2025DeepSeek-V3.2: Pushing the Frontier of Open Large Language Modelscited by 755
24 more
- 2024DeepSeek-V3 Technical Reportcited by 724
- 2026GLM-5: from Vibe Coding to Agentic Engineeringcited by 502
- 2023What Makes Good Data for Alignment? A Comprehensive Study of Automatic Data Selection in Instruction Tuningcited by 354
- 2026SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Taskscited by 289
- 2026SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learningcited by 252
- 2025AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoningcited by 234
- 2025EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agentscited by 213
- 2026Learning beyond Teacher: Generalized On-Policy Distillation with Reward Extrapolationcited by 157
- 2026A Survey of On-Policy Distillation for Large Language Modelscited by 148
- 2026MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agentscited by 129
- 2025Qwen3Guard Technical Reportcited by 125
- 2025ELEPHANT: Measuring and understanding social sycophancy in LLMscited by 115
- 2023DeepSpeed-Chat: Easy, Fast and Affordable RLHF Training of ChatGPT-like Models at All Scalescited by 107
- 2026EvoSkill: Automated Skill Discovery for Multi-Agent Systemscited by 96
- 2025Agent Lightning: Train ANY AI Agents with Reinforcement Learningcited by 94
- 2024How to Train Data-Efficient LLMscited by 91
- 2024OpenRLHF: An Easy-to-use, Scalable and High-performance RLHF Frameworkcited by 70
- 2024Arena Learning: Build Data Flywheel for LLMs Post-training via Simulated Chatbot Arenacited by 26
- 2025Predictive Data Selection: The Data That Predicts Is the Data That Teachescited by 20
- 2026OpenRT: An Open-Source Red Teaming Framework for Multimodal LLMscited by 18
- 2025OpenDataArena: A Fair and Open Arena for Benchmarking Post-Training Dataset Valuecited by 15
- 2025GhostEI-Bench: Do Mobile Agents Resilience to Environmental Injection in Dynamic On-Device Environments?cited by 12
- 2025MultiPriv: Benchmarking Individual-Level Privacy Reasoning in Vision-Language Modelscited by 5
- 2026SciDataCopilot: An Agentic Data Preparation Framework for AGI-driven Scientific Discoverycited by 2
Built on by
Citing papers per year: 2026: 1.
1 paper.
Similar, not cited
Close in wording, no citation either way
- 2026Towards trustworthy agentic AI: a comprehensive survey of safety, robustness, privacy, and system security
- 2026Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence
- 2026Trustworthy Agentic AI: A Comprehensive Cybersecurity and Systems Survey on Threat Landscapes, Defense Architectures, and Open Challenges
- 2026Trustworthy Agent Network: Trust in Agent Networks Must Be Baked In, Not Bolted On
- 2025AI Agents: Evolution, Architecture, and Real-World Applications
- 2026EnvFactory: Scaling Tool-Use Agents via Executable Environments Synthesis and Robust RL
- 2025Designing The Internet of Agents: A Framework for Trustworthy, Transparent, and Collaborative Human-Agent Interaction (HAX)
- 2025A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence