用AI造出AI的训练场，连最强模型都只解对六成
训练AI智能体最贵的是真实环境：让它真去操作电脑，慢、贵、还有安全风险。这篇论文干脆用AI自己来造训练场——一个能同时支持鼠标点击、调用工具、敲命令行的虚拟电脑环境，而且全程只用开源模型生成，不靠GPT-4这类闭源巨头。造出来的341个任务，每个都要上百步才能完成，连目前最强的GPT-6-Astra都只能解对60%。用这些虚拟世界训练出来的两个小模型，在8个没见过的真实测试里全面超过原版。它不是你明天能用上的产品，但指向一个关键趋势：AI的训练数据，正在从「人类录的」变成「AI自己造的」——当合成环境足够逼真，智能体就能在虚拟世界里无限试错，这可能是突破数据瓶颈的一条真路。
📄 原文摘要(英文)
Agent learning is shifting from learning from human data toward learning through interaction with the world. However, scaling such learning directly in real-world computer systems is challenging and can introduce substantial security risks. We therefore propose Agent World Model in the Wild (WildAWM), a scalable pipeline for synthesizing controllable environments and tasks for training general computer-use agents (CUAs). Whereas existing approaches typically specialize in a single agent interaction interface, we construct executable environments that jointly support graphical user interfaces, model context protocol services, and command-line interfaces, allowing agents to flexibly combine visual interaction, tool use, and code execution. WildAWM is entirely powered by open-source models, demonstrating that high-quality computer-use environments can be generated without proprietary frontier models. Beyond environments, we address three recurring challenges in task synthesis: ensuring solvability, maintaining sufficient difficulty, and producing reliable verifiers, by introducing execution-based quality gates that combine heterogeneous agent rollouts, cross-judge consistency checks, and counterfactual probes of judgment robustness. The resulting pipeline synthesizes 341 long-horizon environment-task pairs that can require over 100 agent steps to solve and remain challenging even for frontier models, with GPT-6-Astra solving only 60% of them. We train two Qwen models of different sizes exclusively in these synthetic worlds. Both models achieve substantial gains across 8 out-of-distribution benchmarks spanning web, claw, and computer-use agents, demonstrating that learning in WildAWM's synthesized worlds generalizes broadly to unseen computer-use tasks. The code is publicly available at https://github.com/MSR-Orchard/WildAWM.