Large language models (LLMs) are expected to be trained to act as agents in various real-world environments, but this process relies on rich and varied tool-interaction sandboxes. However, access to real systems is often restricted; LLM-simulated environments are prone to hallucinations and inconsistencies; and manually built sandboxes are hard to scale. In this paper, we propose EnvScaler, an automated framework for scalable tool-interaction environments via programmatic synthesis. EnvScaler comprises two components. First, SkelBuilder constructs diverse environment skeletons through topic mining, logic modeling, and quality evaluation. Then, ScenGenerator generates multiple task scenarios and rule-based trajectory validation functions for each environment. With EnvScaler, we synthesize 191 environments and about 7K scenarios, and apply them to Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) for Qwen3 series models. Results on three benchmarks show that EnvScaler significantly improves LLMs' ability to solve tasks in complex environments involving multi-turn, multi-tool interactions. We release our code and data at https://github.com/RUC-NLPIR/EnvScaler.

翻译：摘要：大型语言模型（LLM）需被训练为能够在各类真实环境中执行任务的智能体，但这一过程依赖于丰富多样的工具交互沙盒。然而，真实系统的访问常受限；LLM模拟环境易产生幻觉与不一致性；人工构建沙盒则难以扩展。本文提出EnvScaler，一种通过程序化合成实现可扩展工具交互环境的自动化框架。EnvScaler包含两个组件：首先，SkelBuilder通过主题挖掘、逻辑建模与质量评估构建多样化的环境骨架；随后，ScenGenerator为每个环境生成多个任务场景与基于规则的轨迹验证函数。借助EnvScaler，我们合成了191个环境及约7000个场景，并将其应用于Qwen3系列模型的监督微调（SFT）与强化学习（RL）。三个基准测试的结果表明，EnvScaler显著提升了LLM在涉及多轮、多工具交互的复杂环境中的任务解决能力。我们已在https://github.com/RUC-NLPIR/EnvScaler 开源代码与数据。