cs.AINov 17, 2026

CrossEnv: Synthesizing Verifiable Cross-Environment Tasks for Long-Horizon Agent Training

Authors: Zhengfeng Yu, Tian Lan, Zhijing Wu, Enbo Zhao, Xuannan Liu, Feihu Jiang, Qianghuai Jia, Longyue Wang, 

Organizations: Beijing Institute of Technology · Alibaba Group · Beijing University of Posts and Telecommunications

Abstract

Executable synthetic environments provide scalable training tasks and verifiable feedback for long-horizon agents. Existing environment synthesis methods primarily generate tasks within individual environments. However, these tasks do not adequately capture real-world interactions across services, where actions in one service depend on information obtained from another. Synthesizing such tasks is challenging because data generated across environments must remain consistent to support executable and verifiable interactions. To address this challenge, we introduce CrossEnv, a framework that uses an entity-tool graph to identify connections between environments and aligns task-specific data to synthesize executable, verifiable cross-environment tasks. We further propose CrossEnv-Curriculum, which progresses from single-environment tool use to coordination across more environments and business domains, before introducing user interaction. Across four external benchmarks, combining cross-environment training data with this curriculum achieves competitive performance with fewer training examples. Further analyses support the benefits of cross-environment data and curriculum training, and provide evidence of transfer to new environment combinations, external tasks less similar to the training data, and longer workflows.

Figures & tables

Appendix figures & tables3 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. AgentMercury: Your Agent Can Synthesize Verifiable Environments for Business Scenarios at scale

    Aug 21, 2026Minbyul Jeong, Chanwoong YoonLLM Agent TrainingRL for LLM Agents

  2. EnvCraft: Synthesizing Executable Environments in Agentic RL for Claw-like Agent

    Sep 4, 2026Yirong Zeng, Shen You, Jinhang Feng +8LLM Agent TrainingAgentic RL