跳到正文
arXiv cs.AI· Zhengfeng Yu, Tian Lan, Zhijing Wu, Enbo Zhao, Xuannan Liu, Feihu Jiang, Qianghuai Jia, Longyue Wang, Zhao Xu, Weihua Luo, Xian-Ling Mao·· 2 小时前AI 评分41

CrossEnv 提出可验证跨环境任务合成框架用于长程智能体训练

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

AI 导读

研究者提出 CrossEnv 框架,利用实体-工具图发现环境间连接并对齐任务数据,合成可执行、可验证的跨环境任务,用于长程智能体训练。配套的 CrossEnv-Curriculum 从单环境工具使用逐步过渡到多环境、多业务领域协作,再引入用户交互。

正文 · 原文

Authors:Zhengfeng Yu, Tian Lan, Zhijing Wu, Enbo Zhao, Xuannan Liu, Feihu Jiang, Qianghuai Jia, Longyue Wang, Zhao Xu, Weihua Luo, Xian-Ling Mao

View PDF HTML (experimental)

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.
Comments: 23 pages
Subjects: Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
Cite as: arXiv:2611.22777 [cs.AI]
  (or arXiv:2611.22777v1 [cs.AI] for this version)
  https://doi.org/10.48550/arXiv.2611.22777

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Yu Zhengfeng [view email]
[v1] Tue, 17 Nov 2026 13:44:28 UTC (762 KB)

来源:arXiv cs.AI · arxiv.org