arXiv cs.CL· Zhengfeng Yu, Tian Lan, Zhijing Wu, Enbo Zhao, Xuannan Liu, Feihu Jiang, Qianghuai Jia, Longyue Wang, Zhao Xu, Weihua Luo, Xian-Ling Mao·· 23 小时前AI 评分38
CrossEnv:为长程智能体训练合成可验证的跨环境任务
CrossEnv: Synthesizing Verifiable Cross-Environment Tasks for Long-Horizon Agent Training
AI 导读
CrossEnv 框架利用实体-工具图识别环境间的连接并对齐任务数据,合成可执行、可验证的跨环境任务,解决现有方法只在单一环境内生成任务、难以刻画跨服务依赖的问题。
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
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.CL · arxiv.org