ScaleEnv: Scaling Environment Synthesis from Scratch for Generalist Interactive Tool-Use Agent Training
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912884856979456 |
|---|---|
| author | Tu, Dunwei Hao, Hongyan Yang, Hansi Chen, Yihao Zhang, Yi-Kai Xia, Zhikang Yang, Yu Sun, Yueqing Liu, Xingchen Shen, Furao Gu, Qi Su, Hui Cai, Xunliang |
| author_facet | Tu, Dunwei Hao, Hongyan Yang, Hansi Chen, Yihao Zhang, Yi-Kai Xia, Zhikang Yang, Yu Sun, Yueqing Liu, Xingchen Shen, Furao Gu, Qi Su, Hui Cai, Xunliang |
| contents | Training generalist agents capable of adapting to diverse scenarios requires interactive environments for self-exploration. However, interactive environments remain critically scarce, and existing synthesis methods suffer from significant limitations regarding environmental diversity and scalability. To address these challenges, we introduce ScaleEnv, a framework that constructs fully interactive environments and verifiable tasks entirely from scratch. Specifically, ScaleEnv ensures environment reliability through procedural testing, and guarantees task completeness and solvability via tool dependency graph expansion and executable action verification. By enabling agents to learn through exploration within ScaleEnv, we demonstrate significant performance improvements on unseen, multi-turn tool-use benchmarks such as $τ^2$-Bench and VitaBench, highlighting strong generalization capabilities. Furthermore, we investigate the relationship between increasing number of domains and model generalization performance, providing empirical evidence that scaling environmental diversity is critical for robust agent learning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_06820 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | ScaleEnv: Scaling Environment Synthesis from Scratch for Generalist Interactive Tool-Use Agent Training Tu, Dunwei Hao, Hongyan Yang, Hansi Chen, Yihao Zhang, Yi-Kai Xia, Zhikang Yang, Yu Sun, Yueqing Liu, Xingchen Shen, Furao Gu, Qi Su, Hui Cai, Xunliang Artificial Intelligence Training generalist agents capable of adapting to diverse scenarios requires interactive environments for self-exploration. However, interactive environments remain critically scarce, and existing synthesis methods suffer from significant limitations regarding environmental diversity and scalability. To address these challenges, we introduce ScaleEnv, a framework that constructs fully interactive environments and verifiable tasks entirely from scratch. Specifically, ScaleEnv ensures environment reliability through procedural testing, and guarantees task completeness and solvability via tool dependency graph expansion and executable action verification. By enabling agents to learn through exploration within ScaleEnv, we demonstrate significant performance improvements on unseen, multi-turn tool-use benchmarks such as $τ^2$-Bench and VitaBench, highlighting strong generalization capabilities. Furthermore, we investigate the relationship between increasing number of domains and model generalization performance, providing empirical evidence that scaling environmental diversity is critical for robust agent learning. |
| title | ScaleEnv: Scaling Environment Synthesis from Scratch for Generalist Interactive Tool-Use Agent Training |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2602.06820 |