ScaleEnv: Scaling Environment Synthesis from Scratch for Generalist Interactive Tool-Use Agent Training
This addresses the problem of limited environmental diversity for researchers and developers training generalist interactive agents, offering a scalable solution that is incremental in improving synthesis methods.
The paper tackles the scarcity of diverse interactive environments for training generalist agents by introducing ScaleEnv, a framework that synthesizes fully interactive environments and verifiable tasks from scratch, resulting in significant performance improvements on unseen multi-turn tool-use benchmarks like $τ^2$-Bench and VitaBench.
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.