| title | Tev: Scaling Long-Horizon Agentic Environments with Dense Progress Rewards |
|---|---|
| authors | Wenbo Hu, Shraman Pramanick, Krishna Kumar Singh, Nanyun Peng, Kai-Wei Chang, Yong Jae Lee |
| date | 2026-10-13 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2610.18868 |
| upvotes | 53 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf |
| abstract | Long-horizon agents have drawn growing attention for their ability to work autonomously -- from hours to days -- on economically valuable tasks, a capability essential to automated discovery and recursive self-improvement (RSI). Yet open-source models still struggle on long-horizon tasks, largely for lack of both training data and a working recipe, and scaling both is hard: long, complex tasks are difficult to curate and verify, and their rewards are sparse. We address both. First, we introduce Tev-Gym, the first long-horizon agent training dataset with verifiable, dense, progressive rewards -- 1,170 verified task environments across 7 domains. It is built on a latent-world-first approach that first constructs a latent world: a complete and correct hidden specification of the task domain, workflow, and expected state after each step. Each task is then progressively rendered from this specification into an agent-facing environment, enabling controllable complexity and a natural progress metric. Second, we turn this metric into a training recipe: via progress-potential reward shaping (PPRS), we convert progress into a dense per-step reward that improves training efficiency and makes otherwise-intractable tasks trainable. Training with this recipe yields Tev-27B, which achieves substantial gains on the Agents' Last Exam computing and math sciences domains (ALE-CM), matching GPT-6 Astra and Claude Opus 5 at Pass@5. Despite training only on ALE-related data, it generalizes to the Terminal-Bench (TB) 3.0 and 4.0 subsets, surpassing GLM 5.2 and Gemini 3.7 Flash, and reaches Claude Opus 4.8-level performance on middle-horizon tasks such as TB 2.1. |
cite
@misc{hu2026tev,
title={Tev: Scaling Long-Horizon Agentic Environments with Dense Progress Rewards},
author={Wenbo Hu and Shraman Pramanick and Krishna Kumar Singh and Nanyun Peng and Kai-Wei Chang and Yong Jae Lee},
year={2026},
eprint={2610.18868},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2610.18868}
}