给AI发“进度条”：长任务训练的新配方
训练AI干长活（几小时到几天）一直卡在“奖励稀疏”：任务太长，中间没有反馈，模型不知道自己做对了没。这篇论文换了个思路：先给任务写一份“隐藏剧本”——每一步之后世界应该变成什么样，然后按剧本把任务渲染出来，每一步都能算出“离终点还有多远”，把这个距离变成每一步的奖励。用这套方法训出的27B模型，在长任务考试里追平了GPT-6和Claude Opus 5，还能迁移到没练过的任务上。它不是你明天能用上的，但“给长任务造进度条”这个思路，可能是让AI真正能独立干完一整天活的钥匙。
📄 原文摘要(英文)
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.