AI 自己造题考自己，越考越难
训练 AI 干「长任务」最贵的是数据：一个任务要同时保证指令、环境、标准答案、判分器四者自洽，人工写一个要花几百到上千美元。这篇让 AI 自己出题：从少量人工验证过的种子任务出发，AI 把答案改长、把判分器和指令同步改掉、再在全新沙盒里跑一遍确认没作弊，通过的题又变成下一轮的种子。15 轮下来造了 3.7 万道题，单题成本降到 5 美分，难度一路飙升——标准答案从 67 行涨到 374 行，最强模型通过率从 90% 跌到 2.5%。拿这些题去微调模型，在三个终端任务基准上最高涨了 10 个点。它不是你明天能用上的东西，但「AI 自己造数据训练自己」这条路，成本曲线和难度曲线都在往对的方向走。
📄 原文摘要(英文)
High-quality long-horizon training data for terminal agents is expensive to produce, often costing hundreds to thousands of dollars per task, because each task must keep the instruction, environment, reference solution, and verifier mutually consistent. Human authoring does not scale, and direct generation with large language models (LLMs) often breaks these dependencies. We present Recursive Synthetic Terminal Tasks (RST), a recursive verified synthesis framework for constructing long-horizon terminal-agent tasks at scale. Starting from verified seed tasks, RST extends the reference solution, realigns the verifier and instruction to the new workflow, validates the result in a fresh sandbox, and reuses accepted tasks as seeds for subsequent rounds. Across fifteen recursive rounds, RST produces 37,484 synthesized terminal-agent tasks at roughly \0.05 per task. Task difficulty increases substantially over rounds: the median reference solution grows from 67 to 374 lines, the median number of executed commands grows from 40 to 244, and DeepSeek-V4-Pro pass@4 drops from 90% at R_1 to 2.5% at R_{15}$. To demonstrate training utility, we collect rejection-sampled Qwen3.5 trajectories on the synthesized tasks and use them for supervised fine-tuning. Fine-tuning on these trajectories improves Qwen3.5-27B and Qwen3.5-122B-A10B by up to 10 points on Terminal-Bench~2, Terminal-Bench Hard, and Long-Horizon Terminal Bench, while agentic PPO lifts Qwen3.5-27B to 49.44\%, 32.00\%, and 22.07\% on the three benchmarks, corresponding to relative gains of 20.0\%, 41.2\%, and 21.9\% over the base model. Moreover, after 15 rounds, the recursion shows no ceiling: synthesis yield and validation rates remain stable as difficulty keeps climbing, indicating that the process can continue well beyond the scale reported here.