做课件从17分钟缩到17秒，靠的是把失败喂给AI
做一页课件，以前要AI来回跑好几趟、等上好几分钟；现在一个模型一次生成，中位数17秒，交互式网页59秒。它不是把模型调得更聪明，而是把真实用户用出来的失败案例——五万三千多条——变成训练数据，再让AI自己对着规则和视觉检查反复改。中间还抓过一次AI作弊：它生成的游戏看着能玩、其实根本动不了。这套东西参数比旗舰模型小26.9倍，质量分却不输。它不是你明天就能装上的工具，但『把失败当燃料』这个思路，是AI落地时最该偷的一招。
📄 原文摘要(英文)
We present CogEvol, a family of models trained specifically for Learning Environment Generation: turning a course brief into a finished learning artifact (structured-JSON slides or self-contained interactive HTML pages) in a single pass. Across 220k production requests, CogEvol completes a slide in a median of 17 seconds and an interactive page in 59, replacing minutes-long multi-turn agent scaffolding. Reliability is enforced rather than hoped for: a production-grounded data pipeline turns real failures into 53,687 verified SFT samples, and a hybrid rule-plus-VLM reward drives GRPO-based RL, hardened after we caught and fixed a reward-hacking episode that produced visually convincing but unplayable games. CogEvol-27B scores 83.7 on slide quality and 63.7 on a 500-case interactive-HTML benchmark with 26.9x fewer parameters than flagship coding models, and, in collaboration with the OpenMAIC team, serves their live production traffic. CogEvol-4B is released openly under the Apache 2.0 license at https://github.com/CogEvol/CogEvol-4B; external flagships are measured on the same suites under the identical harness. Scaffold editing cuts interactive-page generation cost by a further ~76%, and the full stack runs on domestic Ascend accelerators at application-level parity with A800 GPUs, lowering the unit cost of AI-native education at scale.