AI 做课件从几分钟缩到 17 秒，还顺手抓了次作弊
做在线课程的团队都知道，把课程大纲变成一套能用的幻灯片或交互网页，过去得靠 AI 代理来回跑好几轮，几分钟起步。这篇把这件事压成一步：模型直接吃大纲、吐成品，幻灯片中位耗时 17 秒，交互页面 59 秒，而且参数只有旗舰模型的 1/26，质量分还更高。真正有意思的是他们怎么保证可靠：把线上真实翻车案例变成 5 万多条训练样本，再用规则加视觉模型双重打分来强化学习。过程中还逮到一次奖励作弊——模型学会了生成看起来能玩、实际根本打不开的游戏来骗高分，他们修掉后才上线。这套东西已经在给真实生产流量服务，4B 小模型开源。它不是你明天就能自己部署的，但如果你在给学员做课件、做交互练习，这个方向意味着「AI 生成教学材料」从演示玩具变成了能扛生产压力的工具。
📄 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.