AI自己出题自己考，反而进步更快
让AI变聪明，通常要么调模型参数，要么给它更多数据。但有个新路子：在文字空间里直接改AI的“解题思路”和“评分标准”，而且让两者互相追赶。研究者发现，如果只让AI自己出题自己考，它容易把题目出简单来刷分。于是他们让“解题AI”和“出题AI”分开进化：解题的只看每道题的具体得分，出题的则专门找解题AI的薄弱环节——比如覆盖了哪些要求、能不能区分好答案和坏答案。结果在5个测试集上，这种“分头进化”比之前最好的方法平均再提升2.8%-5.0%。它不是你明天能用上的，但揭示了一个反直觉的方向：让AI自己给自己制造“有效困难”，比让它刷分更能成长。
📄 原文摘要(英文)
Text-space optimization adapts large language models (LLMs) by editing external natural-language artifacts rather than model weights, so the optimized artifacts remain inspectable and the model can be treated as a black box. However, most existing text-space methods keep evaluation fixed. On open-ended tasks, this can become a bottleneck: once the solver improves on the criteria a rubric measures, omitted dimensions remain invisible to the optimization signal. Simply evolving the rubric is also unreliable when updates are selected by the current solver's score, because apparent progress can come from making the rubric easier to satisfy. We introduce DecoEvo (Decoupled Co-Evolution), which co-evolves a solver skill and a rubric-generator skill under decoupled objectives without using gold rubrics during optimization. The solver skill is updated using criterion-level feedback, while the rubric-generator skill is revised through complementary audits of requirement coverage and response discrimination that are independent of aggregate solver score. This separation focuses generator updates on newly exposed solver weaknesses, reducing repeated emphasis on criteria the solver already satisfies. Under each benchmark's official evaluation, DecoEvo outperforms all compared methods across five benchmarks and three LLM backbones, yielding 2.8--5.0\% relative gains over SkillOpt in the five-benchmark average.