给AI一个模糊目标，它自己会学吗？
我们总以为AI的进步靠的是人类把任务拆得清清楚楚；这篇偏要反过来，只给AI一句「变得更好」这种模糊目标，看它能不能自己决定学什么、怎么学、学没学会。研究者搭了个叫ASPIRE的考场：只给自然语言的能力目标，下游考题全部藏起来，AI得自己挑数据、选更新方法、自己判断何时该停下来。结果很诚实：AI能跑完整个「学习流程」，但真正让模型变强的权重级提升又少又不稳，最强的AI也打不过人类工程师手调出来的系统。它不是你明天能用上的东西，但它戳破了一个正在流行的幻觉——AI能自我进化。至少现在，它更擅长的是「看起来很努力」。
📄 原文摘要(英文)
Many important forms of human learning begin with a vague goal, such as "become a better physicist" or "improve at research." Learners must interpret the goal, identify capability gaps, decide how to learn, and determine whether they have actually improved. In contrast, existing work on LLM self-evolution typically begins with tasks and evaluation metrics specified by humans, reducing self-evolution to optimizing an explicit objective rather than deciding what and how to learn. We introduce ASPIRE, a benchmark for vague-goal-driven self-evolution. ASPIRE provides only a natural-language capability goal while downstream evaluation tasks remain hidden. The agent must operationalize the goal by choosing data and update methods, constructing training and validation signals, and deciding when to evaluate. ASPIRE supports both model-weight and agent-harness evolution in a unified interactive environment and evaluates the resulting systems on a hidden, expert-authored set of 520 items spanning six goals. Our experiments show that vague goals redirect search effort toward goal interpretation. Current agents routinely complete training and harness-editing loops, but weight-level gains remain sparse and unstable, and the strongest evolved harness remains below the engineered Qwen-Agent reference. Agents often train on mismatched data and trust narrow self-evaluations, so local gains fail to transfer to hidden evaluation and continued search and training can erase earlier improvements.