AI 会从自己的错误里学习吗？新测试说：没那么简单
我们总以为 AI 会像人一样，做错一次就记住、下次改。这篇论文专门测了这件事：让大模型在文字游戏里自己试错、自己判断对错、再用经验改进自己。结果很反直觉：AI 的自我改进既不自动也不稳定。有的模型靠记住完整过程进步明显，有的靠提炼成策略规则更好，还有的干脆越练越差——在部分任务上，训练反而带来严重负迁移。关键发现是：AI 能认出自己做对了什么，不等于能把这份经验变成下次可用的行动规则。这不是你明天能用上的东西，但它划出了一条重要边界：AI 的「成长」远没有我们以为的那么理所当然。
📄 原文摘要(英文)
Large language models (LLMs) increasingly interact with external environments and accumulate substantial behavioral experience, yet existing agent benchmarks largely evaluate them as fixed policies. It therefore remains unclear whether an agent can actively test its behavior, judge the resulting experience, and use that experience to improve future decisions. We introduce S\textsuperscript{3Gym}, an interactive benchmark for evaluating LLM self-improvement through three coupled capabilities: Self-Testing, Self-Judging, and Self-Improvement. S^3Gym separates permissive exploration from strict held-out evaluation and instantiates this protocol in seven text-based games with executable environment verifiers. We evaluate three pathways for incorporating interaction experience: direct History ICL, score-conditioned Summary Memory, and parameter Training. Our experiments reveal that self-improvement is neither automatic nor uniform. Context-level experience improves performance for several model--game pairs, but the most effective pathway depends strongly on the task structure: summaries are beneficial when experience can be compressed into reusable strategic rules, yet often underperform raw history when success depends on precise, state-contingent information. Parameter training produces substantial gains on some tasks, but also exhibits unstable improvement and severe negative transfer on others. These findings show that recognizing successful actions is insufficient; agents must also transform feedback into executable and transferable policies. S^3Gym provides a unified framework for diagnosing this process and identifying the bottlenecks that prevent agents from translating interaction experience into reliable self-improvement.