AI 学会从经验里进化，但离真正变强还差得远
让 AI 自己从干过的活里总结经验、下次干得更顺，这听起来是常识，但一直没人能好好测它到底行不行。这篇论文造了一套专门测「自我进化」的考题：把企业里 CRM、财务、医疗这些真实业务流程拆成一条条规则，让 AI 先做几道只含部分规则的题，再考它做包含新组合规则的题——这样考出来的进步，才能确定是它真从经验里学到了，而不是碰巧见过答案。结果：AI 确实会进化，最高能涨 16 个百分点；但就算进化到最好，离「全知全能」的上限还差一大截。它不是你明天能用上的东西，但给「AI 会不会越用越聪明」这个问题的答案，画了一条诚实的底线。
📄 原文摘要(英文)
Agent self-evolution updates an agent's persistent state from prior experience and reuses it to solve related tasks more effectively. Evaluating self-evolution is difficult: existing benchmarks provide limited coverage of economically valuable task domains, do not always design training and test tasks such that test-time gains can be attributed to training experience, and remain vulnerable to data contamination. We present GDPevo, an evolution-native benchmark grounded in GDP-related enterprise workflows, together with the fully automated data pipeline that generates it. Its core mechanism, rule hybridization, decomposes each enterprise workflow into atomic business rules, distributes subsets of these rules across training tasks, and recombines them in held-out test tasks so that test-time gains are attributable. GDPevo spans CRM, ERP, finance, healthcare, legal, and data-centric workflows. Its V1 release contains 120 tasks in 12 groups, with five training and five held-out test tasks per group. Full automation enables the pipeline to expand the suite to 240 tasks in 24 groups (V2) within two days, providing a practical response to contamination. Using GDPevo, we evaluate four agents, each comprising a harness and a model, under four supervision types. Self-evolution consistently improves held-out accuracy by up to 16.44 percentage points. But the best evolved agents remain far below the fully informed oracle ceiling of 91.6%, indicating that the self-evolution ability of current agents remains far from fully realized. We publicly release the pipeline, benchmark, and full evaluation results at https://github.com/Prism-Shadow/GDPevo.