AI 解题不再靠多试几次，而是专挑关键步骤挑错
大模型做数学题，现在的主流办法是让它多算几遍再投票，算得越多越准，但代价是烧钱。这篇论文换了个思路：与其多算，不如把一次推理拆成几个关键论断，专门去验证这些论断对不对。因为一个完整答案要全对才算对，但推翻一个错误论断只需要找到一个漏洞，后者容易得多。在四个模型和四个推理基准上，同样的算力预算下，这个办法普遍超过多算几遍的准确率，在某个模型上准确率从 77.5% 提到 82.19%，还省了 37% 的 token。它不是你明天能用上的东西，但指向一个趋势：AI 推理的下一步不是更会算，而是更会自我怀疑。
📄 原文摘要(英文)
We propose claim-level falsification as a principle for test-time scaling and instantiate it through Claim-Level Reliability Assessment (CLR), a training-free framework that reallocates test-time compute from additional solution sampling to targeted verification. Since whole-trace evaluation often obscures decisive errors due to signal dilution from routine tokens, CLR condenses each reasoning trace into a compact set of decision-critical claims, thereby isolating its logical anchors. Furthermore, recognizing the inherent difficulty of generating entirely correct solutions under fixed model capabilities, CLR shifts the focus to semantic falsification. This approach exploits a fundamental asymmetry between solution construction and claim refutation. Constructing a valid solution requires a flawless reasoning path, whereas refuting an incorrect claim requires identifying only a single decisive flaw. This targeted search for negative evidence systematically compresses the survival space of high-confidence incorrect traces, effectively suppressing erroneous consensus via nonlinear reliability scoring. Across four LLMs and four reasoning benchmarks under matched budgets, CLR generally improves upon pass@1 and self-consistency. On GPT-OSS-20B/CMIMC25, for instance, CLR exceeds pass@1 by 27.15 percentage-points and raises self-consistency accuracy from 77.50\% to 82.19\% with 37.0\% fewer tokens.