这篇论文讲怎么在预算有限时选LLM，不是简单路由或采样，而是两者结合。用11个模型和4个基准测试，效果比现有方法好。
论文提出预算感知的测试时模型选择问题，在每次查询给定预算和不完美验证器下，分配预算在重采样（resample）和重路由（reroute）之间以最大化正确率。提出的在线Resample-or-Reroute (RoR)策略基于每单位成本的边际正确性估计。在11个开源模型的池子上，使用4个不同难度的基准进行多轮重放实验，RoR相对于单路由、单次提交路由器、预算感知Best-of-K、级联和随机分配基线实现了更优的成本-质量帕累托前沿。增益在异构性最强的基准上最大，且受验证器质量门控。
Resample or Reroute? Budget-Aware Test-Time Model Selection for Large Language Models
Routing among large language models (LLMs) trades response quality against serving cost, motivated by the reported gap between deployed routers and a per-instance oracle. Recent analysis shows that test-time resampling can recover per-instance selection headroom that no single-commit router captures; however, that guarantee holds only under an idealized oracle equipped with correctness labels and an unconstrained budget, neither of which a deployed system has. To the best of our knowledge, no previous work treats resampling the committed model and rerouting to an alternative model as competing uses of a single per-query cost budget. Therefore, this work formulates budget-aware test-time model selection: given a per-query budget and an imperfect verifier, allocate each unit of budget between resampling and rerouting so that expected correctness is maximized. An online resample-or-reroute (RoR) allocation policy driven by estimated marginal correctness per unit cost is proposed, and its behavior is grounded in the recoverability asymmetry between selection and sampling. Replay experiments on newly regenerated multi-draw correctness tensors from an eleven-model open-weight pool over four benchmarks of differing difficulty show that the proposed RoR policy attains a favorable cost-quality Pareto front relative to single-route, one-commit-router, budget-aware best-of-K, cascade, and random-allocation baselines for the tested pools, with the largest gains on the most heterogeneous benchmark; an ablation further shows the gains are verifier-gated, shrinking as verifier quality degrades, and robustness replays under a provider price vector and a label-free agreement verifier delineate where the conclusions carry over.