NVIDIA 论文研究多模型系统中的模型选择策略

使用多个相同模型的副本效果更好。多数投票将 HLE 准确率从 29.

4% 提升至 32.2%，但混合模型组大多表现下降。

从单一模型家族中选择候选模型，比所有八种策略中任何一种单独模型都带来了更大的提升。

Banger paper from NVIDIA. It's on the topic of choosing which models go into a multi-agent system. The team compared eight selection strategies, based on size, accuracy, answer diversity and error diversity, across routing, majority vote and LLM-as-judge setups on hard science benchmarks. Larger pools of different open models raised the theoretical best-case accuracy. Achieved accuracy often fell below the single best model in the pool. Using several copies of one model worked better. Majority vote over the best single model raised HLE accuracy from 29.4% to 32.2%, while nearly every mixed-model group declined. Choosing candidates from a single model family gave the largest improvement over a standalone model of all eight strategies. Before adding another model to a router or ensemble, measure what it adds. Paper: arxiv.org/abs/2609.17306 Chat with Paper: academy.dair.ai/papers/mo-mode…📊 4 ⚡

本条情报归属 AITOP「论文」核心栏目，重点聚焦北美前沿实验室与硅谷科技巨头。在跨区域产业观察坐标中，该动态直接关联「AI 开发者工具链、Coding Agent 与工程化实践」研究主线，反映出当前技术演进与商业落地的最新风向。涉及核心实体与技术议题包括：NVIDIA、多模型系统、模型选择、提示词工程，读者可通过下方标签进入对应专题页查阅历史脉络与关联对比。

信源核验说明：本文原始线索采编自「elvis」（@omarsar0），经 AITOP 多维评分管线结构化提炼。截至目前，全网已有 2 家独立信源对该事件进行交叉印证与跟进报道（含 shao__meng 等），属于近期高关注度行业信号。