多数投票假设被质疑：这篇研究通过能力控制的审计方法，检验现有多样性指标是否真实衡量了LLM集成中的多样性，结果或有颠覆性。
arXiv:2607.20768v1 Announce Type: cross Abstract: Majority voting over LLMs is widely assumed to benefit from diversity, and diversity measures are us…
一门将大语言模型融入多变量微积分课程的创新学习资源，互动讲解向量基础。
Article URL: https://calculus.academa.ai/ Comments URL: https://news.ycombinator.com/item?id=48964585 Points: 23 # Comments: 14
用多LLM集成发现Cisco CUCM 9.8级0day，含完整PoC与技术分析，展示AI驱动的漏洞挖掘新范式。
AI-driven platform using multi-LLM ensemble to discover and disclose critical 0-days. First case study: CVSS 9.8 unauthenticated RCE chain in Cisco CU…
把DeepSeek等第三方LLM当作Claude Code的智能助手，轻松扩展多模型协作工作流。
Article URL: https://github.com/ethanhq/cc-fleet Comments URL: https://news.ycombinator.com/item?id=48614868 Points: 1 # Comments: 0
通过LLM集成提升死亡率预测界面的易用性与可靠性，非专家用户也能轻松上手
arXiv:2606.06235v1 Announce Type: cross Abstract: Mortality forecasting plays an important role in actuarial and policy decision-making, but its imple…
互补代理混合让大模型集成更鲁棒，突破传统集成方法的能力边界
arXiv:2605.24048v1 Announce Type: cross Abstract: Multi-AI collaboration, such as ensembling or debating large language models (LLMs), is a promising …
从混合模型视角重新定义LLM集成，提出新理论框架，ICML 2026 Spotlight论文
arXiv:2605.00419v2 Announce Type: replace Abstract: Model ensembling is a well-established technique for improving the performance of machine learning…