拆解多模型管线二次处理的收益来源，到底是修订还是重解？实验揭示关键差异。
arXiv:2604.01029v2 Announce Type: replace-cross Abstract: Multi-LLM revision pipelines, in which a second model reviews and improves a draft produced …
多模型协作迭代摘要，让AI自动适配数据特征，ICDAR 2026新方法
arXiv:2608.04307v1 Announce Type: cross Abstract: Text summarization is deceptively difficult. While condensing information seems straightforward, rea…
多LLM系统的信任评估新框架，用结构化专家判断融合不确定性度量，提升系统可靠性。
arXiv:2607.20529v1 Announce Type: cross Abstract: Large Language Model (LLM) ensembles are increasingly used to improve reliability by combining predi…
多LLM协作生成脑肿瘤MRI报告，用视觉指令调优提升准确性，医疗AI新突破。
arXiv:2607.14581v1 Announce Type: cross Abstract: Recent advances in large language models (LLMs) and their extension to vision-language models (VLMs)…
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…
多套大模型协同作战，从临床记录中自动评估病情严重级别，医疗AI落地新思路。
arXiv:2607.05032v1 Announce Type: new Abstract: Background: Disease severity is a multidimensional construct difficult to capture with rule-based appr…
多LLM协同攻克德国IT-Grundschutz自动认证，网络安全合规提效新思路，IEEE背书值得一读
arXiv:2606.25608v1 Announce Type: cross Abstract: This paper presents a novel approach to perform semi-automated BSI IT-Grundschutz certification usin…
多LLM集成AI工作空间，一站式切换不同大模型，提升对话与开发效率。
Hi, over the past 6+ months I have built an ecosystem (libraries, CLI, Desktop) of tools to build or use AI agents. Depending on how close or not clos…
研究表明，多LLM系统的对话行为更多取决于后训练配方，而非模型家族差异，挑战了传统选型策略。
arXiv:2606.20632v1 Announce Type: cross Abstract: Multi-LLM systems use multiple language models to deliberate, judge each other's outputs, or coordin…
利用11个LLM投票达成共识，一个开源项目帮你精准揪出AI幻觉。
Article URL: https://github.com/jaquelinejaque/quorum-saas-starter Comments URL: https://news.ycombinator.com/item?id=48596771 Points: 4 # Comments: 1
提出GPU内存气球技术，实现多LLM服务成本大幅降低，已在超万卡生产环境验证。
arXiv:2505.04021v3 Announce Type: replace-cross Abstract: Inference providers must maintain availability for many LLMs, including low-volume but essen…
多LLM加上本体约束，为预测编码文献碎片化问题提供跨学科证据综合新方案。
arXiv:2606.05206v1 Announce Type: cross Abstract: Fragmentation is common in interdisciplinary fields with diverse methods and theoretical commitments…
多LLM协作推理新范式，TRACER用回合级后悔匹配提升合作效率与推理质量
arXiv:2605.28699v1 Announce Type: new Abstract: Large language models increasingly rely on either reinforcement learning or multi-agent prompting to i…
多LLM辩论新范式：利用自信号驱动，在高效与准确推理间取得突破，节省算力并提升效果。
arXiv:2510.06843v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have exhibited impressive capabilities across diverse applicati…
多LLM协同训练新框架，自适应参考演化提升偏好优化效果。
arXiv:2602.02709v3 Announce Type: replace Abstract: Recent multi-LLM agent systems have shown promising capabilities for automated problem-solving, ye…
多LLM协同交易系统，结合实时排行榜，在Alpaca纸交易环境中验证AI策略表现。
Article URL: https://github.com/achaljhawar/1rok Comments URL: https://news.ycombinator.com/item?id=48144911 Points: 2 # Comments: 0
同时使用多个AI编码助手（Codex、Copilot、Claude Code）是否存风险？Hacker News上的真实讨论。
Hello People, I am using codex and copilot , claude code at the same time for my projects.Does it have potential risks for using all of them ? Comment…