无需人工标准答案，跨模型形式共识为LLM生成的RTL代码提供高效分诊，直击硬件设计验证痛点。
arXiv:2608.21962v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used to generate register-transfer-level (RTL) designs…
另辟蹊径——不调LLM，训练harness也能让跨模型、跨基准全面涨点，值得一试。
Article URL: https://github.com/workofart/harness-training Comments URL: https://news.ycombinator.com/item?id=49293267 Points: 4 # Comments: 0
用Cards Against Humanity测试大模型间的幽默偏好，看GPT-4o能否猜中Claude的笑点。
arXiv:2608.07481v1 Announce Type: cross Abstract: This paper investigates whether one large language model can approximate the humor preferences of an…
Claude与ChatGPT跨模型协作，共同书写AI发展史，一场有趣的AI自我对话实验
Article URL: https://docs.google.com/document/d/1SuekouRgA8NrQMOJdmpfowesV4-qTQxmhOe54aTYyw8/edit?tab=t.0 Comments URL: https://news.ycombinator.com/i…
跨模型代码审查技能，为Claude Code提供只读协作体验，提升AI编程协作效率。
Article URL: https://github.com/shimo4228/codex-review Comments URL: https://news.ycombinator.com/item?id=48791474 Points: 1 # Comments: 0
揭示LLM在临床表格数据上的认知盲点，提出跨模型归因分歧检测新方法，提升模型可信度与安全应用。
arXiv:2606.19509v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly applied to structured clinical data, yet whether they ca…
首个大规模评估Agent技能的通用框架，填补跨模型、跨领域评估方法空白，推动LLM Agent能力标准化研究。
arXiv:2606.17819v1 Announce Type: cross Abstract: Agent skills -- structured, reusable knowledge artifacts that augment LLM agent capabilities -- have…
一站式接入Chat、图像、视频和音频模型，一个API搞定所有生成任务
One balance. Every model. Chat, image, video & audio. Discussion | Link
研究不同大模型在推理时是否表现出行为一致性，基于共享交互数据提供实证证据。
arXiv:2606.08129v1 Announce Type: new Abstract: Large language models (LLMs) differ in architecture, training data, and optimization procedures, yet t…
突破不同模型家族间的分词器壁垒，提出在策略蒸馏新方法，提升跨模型知识迁移效果。
arXiv:2606.09456v1 Announce Type: new Abstract: On-Policy Distillation (OPD) has become a core technique in the post-training of Large Language Models…
一份结合RAG与跨模型多数投票的评估协议，为在生物医学领域测试ChatGPT的关联生成与验证能力提供了可复现的新方案。
arXiv:2605.30400v1 Announce Type: new Abstract: We present a protocol to evaluate ChatGPT's ability to generate disease-centric biomedical association…
跨模型代理剪枝巧妙兼顾低延迟与高精度，解决长上下文LLM推理中KV缓存内存墙难题
arXiv:2605.16360v1 Announce Type: new Abstract: Efficient long-context inference in Large Language Models (LLMs) is severely constrained by the Key-Va…
Vercel AI Gateway 引入 Parallel 通用网络搜索，跨模型可用，开发更灵活
You can now use Parallel's LLM-optimized web search and other tools all across Vercel. AI Gateway Unlike provider-specific web search tools that only …