AI Mindmeld:面向LLM的潜在互联协议
原标题:AI Mindmeld: A Latent Interconnect Protocol
AI 摘要
该论文提出潜在互联协议(LIP),让大语言模型直接接收专家模型的高维潜在表示,而非将其转译为文本、图像等人类媒介,以突破模型间通信的带宽瓶颈。作者将三个蛋白质专家和三个小分子专家连接到Gemma 3(4B/12B)与Kimi K2.6(1T总参数、32B激活参数),保持所有预训练模型冻结,仅训练连接器。实验显示独立训练的连接器可提供有用信息并支持零样本跨域任务迁移,但也暴露出当前LLM未接受过将专家表示作为原生输入的训练,难以可靠解释和整合这些信息。作者开源了数据、预训练连接器及训练评估代码。
正文节选
AI Mindmeld: A Latent Interconnect Protocol Abstract Large language models (LLMs) are powerful tools for science, and tool calling enables them to act as autonomous agents that consult specialist models, run calculations and carry out experiments. To guide an agent’s reasoning, however, specialist information must enter the LLM’s context. Current-generation LLMs generally require that information to be translated into text, images, audio or video—a severe bottleneck between models that natively