NVIDIA 发布 Nemotron 3.5 检索模型系列，提升 Agent 检索效率
原标题：NVIDIA Nemotron 3.5 Embed, Rerank, and Parse: Advancing Agents with World-Class Retrieval Models
AI 摘要
NVIDIA 在 Hugging Face 发布 Nemotron 3.5 检索模型系列，包括 8B/1B 的 Embed 嵌入模型（含 NVFP4 量化版）、8B Rerank 重排模型和 631M 的 Parse 文档解析模型，均开放且可商用。这些模型支持文本与图像的多模态检索、多语言检索和跨模态重排，旨在提升企业级 Agent 工作流的检索质量。评测显示，加入 Rerank 后 Agent 每次查询的推理 token 成本降低约 13%-14%，同时检索准确率提升；Embed 8B 在 ViDoRe v3.1 上以 61.17 nDCG@10 位列稠密检索模型第一。
正文节选
An agent’s answers depend on the evidence it can retrieve. When that evidence is incomplete or irrelevant, the agent will repeat searches and inspect additional documents, consuming more inference tokens before completing the task. Better retrieval can help agents reach grounded answers with fewer wasted tokens. At enterprise scale, that waste leads to massive inefficiencies. Agents need the right retrieval models and systems to reach insights faster. Today, we are expanding the Nemotron Retriev