Event ·Multi-source

Box 基于 Nvidia Nemotron 推出面向智能体的内容检索系统

Box 采用 Nvidia 的 Nemotron 模型构建了一套面向智能体的企业内容检索系统。新系统回答查询的速度提升 4 倍，错误减少 20%，token 消耗降低 90%。这套系统定位为智能体优先的检索架构，让 Agent 在企业文档中定位信息时更快、更省、更准。

Current read

Box 拿 Nvidia 的 Nemotron 重做了内容检索，速度快 4 倍、错误少 20%、token 省九成，做企业 Agent 的可以看看。

11 sources41° AI heatLast updated 2026/11/5 14:00:00

Evidence

11 sources

Primary sourcetechcrunch

2026/11/5 14:00:00View source

Related source 1NVIDIA AI

2026/11/3 17:59:36View source

Related source 2shao__meng

2026/11/3 14:20:07View source

Related source 3AIGCLINK

2026/11/4 02:54:56View source

Related source 4LlamaIndex

2026/11/3 16:49:05View source

Related source 5Fireworks AI

2026/11/3 20:54:43View source

Related source 6vLLM

2026/11/3 23:53:16View source

Related source 7elvis

2026/11/4 12:25:01View source

Related source 8@atomic_chat_hq

2026/11/4 17:53:37View source

Related source 9rohanpaul_ai

2026/11/4 18:20:44View source

Related source 10Gorden Sun

2026/11/3 14:11:14View source

Conflict check

Dedup data only shows that these sources discuss the same event, not that they agree. There is no structured supporting or refuting evidence yet, so no conflict is inferred automatically.

Open the story