NVIDIA 发布 Nemotron 3.5 Lightning，面向长时运行智能体的执行层
NVIDIA Nemotron 3.5 Lightning Delivers Fast, Accurate Specialized Task Execution for Long-Running Agents
NVIDIA 发布 Nemotron 3.5 Lightning，这是一个开放的 30B MoE 模型，激活参数 3B，面向长时运行 AI 智能体的执行层。NVIDIA 指出，长时运行智能体大部分时间花在工具调用、结果校验和子智能体委派等高吞吐执行环节，若每一步都用前沿推理模型会带来额外成本与延迟。
面向长时运行智能体的执行层，给出 30B MoE 与 3B 激活参数的取舍思路，可对照前沿推理模型的高成本方案。
Long-running AI agents spend most of their time on high-volume execution: tool calls, result validation, and subagent delegation. Using a frontier reasoning...
Long-running AI agents spend most of their time on high-volume execution: tool calls, result validation, and subagent delegation. Using a frontier reasoning model for every execution step adds cost and latency. NVIDIA Nemotron 3.5 Lightning is an open 30B mixture-of-experts (MoE) model with 3B active parameters built for that execution layer of always-on agents. It is designed for harnesses…
来源：NVIDIA Developer Blog · developer.nvidia.com