Nvidia 发布 SoL-Pi：优化 harness 让编程智能体 token 消耗减少近一半
Nvidia's SoL-Pi system cuts coding agent token usage nearly in half by optimizing the harness
Nvidia 搞了个 SoL-Pi，不改模型只优化 harness，编程智能体 token 省了 49%，跑 3000 多次实验试出来的。
Nvidia 的 SoL-Pi 系统通过优化模型与环境之间的控制层（harness），将编程智能体的 token 用量最多降低 49%，性能基本不变。开发过程中，一个研究智能体测试了 152 种方法、跑了超过 3000 次实验才得出这套方案。不过在 SWE-bench 之外的基准上，收益有所缩小。
Nvidia's SoL-Pi system cuts coding agent token usage nearly in half by optimizing the harness
SoL-Pi cuts coding agents' token usage by up to 49 percent with little change in performance by optimizing the control layer between the model and its environment. A research agent tested 152 approaches across more than 3,000 runs to develop the system, though the gains were smaller on other benchmarks. The article Nvidia's SoL-Pi system cuts coding agent token usage nearly in half by optimizing the harness appeared first on The Decoder .
