英伟达 SoL-Pi 通过优化 harness 将编码智能体 token 用量减半
原标题：Nvidia's SoL-Pi system cuts coding agent token usage nearly in half by optimizing the harness
AI 摘要
英伟达研究人员提出 SoL-Pi 系统，通过自动优化编码智能体的控制层（harness）来降低 token 消耗。该系统让一个研究智能体观察另一个智能体的执行轨迹、提出修改并在预设环境中测试，在 535 个可执行环境中探索了 152 个方向，生成超 3000 次运行。在 EdgeBench 的 51 个公开任务上，SoL-Pi 性能与原始 Pi harness 大致相当，token 使用量下降 44.7% 至 49%，最省 token 的变体节省 49% 并达到 Pi 分数的 93.7%。
正文节选
Nvidia's SoL-Pi system cuts coding agent token usage nearly in half by optimizing the harness A new Nvidia paper describes a system that automatically optimizes the control layer of coding agents, known as the harness. Token usage drops by almost half while performance stays roughly the same, according to the researchers. The longer AI agents work unsupervised, the more expensive they get. Single predictions turn into long chains of reasoning, tool calls, and feedback loops, and token usage ball