Cisco AI 开发了 FAPO，这是一个开源系统，旨在自主优化多步 LLM 管道。FAPO 使用 Claude Code 来评估、分类故障、提出变体并迭代提示以达到目标准确性。在评估中，FAPO 在大多数基准测试中均优于最先进的提示优化器 GEPA，尤其是在涉及结构性管道更改时，显示出显著的收益。 AI
影响 该工具可以通过自动化提示优化和故障分析来简化 LLM 应用程序的开发和部署。
排序理由 这是来自一家公司的新工具/框架发布，而不是来自主要 AI 实验室的前沿模型发布。
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
<p>Cisco Foundation AI has open-sourced FAPO (Fully Automated Prompt Optimization), a Claude Code-driven system that autonomously optimizes multi-step LLM pipelines from baseline prompts to target accuracy. FAPO evaluates a chain, attributes failures at the step level, proposes v…
Cisco Foundation AI has open-sourced FAPO, a Claude Code-driven system that autonomously optimises multi-step LLM pipelines. It evaluates chains, attributes failures at step level, proposes variants and validates them. In testing it beat GEPA on 15 of 18 model-benchmark compariso…
🤖 Cisco's FAPO Optimizes LLM Pipelines with Claude Code Cisco AI's introduction of FAPO has enabled autonomous optimization of multi step LLM pipelines, outperforming state of the art prompt optimizers like GEPA. This new system, known as Fully Automated Prompt Optimization, dire…