https://guijiagi.com/tags/%E6%96%B9%E6%B3%95%E8%AE%BA/Recent content in 方法论 on 硅基 AGI · 智能体学习与测评Hugozh-cn本站内容采用 CC BY-NC-SA 4.0 国际许可协议授权Sun, 28 Jun 2026 11:25:00 +0800https://guijiagi.com/posts/agent-performance-benchmark-methodology-2026/Sun, 28 Jun 2026 11:25:00 +0800https://guijiagi.com/posts/agent-performance-benchmark-methodology-2026/构建Agent性能基准测试体系，涵盖延迟、吞吐量、成本、质量四维评估方法论https://guijiagi.com/posts/system-prompt-design-methodology/Sun, 28 Jun 2026 10:15:00 +0800https://guijiagi.com/posts/system-prompt-design-methodology/系统化System Prompt设计方法论：从角色定义、约束设定到知识注入的完整框架https://guijiagi.com/posts/agent-canary-release/Sat, 27 Jun 2026 15:00:00 +0800https://guijiagi.com/posts/agent-canary-release/AI Agent灰度发布方法论https://guijiagi.com/posts/llm-red-team-methodology/Sat, 27 Jun 2026 15:00:00 +0800https://guijiagi.com/posts/llm-red-team-methodology/大模型红队测试方法论https://guijiagi.com/posts/pretraining-data-cleaning/Sat, 27 Jun 2026 15:00:00 +0800https://guijiagi.com/posts/pretraining-data-cleaning/大模型预训练数据清洗方法论https://guijiagi.com/posts/multimodal-eval-methodology/Sat, 27 Jun 2026 15:00:00 +0800https://guijiagi.com/posts/multimodal-eval-methodology/多模态模型评测方法论https://guijiagi.com/posts/agent-benchmark-methodology/Wed, 24 Jun 2026 14:00:00 +0800https://guijiagi.com/posts/agent-benchmark-methodology/系统讲解 Agent 基准测试的设计原则、测试集构建、评估指标体系及主流基准对比