“model-routing”的搜索结果

Maintain reference test data and expected results for model-routing audits, which analyze how AI models are selected. Investigate mismatches, update outputs after intentional behavior changes, and add captured workflow runs as new test cases.

中文简介正在准备中。当前显示英语简介。

• Investigating failures in model-routing reference tests
• Updating expected results after intentional analysis changes
• Adding workflow runs as new reference test cases

在 Codex App 中为复杂、可并行的知识工作或编程任务自动创建多个可指定模型与推理强度的后台任务，由主 Agent 负责规划、分工、集成和验收。用于多来源调研、多章节内容、复杂 Skill/PPT、跨模块开发、独立验证或 2 个以上互不依赖工作流；也用于用户明确要求模型路由、后台 Worker、Agents Team 或持久项目协作。简单问答、状态查询、单文件小改、强顺序任务和发布/付款/删除/账户操作不得自动触发。

中文简介正在准备中。当前显示原文说明。

Use to pick the cheapest good-enough model or effort for a turn or a delegated task (lanes small to escalate), to decide continue/retry/verify/escalate/complete after each cycle, or to tune routing.

中文简介正在准备中。当前显示原文说明。

Split the Plan/Act/Verify loop across three model tiers — frontier planner, cheap executor, frontier judge — via env vars read by run.sh.

中文简介正在准备中。当前显示原文说明。

Dynamic model selection based on task complexity scoring. Replaces static model mappings with a weighted signal system that picks Opus, Sonnet, or Haiku-class speed per task. Works with agent-assignment-matrix.md.

中文简介正在准备中。当前显示原文说明。

Measurement-driven model router for Claude Code. Routes Haiku/Sonnet/Opus per task class, logs every routed task with real $ numbers, and A/B tests cheaper tiers before you trust the savings.

中文简介正在准备中。当前显示原文说明。