# Elvis Saravia 分享动态工作流讨论笔记

- 来源：elvis (@omarsar0)
- 发布时间：2026-06-26 04:23
- AIHOT 分数：49
- AIHOT 链接：https://aihot.virxact.com/items/cmqtycj8z00c2slcv2lbvmfxf
- 原文链接：https://x.com/omarsar0/status/2070241450227331120

## AI 摘要

动态工作流仅适用于少量用例，可视为测试时计算（TTC）新范式，对爬山式研究实验有效。仔细规划及提升推理级别均可改善效果。/goal + /loop 是其子集，验证者/评判者至关重要。结合不同编码智能体能获更好结果，适合需要多智能体视角的 LLM 评审团场景。前沿模型不擅即时生成 harnesses，但 Mythos 等新模型可能更优地处理智能体编排。TTC 基准尚缺，需建立。元提示动态工作流很有趣，Opus 4.8 也可能带来惊喜。动态工作流可打包为技能以便进一步优化。

## 正文

Just had a great discussion on dynamic workflows.

Rough notes：

- applies to a very small set of use cases
- think of it as a new paradigm of （test-time compute） TTC
- strong for hill-climbing research experiments
- careful planning leads to better results
- you can often get better results by just increasing the reasoning level
- /goal + /loop is a subset of dynamic workflows
- verifiers/judges are crucial to get good results
- combine/fuse different coding agents for even better results
- great for when you need different perspectives from agents （llm council）
- frontier models are not equipped for optimally generating harnesses on the fly
- newer models like Mythos are probably better trained to do more optimal agent orchestration
- benchmarks on TTC are lacking， but we need them to measure how effective dynamic workflows are
- meta prompt dynamic workflows are a lot of fun； even opus 4.8 might surprise you
- dynamic workflows can be packaged as skills for further optimization of them

Longer post coming soon.