### What problem does this PR solve?

As title

### Type of change

- [x] Documentation Update

Signed-off-by: Jin Hai <haijin.chn@gmail.com>
This commit is contained in:
Jin Hai
2025-11-12 14:20:04 +08:00
committed by GitHub
parent 20b6dafbd8
commit 8406a5ea47
21 changed files with 34 additions and 34 deletions

View File

@ -17,7 +17,7 @@ An Agents response time generally depends on many factors, e.g., the LLMs
- For simple tasks, such as retrieval, rewriting, formatting, or structured data extraction, use concise prompts, remove planning or reasoning instructions, enforce output length limits, and select smaller or Turbo-class models. This significantly reduces latency and cost with minimal impact on quality.
- For complex tasks, like multi-step reasoning, cross-document synthesis, or tool-based workflows, maintain or enhance prompts that include planning, reflection, and verification steps.
- For complex tasks, like multistep reasoning, cross-document synthesis, or tool-based workflows, maintain or enhance prompts that include planning, reflection, and verification steps.
- In multi-Agent orchestration systems, delegate simple subtasks to sub-Agents using smaller, faster models, and reserve more powerful models for the lead Agent to handle complexity and uncertainty.