wangtinghu/agentUniverse
1
0
Fork 0
mirror of https://github.com/agentuniverse-ai/agentUniverse.git synced 2026-02-09 01:59:19 +08:00
Code Issues Packages Projects Releases Wiki Activity

docs: update Creating_and_Using_Agent_Templates.md

Browse Source
This commit is contained in:
Jerry Z H
2025-09-24 17:16:39 +08:00
parent f3a1fc1a4c
commit 827075df15
2 changed files with 4 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
docs/guidebook/en/Get_Start/5.Creating_and_Using_Agent_Templates.md
View File

@@ -14,8 +14,8 @@ In fact, the AU framework provides a considerable number of [agent templates](..
You might have noticed that the standard template comprised of the three agents mentioned above includes Planning (Plan), Executing (Execute), and Expressing (Express). We refer to this as the PEE model. In complex scenarios, we hope this model can further self-evaluate and adjust, so we can add an evaluation node at the end. This is what the PEER framework refers to. PEER uses agents with different responsibilities—Plan, Execute, Express, and Review—to break down complex problems into manageable steps, execute the steps in sequence, and iteratively improve based on feedback, enhancing the performance of reasoning and analysis tasks. Typical use cases: Event interpretation, industry analysis.
# PEER Agent Template
Template Demo：[demo_startup_app_with_agent_templates](../../../../examples/sample_apps/peer_agent_app)
# Example of Using PEER Agent Template
This sample, [Peer Agent App](../../../../examples/sample_apps/peer_agent_app), show a multi-agent application built using the PEER Agent Template.
## Running Test
You can run PEER demo in the [test file](../../../../examples/sample_apps/peer_agent_app/intelligence/test/peer_agent.py).

4
docs/guidebook/zh/开始使用/5.沉淀与使用智能体模版.md
View File

@@ -14,8 +14,8 @@
细心的你可能发现上了上述3个智能体构成的标准模版，包含了策划（Plan）、执行（Execute）、表达（Express），我们将其称为PEE模式。在复杂的场景中，我们希望这种模式可以进一步自我评估与修正，于是我们可以在最后额外加入评估节点，这便是AU框架中提到的PEER模式。该pattern通过计划（Plan）、执行（Execute）、表达（Express）、评价（Review）四个不同职责的智能体，实现对复杂问题的多步拆解、分步执行，并基于评价反馈进行自主迭代，最终提升推理分析类任务表现。典型适用场景：事件解读、行业分析
# PEER智能体模版
样例地址：[demo_startup_app_with_agent_templates](../../../../examples/sample_apps/peer_agent_app)
# PEER智能体模版使用样例
在样例 [Peer Agent App](../../../../examples/sample_apps/peer_agent_app) 中，使用了PEER智能体模版构建了PEER多智能体应用。
## 运行测试
您可以在[测试文件](../../../../examples/sample_apps/peer_agent_app/intelligence/test/peer_agent.py)中完整运行PEER案例。