本系列介绍增强现代智能体系统可靠性的设计模式，以直观方式逐一介绍每个概念，拆解其目的，然后实现简单可行的版本，演示其如何融入现实世界的智能体系统。本系列一共 14 篇文章，这是第 6 篇。原文：Building the 14 Key Pillars of Agentic AI
优化智能体解决方案需要软件工程确保组件协调、并行运行并与系统高效交互。例如预测执行，会尝试处理可预测查询以降低延迟 ，或者进行冗余执行，即对同一智能体重复执行多次以防单点故障。其他增强现代智能体系统可靠性的模式包括：
- 并行工具：智能体同时执行独立 API 调用以隐藏 I/O 延迟。
- 层级智能体：管理者将任务拆分为由执行智能体处理的小步骤。
- 竞争性智能体组合：多个智能体提出答案，系统选出最佳。
- 冗余执行：即两个或多个智能体解决同一任务以检测错误并提高可靠性。
- 并行检索和混合检索：多种检索策略协同运行以提升上下文质量。
- 多跳检索：智能体通过迭代检索步骤收集更深入、更相关的信息。
还有很多其他模式。
本系列将实现最常用智能体模式背后的基础概念，以直观方式逐一介绍每个概念，拆解其目的，然后实现简单可行的版本，演示其如何融入现实世界的智能体系统。
所有理论和代码都在 GitHub 仓库里：🤖 Agentic Parallelism: A Practical Guide 🚀
代码库组织如下：
erlang
agentic-parallelism/
├── 01_parallel_tool_use.ipynb
├── 02_parallel_hypothesis.ipynb
...
├── 06_competitive_agent_ensembles.ipynb
├── 07_agent_assembly_line.ipynb
├── 08_decentralized_blackboard.ipynb
...
├── 13_parallel_context_preprocessing.ipynb
└── 14_parallel_multi_hop_retrieval.ipynb竞争代理组合
在智能体解决方案中，每个 AI 智能体都有其特定偏见、优势和劣势。
使用多样化代理组合可以降低单一代理产生次优或缺陷输出的风险。
通过结合多模型或提示策略，系统更具韧性，避免单点故障，更有可能产出高质量输出。
这种模式相当于人工智能寻求 "第二意见" 或进行竞争性设计流程。
我们将构建三个风格迥异的文案代理组合，负责撰写产品描述，然后看看评估器如何基于这些代理的输出进行推理，选择最佳方案，从而显著提升质量控制流程。
首先，组合的力量来自其成员的多样性。我们将利用两个不同的 LLM 家族创建三种不同的文案"角色"，以最大化多样性。
python
from langchain_huggingface import HuggingFacePipeline
from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
from langchain_google_vertexai import ChatVertexAI
import torch
# LLM 1: Llama 3 8B Instruct (开源, 通过 Hugging Face 本地部署)
# 为两个角色赋能
model_id = "meta-llama/Meta-Llama-3-8B-Instruct"
tokenizer = AutoTokenizer.from_pretrained(model_id)
hf_model = AutoModelForCausalLM.from_pretrained(
model_id,
torch_dtype=torch.bfloat16,
device_map="auto",
load_in_4bit=True
)
pipe = pipeline("text-generation", model=hf_model, tokenizer=tokenizer, max_new_tokens=1024, do_sample=True, temperature=0.7, top_p=0.9)
llama3_llm = HuggingFacePipeline(pipeline=pipe)
# LLM 2: Claude 3.5 Sonnet on Vertex AI (专有, 基于云服务)
# 使用来自不同厂商的模型和训练方法引入了显著的多样性
claude_sonnet_llm = ChatVertexAI(model_name="claude-3-5-sonnet@001", temperature=0.7)
print("LLMs Initialized: Llama 3 and Claude 3.5 Sonnet are ready to compete.")通过使用两个完全不同的模型 ------ 开源的 Llama 3 和谷歌的 Claude 3.5 Sonnet，确保组合拥有真正的多样性。这些代理拥有不同写作风格、知识门槛和固有偏见，而这正是我们想要的强有力竞争过程。
接下来定义 Pydantic 模型，以结构化文案代理和最终评估器的产出。
python
from langchain_core.pydantic_v1 import BaseModel, Field
from typing import List
class ProductDescription(BaseModel):
"""有标题和正文的结构化产品描述，是文案代理的输出"""
headline: str = Field(description="A catchy, attention-grabbing headline for the product.")
body: str = Field(description="A short paragraph (2-3 sentences) detailing the product's benefits and features.")
class FinalEvaluation(BaseModel):
"""评估器代理的结构化输出，包含最佳描述和详细评论"""
best_description: ProductDescription = Field(description="The winning product description chosen by the judge.")
critique: str = Field(description="A detailed, point-by-point critique explaining why the winner was chosen over the other options, referencing the evaluation criteria.")
winning_agent: str = Field(description="The name of the agent that produced the winning description (e.g., 'Claude_Sonnet_Creative', 'Llama3_Direct', 'Llama3_Luxury').")这些数据模型就是通信协议。
ProductDescription模版确保三家竞争者以相同且一致的格式提交输出。FinalEvaluation模版更为关键，迫使评估器代理不仅要选择一个winning_agent，还要提供详细评审（critique），使决策过程透明且可审计。
现在定义 GraphState 和代理节点。节点将通过辅助功能创建，以减少重复代码。
python
from typing import TypedDict, Annotated, Dict
import operator
import time
class GraphState(TypedDict):
product_name: str
product_category: str
features: str
# 字典存储来自竞争代理的结果，并通过 operator.update 合并
competitor_results: Annotated[Dict[str, ProductDescription], operator.update]
final_evaluation: FinalEvaluation
performance_log: Annotated[List[str], operator.add]
# 创建竞争节点的辅助"工厂"函数
def create_competitor_node(agent_name: str, llm, prompt):
# 每个竞争者都是一条链：提示词 -> LLM -> Pydantic 结构化输出
chain = prompt | llm.with_structured_output(ProductDescription)
def competitor_node(state: GraphState):
print(f"--- [COMPETITOR: {agent_name}] Starting generation... ---")
start_time = time.time()
result = chain.invoke({
"product_name": state['product_name'],
"product_category": state['product_category'],
"features": state['features']
})
execution_time = time.time() - start_time
log = f"[{agent_name}] Completed in {execution_time:.2f}s."
print(log)
# 输出键与代理名称匹配，以便于聚合
return {"competitor_results": {agent_name: result}, "performance_log": [log]}
return competitor_nodecreate_competitor_node 是构建多元化组合的最简单方式，输入名称、LLM 和提示符，返回一个完备的、支持结构化输出的 LangGraph 节点。让我们能够轻松定义三位竞争对手，让每个都有独特的模型和个性。
现在创建三个竞争节点和最终评估器节点。
python
# 使用工厂创建三个竞争节点
# 每个都有不同的模型和提示词组合，以确保多样性
claude_creative_node = create_competitor_node("Claude_Sonnet_Creative", claude_sonnet_llm, claude_creative_prompt)
llama3_direct_node = create_competitor_node("Llama3_Direct", llama3_llm, llama3_direct_prompt)
llama3_luxury_node = create_competitor_node("Llama3_Luxury", llama3_llm, llama3_luxury_prompt)
# 评估器节点
def judge_node(state: GraphState):
"""评估所有竞争者的结果并选出获胜者"""
print("--- [JUDGE] Evaluating competing descriptions... ---")
start_time = time.time()
# 根据评估器提示，将不同描述格式化
descriptions_to_evaluate = ""
for name, desc in state['competitor_results'].items():
descriptions_to_evaluate += f"--- Option from {name} ---\nHeadline: {desc.headline}\nBody: {desc.body}\n\n"
# 创建评估链
judge_chain = judge_prompt | llm.with_structured_output(FinalEvaluation)
evaluation = judge_chain.invoke({
"product_name": state['product_name'],
"descriptions_to_evaluate": descriptions_to_evaluate
})
execution_time = time.time() - start_time
log = f"[Judge] Completed evaluation in {execution_time:.2f}s."
print(log)
return {"final_evaluation": evaluation, "performance_log": [log]}现在确定了组合里的三个代理，有三个不同的文案节点，每个节点都针对不同风格设计，还有一个评估节点负责根据收集到的输出进行最终关键评估。
最后用"扇出扇入"架构组装图。
python
from langgraph.graph import StateGraph, END
workflow = StateGraph(GraphState)
# 添加三个竞争节点
workflow.add_node("claude_creative", claude_creative_node)
workflow.add_node("llama3_direct", llama3_direct_node)
workflow.add_node("llama3_luxury", llama3_luxury_node)
# 添加最终评估节点
workflow.add_node("judge", judge_node)
# 入口点是节点列表，告诉 LangGraph 并行运行这些节点
workflow.set_entry_point(["claude_creative", "llama3_direct", "llama3_luxury"])
# 列表中的边意味着图在继续之前会等待所有边完成，这就是扇入
workflow.add_edge(["claude_creative", "llama3_direct", "llama3_luxury"], "judge")
# 最后一步是评估器决策
workflow.add_edge("judge", END)
app = workflow.compile()
现在进行最后的一对一分析，审视这三种竞争性描述及评估器的最终决定，以理解该组合的好处。
python
import json
print("="*60)
print(" THE COMPETING PRODUCT DESCRIPTIONS")
print("="*60)
for name, desc in final_state['competitor_results'].items():
print(f"\n--- [{name}] ---")
print(f"Headline: {desc['headline']}")
print(f"Body: {desc['body']}")
print("\n" + "="*60)
print(" THE JUDGE'S FINAL VERDICT")
print("="*60)
final_eval = final_state['final_evaluation']
print(f"\nWinning Agent: {final_eval['winning_agent']}\n")
print("Winning Description:")
print(f" - Headline: {final_eval['best_description']['headline']}")
print(f" - Body: {final_eval['best_description']['body']}\n")
print("Judge's Critique:")
print(final_eval['critique'])
print("\n" + "-"*60)
print(" PERFORMANCE ANALYSIS")
print("-"*60)
competitor_times = [7.33, 6.12, 6.45]
judge_time = 8.91
parallel_time = max(competitor_times)
sequential_time = sum(competitor_times)
total_time = parallel_time + judge_time
print(f"\nTotal Execution Time: {total_time:.2f} seconds\n")输出：
python
#### 输出 ####
============================================================
THE COMPETING PRODUCT DESCRIPTIONS
============================================================
--- [Claude_Sonnet_Creative] ---
Headline: Your Life, Unlocked. Your Wellness, Understood.
Body: The Aura Smart Ring is more than a tracker; its your silent wellness partner. Crafted from durable titanium, it deciphers your body signals-sleep, activity, and heart rate-translating them into insights that empower your every day. With a 7-day battery, its always on, always learning, always you.
--- [Llama3_Direct] ---
Headline: Track Everything. Wear Nothing.
Body: Meet the Aura Smart Ring. Get elite sleep and activity tracking, 24/7 heart rate monitoring, and a 7-day battery. Built from tough titanium, it delivers powerful health insights without the bulk of a watch.
--- [Llama3_Luxury] ---
Headline: Master Your Narrative.
Body: For the discerning individual, the Aura Smart Ring is an emblem of effortle...ously engineered from aerospace-grade titanium, it provides a seamless interface to your personal biometrics. Command your well-being with seven days of uninterrupted power and unparalleled insight.
============================================================
THE JUDGES FINAL VERDICT
============================================================
Winning Agent: Claude_Sonnet_Creative
Winning Description:
- Headline: Your Life, Unlocked. Your Wellness, Understood.
- Body: The Aura Smart Ring is more than a tracker; its your silent wellness partner. Crafted from durable titanium, it deciphers your body's signals-sleep, activity, and heart rate-translating them into insights that empower your every day. With a 7-day battery, it's always on, always learning, always you.
------------------------------------------------------------
PERFORMANCE ANALYSIS
------------------------------------------------------------
Total Execution Time: 16.24 seconds最终分析强调了竞争组合模式的两个关键优势。
- 通过多样性+评估器实现高质量：三个代理产生了明显不同的输出 Llama3_Direct（有力）、Llama3_Luxury（理想）和 Claude_Sonnet_Creative（利益驱动）。这种多样性为评估器代理提供了更强有力的评估工具。其最终选择体现了对权衡的明确推理，表明质量来自过程（竞争+评估），而非单一模型。
- 通过并行性实现高性能：所有代理并行运行使流水线速度比顺序执行快了 63%，仅以最慢代理的时间开销，就获得了多样化输出，带来更高的质量和更高的运行效率。
Hi，我是俞凡，一名兼具技术深度与管理视野的技术管理者。曾就职于 Motorola，现任职于 Mavenir，多年带领技术团队，聚焦后端架构与云原生，持续关注 AI 等前沿方向，也关注人的成长，笃信持续学习的力量。在这里，我会分享技术实践与思考。欢迎关注公众号「DeepNoMind」，星标不迷路。也欢迎访问独立站 www.DeepNoMind.com，一起交流成长。