对比三种智能体交互模式，提升复杂任务的可靠性和执行效率。
Multi-Paradigm Agent Interaction in Practice:A Systematic Analysis of Generator-Evaluator, ReAct Loop,and Adversarial Evaluation in the buddyMe Framework
- 构建五阶段处理流程，融合生成-评估、ReAct循环与对抗式讨论
- 80%复杂任务经生成评估预审通过，30%工具调用存在冗余
- 70%场景下对抗讨论2-3轮达成共识，适合内容优化而非逻辑纠错
大型语言模型智能体的快速发展催生了多样化的交互范式，但少有生产系统在统一架构中整合多种范式。本文对三种核心交互模式——多智能体编排（生成-评估）、ReAct工具使用循环、记忆增强交互——在开源多模态智能体框架buddyMe中的实现进行了系统分析。我们提出了一个五阶段处理流程：需求预审 -> 任务分解 -> ReAct执行 -> 实际执行验证 -> 对抗评估讨论，并建立六维加权评分体系。基于真实部署日志的四个案例研究涵盖博物馆导览生成、定时天气任务和综合旅游规划，得出三项关键结论：首先，生成-评估预审可发现20%复杂任务的需求遗漏，80%任务通过初始检查；其次，ReAct循环保障子任务稳定执行，但导致约30%工具调用冗余；第三，评估者-防御者对抗讨论在近70%场景中于2-3轮内达成一致，主要作用为内容优化而非逻辑推翻。本文还提供三个Mermaid架构图，并与CrewAI、AutoGen、LangGraph、MemGPT和A-Mem在六个系统维度上进行跨范式比较。研究成果为构建稳定可靠的多范式智能体系统提供了实用设计指南。
原文摘要 · Abstract (English)
The rapid evolution of Large Language Model (LLM) agents has produced diverse interaction paradigms, yet few production systems integrate multiple paradigms within a unified architecture. This paper presents a systematic analysis of three principal agent interaction paradigms, including Multi-Agent Orchestration (Generator-Evaluator), ReAct Tool-Use Loops, and Memory-Augmented Interaction, as implemented in buddyMe, an open-source multi-model agent programming framework. We formalize a five-stage processing pipeline: Requirement Pre-Review -> Task Decomposition -> ReAct Execution -> Real-Execution Verification -> Adversarial Evaluation Discussion, and establish a six-dimensional evaluation schema with weighted scoring. Through four empirical case studies drawn from real-world deployment logs covering museum guide generation, scheduled weather tasks, and comprehensive tour planning, we draw three key conclusions. First, Generator-Evaluator pre-review detects requirement omissions in 20 percent of complex tasks, with 80 percent tasks passing initial inspection. Second, the ReAct loop ensures stable subtask execution but leads to around 30 percent redundant tool invocations. Third, adversarial Evaluator-Defender discussions reach consensus within 2-3 rounds for nearly 70 percent of scenarios, functioning mainly for content refinement rather than logical reversal. We additionally provide three Mermaid-based architectural diagrams and conduct cross-paradigm comparisons with CrewAI, AutoGen, LangGraph, MemGPT and A-Mem across six system dimensions. The research outcomes offer practical design guidelines for constructing stable and reliable multi-paradigm agent systems.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。