Multi-Paradigm Agent Interaction in Practice:A Systematic Analysis of Generator-Evaluator, ReAct Loop,and Adversarial Evaluation in the buddyMe Framework

• URL: http://arxiv.org/abs/2605.16821v1
• Date: Sat, 16 May 2026 05:35:50 GMT
• Title: Multi-Paradigm Agent Interaction in Practice:A Systematic Analysis of Generator-Evaluator, ReAct Loop,and Adversarial Evaluation in the buddyMe Framework
• Abstract summary: 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.
• Score: 17.155004351157093
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Agentic AI and Retrieval-Augmented Models in Straight-Through Underwriting [7.670757733138505]
  Actuaries now face a design space that ranges from traditional rule-based automation to large language models.<n>This paper examines how these emerging architectures can support actuarial priorities such as transparency, auditability, and human-in-the-loop governance.
  arXiv  Detail & Related papers  (2026-07-08T18:43:34Z)
• DuMate-DeepResearch: An Auditable Multi-Agent System with Recursive Search and Rubric-Grounded Reasoning [58.09293442211248]
  Deep Research (DR) has emerged as a new agentic paradigm to tackle complex, open-ended research tasks.<n>This report presents DuMate-DeepResearch, a multi-agent DR framework built on the Qianfan Agent Foundry.
  arXiv  Detail & Related papers  (2026-06-05T14:10:48Z)
• EngiAI: A Multi-Agent Framework and Benchmark Suite for LLM-Driven Engineering Design [0.4499833362998488]
  We introduce a benchmark suite with three evaluation dimensions.<n>We present EngiAI, a Multi-Agent System (MAS) implementation built on LangGraph.
  arXiv  Detail & Related papers  (2026-05-19T12:12:09Z)
• Agent-First Tool API: A Semantic Interface Paradigm for Enterprise AI Agent Systems [1.3259123126940986]
  We propose the Agent-First Tool API paradigm, which decomposes tool interactions into search, resolve, preview, execute, verify, and recover phases.<n>The paradigm is implemented and validated in a production multi-tenant platform serving 85 registered tools across 6 business domains.
  arXiv  Detail & Related papers  (2026-05-11T13:30:43Z)
• ABSTRAL: Automatic Design of Multi-Agent Systems Through Iterative Refinement and Topology Optimization [0.033246582398800045]
  We introduce ABSTRAL, a framework that treats MAS architecture as an evolving natural-language document.<n>Under fixed turn budgets, ensembles achieve only 26% turn efficiency, with 66% of tasks exhausting the limit.<n> contrastive trace analysis discovers specialist roles absent from any initial design.
  arXiv  Detail & Related papers  (2026-03-24T04:28:07Z)
• DOVA: Deliberation-First Multi-Agent Orchestration for Autonomous Research Automation [0.0]
  Large language model (LLM) agents have demonstrated remarkable capabilities in tool use, reasoning, and code generation.<n>We present DOVA (Deep Orchestrated Versatile Agent), a multi-agent platform introducing three key innovations.<n>We formalize the core algorithms, present an architectural ablation study across seven system configurations, and analyze the contribution of each component to answer confidence, source coverage, and token efficiency.
  arXiv  Detail & Related papers  (2026-03-04T20:58:40Z)
• MC-Search: Evaluating and Enhancing Multimodal Agentic Search with Structured Long Reasoning Chains [79.14584837105808]
  We present MC-Search, the first benchmark for agentic MM-RAG with long, step-wise annotated reasoning chains spanning five representative reasoning structures.<n>Beyond answer accuracy, MC-Search introduces new process-level metrics for reasoning quality, stepwise retrieval and planning accuracy.<n>By developing a unified agentic MM-RAG pipeline, we benchmark six leading MLLMs and reveal systematic issues such as over- and under-retrieval and modality-misaligned planning.
  arXiv  Detail & Related papers  (2026-03-01T02:25:57Z)
• MagicAgent: Towards Generalized Agent Planning [73.21129030631421]
  We present textbfMagicAgent, a series of foundation models specifically designed for generalized agent planning.<n>We introduce a lightweight and scalable synthetic data framework that generates high-quality trajectories across diverse planning tasks.<n>We show that MagicAgent-32B and MagicAgent-30B-A3B achieve superior performance across diverse open-source benchmarks.
  arXiv  Detail & Related papers  (2026-02-22T01:39:16Z)
• AMUSE: Audio-Visual Benchmark and Alignment Framework for Agentic Multi-Speaker Understanding [73.05946667683259]
  Recent large language models (MLLMs) show strong perception but struggle in multi-speaker, dialogue-centric settings.<n>We introduce AMUSE, a benchmark designed around tasks that are inherently agentic.<n>We propose RAFT, a data-efficient agentic alignment framework that integrates reward optimization with intrinsic multimodal self-evaluation.
  arXiv  Detail & Related papers  (2025-12-18T07:01:47Z)
• A Lightweight Large Language Model-Based Multi-Agent System for 2D Frame Structural Analysis [21.13581042992661]
  Large language models (LLMs) have recently been used to empower autonomous agents in engineering.<n>This paper develops a LLM-based multi-agent system to automate finite element modeling of 2D frames.<n>The system achieves accuracy over 80% in most cases across 10 repeated trials, outperforming Gemini-2.5 Pro and ChatGPT-4o models.
  arXiv  Detail & Related papers  (2025-10-06T22:12:52Z)
• Flash-Searcher: Fast and Effective Web Agents via DAG-Based Parallel Execution [48.7788770680643]
  Flash-Searcher is a novel parallel agent reasoning framework.<n>It decomposes complex tasks into subtasks with explicit dependencies, enabling concurrent execution of independent reasoning paths.<n>It achieves 67.7% accuracy on BrowseComp and 83% on xbench-DeepSearch, while reducing agent execution steps by up to 35% compared to current frameworks.
  arXiv  Detail & Related papers  (2025-09-29T17:39:30Z)
• SPARE: Single-Pass Annotation with Reference-Guided Evaluation for Automatic Process Supervision and Reward Modelling [58.05959902776133]
  We introduce Single-Pass.<n>with Reference-Guided Evaluation (SPARE), a novel structured framework that enables efficient per-step annotation.<n>We demonstrate SPARE's effectiveness across four diverse datasets spanning mathematical reasoning (GSM8K, MATH), multi-hop question answering (MuSiQue-Ans), and spatial reasoning (SpaRP)<n>On ProcessBench, SPARE demonstrates data-efficient out-of-distribution generalization, using only $sim$16% of training samples compared to human-labeled and other synthetically trained baselines.
  arXiv  Detail & Related papers  (2025-06-18T14:37:59Z)
• Boosting Virtual Agent Learning and Reasoning: A Step-Wise, Multi-Dimensional, and Generalist Reward Model with Benchmark [72.46357004059661]
  Generalist Virtual Agents (GVAs) have shown significant promise in autonomous task execution.<n>To address these challenges, we propose Similar, a Step-Wise Multi-Dimensional Generalist Reward Model.<n>Similar offers fine-grained signals for agent training and can choose better action for inference-time scaling.
  arXiv  Detail & Related papers  (2025-03-24T13:30:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.