用棒球自由球员机制动态替换低效生成式AI代理，提升系统稳定性。
Free Agent in Agent-Based Mixture-of-Experts Generative AI Framework
- 基于强化学习的自由代理算法，实时识别并替换表现不佳的代理。
- 新代理经试用期验证后完全替代旧代理，保持系统持续高精度。
- 适合需要快速响应威胁的生成式AI场景，如欺诈检测。
多智能体系统通常将任务分配给专业化、自主的智能体，但缺乏实时替换或重新分配表现不佳智能体的机制。受美国职业棒球大联盟自由球员模式启发，本文提出强化学习自由代理（RLFA）算法，通过奖励机制检测并移除持续表现不佳的智能体，无缝引入更高效的新智能体。每个智能体内部采用专家混合（MoE）架构，由门控函数指导任务分发至特定子模型。以欺诈检测为例，当某智能体的检测准确率低于预设阈值时，系统立即启动替换流程：新智能体先在试用期运行，若表现更优则完全取代原智能体。这一动态自由代理循环确保系统持续高精度，更快适应新兴威胁，且对现有操作干扰极小。通过不断更新智能体阵容，系统在多智能体生成式AI环境中实现持续优化与更强韧性。
原文摘要 · Abstract (English)
Multi-agent systems commonly distribute tasks among specialized, autonomous agents, yet they often lack mechanisms to replace or reassign underperforming agents in real time. Inspired by the free-agency model of Major League Baseball, the Reinforcement Learning Free Agent (RLFA) algorithm introduces a reward-based mechanism to detect and remove agents exhibiting persistent underperformance and seamlessly insert more capable ones. Each agent internally uses a mixture-of-experts (MoE) approach, delegating incoming tasks to specialized sub-models under the guidance of a gating function. A primary use case is fraud detection, where RLFA promptly swaps out an agent whose detection accuracy dips below a preset threshold. A new agent is tested in a probationary mode, and upon demonstrating superior performance, fully replaces the underperformer. This dynamic, free-agency cycle ensures sustained accuracy, quicker adaptation to emerging threats, and minimal disruption to ongoing operations. By continually refreshing its roster of agents, the system fosters ongoing improvements and more resilient collaboration in multi-agent Generative AI environments.
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。