让企业级多智能体系统快速定制并高效部署。
Towards Scalable Customization and Deployment of Multi-Agent Systems for Enterprise Applications
- 分两阶段：先用持续预训练等方法适配领域，再用推测解码和量化优化推理
- 吞吐量提升4.48倍，长尾场景更稳定，性能几乎无损
- 适合需要快速落地多智能体系统的大型企业用户
基于大语言模型的多智能体系统在复杂推理与任务执行中表现优异，适用于广泛的企业应用。但实际部署面临领域定制难、推理延迟高及成本高的挑战。本文提出一个统一框架，实现多智能体系统的高效定制与部署。第一阶段「智能体模型定制」结合持续预训练、监督微调与偏好优化，将轻量模型适配到特定领域，同时保持强智能体能力。第二阶段「推理优化」集成推测解码与FP8量化，并通过定向校准实现低成本服务，质量损失极小。在多个企业工作负载上，该框架实现了快速领域适应，吞吐量提升4.48倍，性能保持稳定，长尾场景鲁棒性显著增强。
原文摘要 · Abstract (English)
Large language model (LLM)-based multi-agent systems demonstrate strong performance on complex reasoning and task execution, enabling broad enterprise applications. However, production deployment remains challenging due to domain-specific customization requirements and high latency and inference costs in agentic workflows. We propose a unified framework for customization and efficient deployment of multi-agent systems in real-world settings. The first stage, Agentic Model Customization, combines continual pretraining, supervised fine-tuning, and preference optimization to adapt a compact model to specialized domains while retaining strong agentic capabilities. The second stage, Inference Optimization, integrates speculative decoding and FP8 quantization with targeted calibration to enable cost-efficient serving with minimal quality loss. Across enterprise workloads, our framework enables rapid domain adaptation and achieves a 4.48x speedup in throughput while maintaining performance and improving robustness on long-tail scenarios.
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。