用检索选模型+探索利用机制，让多个开源大模型协作更高效
A Scalable Multi-LLM Collaboration System with Retrieval-based Selection and Exploration-Exploitation-Driven Enhancement
- 基于检索动态选最优模型，提升任务匹配度
- 融合探索与利用机制，输出质量比单模型高5.36%
- 支持大规模模型扩展，适合想用开源模型做实战的团队
现有多大模型协作系统在集成新模型和任务时常面临可扩展性挑战，导致性能不佳。为此，我们提出SMCS——一种可扩展的多大模型协作系统，有效协调多个开源大模型。系统包含两个核心组件：基于检索的先验选择（RPS）模块，动态为每个输入选择最合适的模型；以及探索-利用驱动的后验增强（EPE）模块，通过混合评分机制提升响应多样性并筛选高质量输出。在八个主流基准上的实验验证了系统有效性：集成十五个开源大模型后，SMCS在多个任务上超越主流闭源模型，如GPT-4.1(+5.36%)和GPT-o3-mini(+5.28%)；其性能甚至超过各数据集最佳结果的平均值（+2.86%），显著推动了开源协作的实证性能边界。代码已公开于https://github.com/magent4aci/SMCS。
原文摘要 · Abstract (English)
Existing multi-LLM collaboration systems often encounter scalability challenges when integrating new LLMs and tasks, leading to suboptimal performance. To address this, we propose SMCS, a Scalable Multi-LLM Collaboration System designed to effectively coordinate multiple open-source LLMs. The system consists of two core components: a Retrieval-based Prior Selection (RPS) module, which dynamically selects the most suitable LLMs for each input, and an Exploration-Exploitation-Driven Posterior Enhancement (EPE) module, which fosters response diversity and selects high-quality outputs through a hybrid scoring mechanism. Experiments on eight mainstream benchmarks validate the effectiveness of our system: by integrating fifteen open-source LLMs, SMCS outperforms prevailing closed-source LLMs, e.g., GPT-4.1(+5.36%) and GPT-o3-mini(+5.28%) across multiple tasks. Remarkably, it even exceeds the average of best results on different datasets with open-source LLMs (+2.86%), significantly advancing the empirical performance frontier of open-source collaboration. The code is released at https://github.com/magent4aci/SMCS.
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。