用强化学习优化多智能体协作流程，提升任务完成率与效率。
Reinforced Collaboration in Multi-Agent Flow Networks
- 构建基于成功案例的流网络，用强化学习优化协作路径与代理行为。
- 在7个基准上提升性能12.8%，效率提高47.4%，跨域泛化能力强。
- 适合需要高可靠性多步推理的任务，如复杂问题求解与自动化系统。
多智能体系统通过将复杂任务分解为由不同智能体处理的子任务，扩展了大语言模型的能力。然而，其性能常受错误传播影响，源于工作流设计不佳或智能体输出不准确，错误会沿协作过程传递并降低最终结果。为此，我们提出MANGO（多智能体网络梯度优化）——一种数据驱动框架，通过过去成功工作流构建的流网络组织并优化智能体协作。MANGO结合强化学习与文本梯度，联合优化工作流路径与智能体行为，同时引入跳过机制避免对已优化智能体重复更新，提升效率。在7个基准上的大量实验表明，MANGO相比现有最优基线性能提升最高达12.8%，效率提升47.4%，且在未见领域表现出良好泛化能力。代码与数据集已公开于https://github.com/openJiuwen-ai/agent-store/tree/main/community/mango。
原文摘要 · Abstract (English)
Multi-agent systems provide a powerful way to extend large language models (LLMs) by decomposing a complex task into specialized subtasks handled by different agents. However, their performance is often hindered by error propagation, arising from suboptimal workflow design or inaccurate agent outputs, which can propagate through the agent collaboration process and degrade final results. To address the challenges, we present MANGO (Multi-Agent Network Gradient Optimization), a data-driven framework that organizes and refines agent collaboration via a flow network constructed from past successful workflows. MANGO integrates reinforcement learning and textual gradients to jointly optimize workflow paths and agent behaviors, while a skipping mechanism prevents redundant updates to well-optimized agents for improving efficiency. Extensive experiments on seven benchmarks show that MANGO achieves up to 12.8% performance improvement over state-of-the-art baselines, enhances efficiency by 47.4%, and generalizes effectively to unseen domains. Our code and datasets are publicly available at https://github.com/openJiuwen-ai/agent-store/tree/main/community/mango.
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。