让多个AI代理像神经网络一样自动协作进化，提升复杂任务的适应性。
Self-Evolving Multi-Agent Systems via Textual Backpropagation
- 将多代理系统设计为分层神经网络，每层专注一个子任务。
- 通过双向反馈迭代优化代理角色与协作方式，实现自我演化。
- 在7个数据集上超越现有方法，适合高复杂度任务研究者。
利用多个大语言模型（LLMs）在解决复杂、高维任务方面已证明有效，但当前方法通常依赖静态且手动设计的多代理配置。为克服这一局限，我们提出代理神经网络（ANN）框架，将多代理协作概念化为分层神经网络架构。在此设计中，每个代理作为节点，每层构成专注于特定子任务的合作团队。该框架采用两阶段优化策略：(1) 前向阶段——借鉴神经网络前向传播，动态分解任务为子任务，并逐层构建具备合适聚合方式的合作代理团队；(2) 反向阶段——类比反向传播，通过迭代反馈优化全局与局部协作，使代理能够自我演化其角色、提示词与协调机制。这种神经符号方法使框架在训练后可生成新或专用的代理团队，显著提升准确率与适应性。在七个基准数据集上，本工作在相同配置下超越领先多代理基线，表现出一致性能提升。
原文摘要 · Abstract (English)
Leveraging multiple Large Language Models (LLMs) has proven effective for addressing complex, high-dimensional tasks, but current approaches often rely on static, manually engineered multi-agent configurations. To overcome these constraints, we present the Agentic Neural Network (ANN), a framework that conceptualizes multi-agent collaboration as a layered neural network architecture. In this design, each agent operates as a node, and each layer forms a cooperative team focused on a specific subtask. Our framework follows a two-phase optimization strategy: (1) Forward Phase - Drawing inspiration from neural network forward passes, tasks are dynamically decomposed into subtasks, and cooperative agent teams with suitable aggregation methods are constructed layer by layer. (2) Backward Phase - Mirroring backpropagation, we refine both global and local collaboration through iterative feedback, allowing agents to self-evolve their roles, prompts, and coordination. This neuro-symbolic approach enables our framework to create new or specialized agent teams post-training, delivering notable gains in accuracy and adaptability. Across seven benchmark datasets, our work surpasses leading multi-agent baselines under the same configurations, showing consistent performance improvements.
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。