让多智能体通信结构随环境动态调整，提升协作稳定性。
CARD: Towards Conditional Design of Multi-agent Topological Structures
- 基于环境信号条件生成通信图，实现动态拓扑设计。
- 在HumanEval等数据集上准确率显著高于静态基线。
- 适合需要应对模型更新或资源变化的复杂协作系统。
基于大语言模型的多智能体系统在代码生成和协同推理等任务中表现出色，但其效能与鲁棒性高度依赖通信拓扑结构。当前方法普遍采用固定或静态学习的拓扑，忽视了模型升级、API（或工具）变更或知识源波动等现实动态。为此，我们提出CARD（Conditional Agentic Graph Designer），一个用于自适应多智能体通信的图生成框架，其核心是可动态调整的AMACP协议。CARD通过条件变分图编码器与环境感知优化，在训练和运行时均能根据环境信号动态构建通信结构，使系统具备对模型能力或资源可用性变化的强适应性。在HumanEval、MATH和MMLU上的实验证明，CARD持续优于静态与提示基线，展现出更高准确率与鲁棒性。源代码已开源：https://github.com/Warma10032/CARD。
原文摘要 · Abstract (English)
Large language model (LLM)-based multi-agent systems have shown strong capabilities in tasks such as code generation and collaborative reasoning. However, the effectiveness and robustness of these systems critically depend on their communication topology, which is often fixed or statically learned, ignoring real-world dynamics such as model upgrades, API (or tool) changes, or knowledge source variability. To address this limitation, we propose CARD (Conditional Agentic Graph Designer), a conditional graph-generation framework that instantiates AMACP, a protocol for adaptive multi-agent communication. CARD explicitly incorporates dynamic environmental signals into graph construction, enabling topology adaptation at both training and runtime. Through a conditional variational graph encoder and environment-aware optimization, CARD produces communication structures that are both effective and resilient to shifts in model capability or resource availability. Empirical results on HumanEval, MATH, and MMLU demonstrate that CARD consistently outperforms static and prompt-based baselines, achieving higher accuracy and robustness across diverse conditions. The source code is available at: https://github.com/Warma10032/CARD.
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。