多智能体系统设计者终于有了一个能同时优化提示和通信拓扑的框架——TCP-MCP 在保持高准确率的同时大幅降低 token 成本，做复杂协作任务的团队可以直接参考其方法。
TCP-MCP 提出了一种将智能体提示和通信拓扑作为统一基因进行协同进化的框架，解决了传统方法中两者孤立设计的问题。该框架通过初始化景观探测校准早期搜索行为，并利用帕累托前沿诊断在任务性能、token 成本和结构复杂度三个目标下自适应探索。在 DeepSeek-V3.2 骨干模型上，TCP-MCP 在 MMLU-Pro、MMLU 和 GSM8K 上分别达到 82.66%、89.96% 和 96.61% 的准确率，相比辩论式系统最多节省 5.69 倍 token。实验表明，联合进化提示和通信结构是实现成本感知和任务自适应多智能体系统设计的实用路径。
TCP-MCP: Landscape-Guided Co-Evolution of Prompts and Communication Topologies for Multi-Agent Systems
Effective multi-agent systems cannot be designed by selecting prompts or communication graphs in isolation. Agent behavior depends on the information an agent receives, while the usefulness of a communication edge depends on how the receiving agent interprets and uses that information. We propose \textbf{TCP-MCP} (Topology-Coupled Prompting for Multi-Agent Collaborative Problem-Solving), a co-evolution framework that searches agent prompts and communication topologies as a unified genome. TCP-MCP uses an initialization-time landscape probe to calibrate early search behavior, and then relies on Pareto-front diagnostics to adapt exploration under three objectives: task performance, token cost, and structural complexity. Using the same DeepSeek-V3.2 backbone across all methods, TCP-MCP achieves 82.66\%, 89.96\%, and 96.61\% accuracy on MMLU-Pro, MMLU, and GSM8K, respectively. Across the three benchmarks, it consistently outperforms automated graph-generation baselines and achieves competitive accuracy relative to debate-style systems, while using up to 5.69$\times$ fewer tokens than those systems at the reported operating points. These results show that jointly evolving prompts and communication structure provides a practical route to cost-aware and task-adaptive multi-agent system design in controlled evaluations.