Recent advances in generalist multi-agent systems (MAS) have largely followed a context-engineering plus centralized paradigm, where a planner agent coordinates multiple worker agents through unidirectional prompt passing. While effective under strong planner models, this design suffers from two critical limitations: (1) strong dependency on the planner's capability, which leads to degraded performance when a smaller LLM powers the planner; and (2) limited inter-agent communication, where collaboration relies on prompt concatenation rather than genuine refinement through structured discussions. To address these challenges, we propose Anemoi, a semi-centralized MAS built on the Agent-to-Agent (A2A) communication MCP server from Coral Protocol. Unlike traditional designs, Anemoi enables structured and direct inter-agent collaboration, allowing all agents to monitor progress, assess results, identify bottlenecks, and propose refinements in real time. This paradigm reduces reliance on a single planner, supports adaptive plan updates, and minimizes redundant context passing, resulting in more scalable execution. Evaluated on the GAIA benchmark, Anemoi achieved 52.73% accuracy with a small LLM (GPT-4.1-mini) as the planner, surpassing the strongest open-source baseline OWL (43.63%) by +9.09% under identical LLM settings. Our implementation is publicly available at https://github.com/Coral-Protocol/Anemoi.

翻译：近期通用多智能体系统（MAS）的发展主要遵循上下文工程化与集中式范式，即规划智能体通过单向提示传递协调多个工作智能体。尽管在强规划模型下有效，该设计存在两个关键局限：（1）对规划器能力的强依赖性，导致当规划器由较小规模语言模型驱动时性能下降；（2）有限的智能体间通信，其协作依赖于提示拼接而非通过结构化讨论实现的真正优化。为应对这些挑战，我们提出Anemoi——一个基于Coral Protocol中Agent-to-Agent（A2A）通信MCP服务器构建的半集中式MAS。与传统设计不同，Anemoi支持结构化且直接的智能体间协作，使所有智能体能够实时监控进展、评估结果、识别瓶颈并提出优化方案。该范式降低了对单一规划器的依赖，支持自适应计划更新，并最大程度减少冗余上下文传递，从而实现更具可扩展性的执行。在GAIA基准测试中，Anemoi使用小型语言模型（GPT-4.1-mini）作为规划器取得了52.73%的准确率，在相同语言模型设置下超越最强开源基线OWL（43.63%）达+9.09%。我们的实现已公开于https://github.com/Coral-Protocol/Anemoi。