{"ID":2879160,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.17068","arxiv_id":"2508.17068","title":"Anemoi: A Semi-Centralized Multi-agent System Based on Agent-to-Agent Communication MCP server from Coral Protocol","abstract":"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.","short_abstract":"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: (...","url_abs":"https://arxiv.org/abs/2508.17068","url_pdf":"https://arxiv.org/pdf/2508.17068v3","authors":"[\"Xinxing Ren\",\"Caelum Forder\",\"Qianbo Zang\",\"Ahsen Tahir\",\"Roman J. Georgio\",\"Suman Deb\",\"Peter Carroll\",\"Önder Gürcan\",\"Zekun Guo\"]","published":"2025-08-23T15:45:10Z","proceeding":"cs.MA","tasks":"[\"cs.MA\",\"cs.CL\"]","methods":"[\"Large Language Model\"]","has_code":false,"code_links":[{"ID":610563,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2879160,"paper_url":"https://arxiv.org/abs/2508.17068","paper_title":"Anemoi: A Semi-Centralized Multi-agent System Based on Agent-to-Agent Communication MCP server from Coral Protocol","repo_url":"https://github.com/Coral-Protocol/Anemoi","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}