arXiv cs.MA· Elia Pacioni, Davide Calvaresi, Andrei C. Coman, Ismael Jaggi, Valerio Crocetti, Gaetano Manzo, Michael Ignaz Schumacher·· 11 小时前AI 评分39
EREBOTS 4.0：面向对话助手的 A2A 智能体与 MCP 工具框架
EREBOTS 4.0: A framework for conversational assistants with A2A agents and MCP tools
AI 导读
EREBOTS 4.0 是一个开源混合 AI 多智能体框架，面向对话助手，由语言模型智能体负责规划与路由，确定性工具通过 MCP 计算精确结果，编排器每轮经 A2A 协议选择一个或多个专家智能体。
正文
Abstract:In recent years, multi-agent systems have shifted from rule-based, symbolic agents to sub-symbolic agents built on language models. However, several limitations remain unresolved. The new frontier is neuro-symbolic agents, which pair language models with deterministic tools and explicit protocols. Without a common framework to standardize and compose them, each study rebuilds the same infrastructure, and results are hard to replicate. This paper presents EREBOTS 4.0, an open-source, hybrid-AI, multi-agent framework that fills this gap for conversational assistants. Language-model agents plan and route requests, while deterministic tools compute exact results over the Model Context Protocol (MCP). An orchestrator selects one or more specialist agents per turn and calls them over the Agent2Agent protocol (A2A). A new agent, local or remote, is added by listing its URL in a configuration file. The framework also manages identity, user context with consent flags, task states and traces. Its A2A server passed 97 tracked requirements in the official A2A Technology Compatibility Kit, with no failures.
| Subjects: | Multiagent Systems (cs.MA) |
| Cite as: | arXiv:2610.36221 [cs.MA] |
| (or arXiv:2610.36221v1 [cs.MA] for this version) | |
| https://doi.org/10.48550/arXiv.2610.36221 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Elia Pacioni [view email]
[v1]
Mon, 26 Oct 2026 19:56:14 UTC (278 KB)
来源：arXiv cs.MA · arxiv.org