cs.MAOct 26, 2026

EREBOTS 4.0: A framework for conversational assistants with A2A agents and MCP tools

Authors: Elia Pacioni, Davide Calvaresi, Andrei C. Coman, Ismael Jaggi, Valerio Crocetti, Gaetano Manzo, Michael Ignaz Schumacher

Organizations: HES-SO Valais-Wallis, Rue de Technopôle 10, 3960 Sierre, Switzerland · University of Extremadura, 06800, Mérida, Spain

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

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.

Figures & tables

Nr.Code metadata descriptionValue
C1Current code version1.0.0
C2Permanent GitHub link to code/repository used for this code versionhttps://github.com/aislab-hevs/erebots4.0/tree/v1.0.0
C3Legal Code LicenseMIT
C4Code versioning system usedgit
C5Software code languages, tools, and services usedPython, FastAPI, a2a-sdk , MCP Python SDK, OpenAI-compatible LLM APIs, SQLAlchemy, PostgreSQL and SQLite, Keycloak, Vue.js, Gradio, Docker Compose, Traefik
C6Compilation requirements, operating environments & dependenciesPython ≥\geq 3.13 and an OpenAI-compatible LLM endpoint. A checkout resolves from a uv lockfile, and the published wheel bounds the three SDKs the framework codes against. Tool-using specialists need a model that supports tool calls. Docker Compose provides an optional deployment stack
Table 1: Code metadata
Figure 1: EREBOTS 4.0 architecture. One user turn: (1) message, (2) context loading, (3) LLM planning, (4) A2A delegation, (5) MCP tool calls, (6) streamed answer, (7) persistence. Dashed lines: possible process or host boundaries.
Evaluation unitPassedFailedSkippedNot tested
Tests, /a2a/tck180085n/a
Tests, /a2a/tck-minimal1400125n/a
Requirements, /a2a/tck9401025
Requirements, /a2a/tck-minimal7303026
Requirements, union of both runs970725
Table 2: TCK counts for version 1.0.0, out of the 129 requirements the suite tracks. The two endpoints cover different requirements by construction. The minimal card declares three capabilities absent, which is why 30 requirements are skipped against it, and without streaming it offers no Server-Sent Events to exercise.
Figure 2: The Vue [ 31 ] client during the clarification scenario. The orchestrator routes to PersonalAgent , which asks for the missing value it does not have, and every turn carries its trace and its timings. The question comes back in Italian because the stored preference is already in the prompt.
Figure 3: The clarification scenario seen in PostgreSQL. The task sits in TASK_STATE_INPUT_REQUIRED while the question is open, completes once the user answers, and the stored profile changes from Italian to Spanish.
More in this topic

Multi-Agent LLM Systems

Multi-agent large language model systems coordinate multiple AI agents to solve tasks through communication, specialization, shared tools, and memory.

See all 1,039 papers

Explore similar work

CardsList

  1. Ahoy: LLMs Enacting Multiagent Interaction Protocols

    Jun 3, 2026Omkar J. Joshi, Munindar P. Singh, Amit K. ChopraLLM AgentsMulti-Agent Systems

    North Carolina State University, Raleigh, NC, USA · Lancaster University, Lancaster, UK

  2. ETA: A New Agentic Paradigm for Embodied Tasks

    Aug 4, 2026Yitong Chen, Zezheng Huai, Sixian Li +7Tool-Using AgentsRobot Task Planning

    1Shanghai Innovation Institute · 2Fudan University · 3Jilin University +2

  3. HyperTool: Beyond Step-Wise Tool Calls for Tool-Augmented Agents

    Jun 11, 2026Yaxin Du, Yifan Zhou, Yujie Ge +7Tool-Augmented Language Model AgentsLLM Agent Workflow Optimization

    Shanghai Jiao Tong University · IQuest Research · Beijing University of Aeronautics and Astronautics