ADL: A Declarative Language for Agent-Based Chatbots

Sirui Zeng, Xifeng Yan
4/21/2025
cs.MA

Official code: Mica-labs/MICA (55 stars, Apache-2.0, last commit 2026-02-09).

Abstract

There are numerous frameworks capable of creating and orchestrating agents to address complex tasks. However, most of them highly coupled Python programming with agent declaration, making it hard for maintenance and runtime optimization. In this work, we introduce ADL, an agent declarative language for customer service chatbots. ADL abstracts away implementation details, offering a declarative way to define agents and their interactions, which could ease maintenance and debugging. It also incorporates natural language programming at its core to simplify the specification and communication of chatbot designs. ADL includes four basic types of agents and supports integration with custom functions, tool use, and third-party agents. MICA, a multi-agent system designed to interpret and execute ADL programs, has been developed and is now available as an open-source project at https://github.com/Mica-labs/MICA. Its documentation can be found at https://mica-labs.github.io/.

View on arXivView PDF

Code Implementations(1)

Mica-labs/MICAOfficial100%
Apache-2.0

MICA (Multiple Intelligent Conversational Agents) is designed to simplify the development of customer service bots.

5510HTML, ShellFeb 5, 20258 months agoApache-2.0

Similar Papers

Lemur: Harmonizing Natural Language and Code for Language Agents

84% match1 repo5582023

TaskWeaver: A Code-First Agent Framework

84% match1 repo6.2k2023

AgentLite: A Lightweight Library for Building and Advancing Task-Oriented LLM Agent System

83% match1 repo6512024

Creation Of A ChatBot Based On Natural Language Proccesing For Whatsapp

83% match2023

A System for Human-AI collaboration for Online Customer Support

82% match2023

DiagGPT: An LLM-based and Multi-agent Dialogue System with Automatic Topic Management for Flexible Task-Oriented Dialogue

82% match2023

Cite this paper

@article{zeng2025adl,
  title  = {ADL: A Declarative Language for Agent-Based Chatbots},
  author = {Sirui Zeng and Xifeng Yan},
  year   = {2025},
  eprint = {2504.14787},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2504.14787v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2504.14787.svg)](https://codeofpaper.com/paper/2504.14787)

Discussion