A Concurrent Modular Agent: Framework for Autonomous LLM Agents

TL;DR

The paper presents the Concurrent Modular Agent (CMA), a framework that enables asynchronous, modular LLM-based agents to work together coherently, supporting complex behaviors and emergent cognitive phenomena like self-awareness.

Contribution

It introduces a novel asynchronous modular framework for LLM agents that facilitates emergent behaviors and aligns with Minsky's Society of Mind theory.

Findings

Demonstrates the viability of CMA through practical use-case studies.

Shows emergent properties suggesting complex cognition can arise from simple modules.

Supports flexible, adaptive, and context-dependent agent behaviors.

Abstract

We introduce the Concurrent Modular Agent (CMA), a framework that orchestrates multiple Large-Language-Model (LLM)-based modules that operate fully asynchronously yet maintain a coherent and fault-tolerant behavioral loop. This framework addresses long-standing difficulties in agent architectures by letting intention emerge from language-mediated interactions among autonomous processes. This approach enables flexible, adaptive, and context-dependent behavior through the combination of concurrently executed modules that offload reasoning to an LLM, inter-module communication, and a single shared global state.We consider this approach to be a practical realization of Minsky's Society of Mind theory. We demonstrate the viability of our system through two practical use-case studies. The emergent properties observed in our system suggest that complex cognitive phenomena like self-awareness may indeed arise from the organized interaction of simpler processes, supporting Minsky-Society of Mind concept and opening new avenues for artificial intelligence research. The source code for our work is available at: https://github.com/AlternativeMachine/concurrent-modular-agent.