Unified Mind Model: Reimagining Autonomous Agents in the LLM Era

2025-03-05

AI Summary

This study addresses the lack of a unified cognitive theoretical foundation for general-purpose autonomous agents. We propose UMM, the first full-stack cognitive architecture integrating Global Workspace Theory (GWT) with large language models (LLMs). UMM holistically models human-level cognitive capabilities—including multimodal perception, hierarchical planning, neuro-symbolic reasoning, external memory, tool invocation, and reflective learning—overcoming the fragmentation inherent in conventional agent architectures. To enable rapid deployment, we introduce MindOS, a zero-code construction engine supporting domain-specific agent development within minutes. Empirical evaluations demonstrate that UMM significantly outperforms existing frameworks in complex task planning, cross-tool coordination, and continual learning, while maintaining strong scalability and interpretability.

Technology Category

• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Machine Learning: Large Multimodal Models (LMMs)
• Multiagent Systems: Agent/AI Theories and Architectures

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Economics, Online Markets and Human Computation: Architectures and workflows that use LLMs for crowd work

Abstract

Large language models (LLMs) have recently demonstrated remarkable capabilities across domains, tasks, and languages (e.g., ChatGPT and GPT-4), reviving the research of general autonomous agents with human-like cognitive abilities.Such human-level agents require semantic comprehension and instruction-following capabilities, which exactly fall into the strengths of LLMs.Although there have been several initial attempts to build human-level agents based on LLMs, the theoretical foundation remains a challenging open problem. In this paper, we propose a novel theoretical cognitive architecture, the Unified Mind Model (UMM), which offers guidance to facilitate the rapid creation of autonomous agents with human-level cognitive abilities. Specifically, our UMM starts with the global workspace theory and further leverage LLMs to enable the agent with various cognitive abilities, such as multi-modal perception, planning, reasoning, tool use, learning, memory, reflection and motivation. Building upon UMM, we then develop an agent-building engine, MindOS, which allows users to quickly create domain-/task-specific autonomous agents without any programming effort.

Problem

• Developing human-level autonomous agents using LLMs
• Establishing a theoretical foundation for cognitive architectures
• Creating a tool for rapid agent development without programming

Innovation

• Proposes Unified Mind Model for cognitive architecture
• Leverages LLMs for multi-modal cognitive abilities
• Develops MindOS for easy agent creation