Unified Mind Model: Reimagining Autonomous Agents in the LLM Era
This work addresses the problem of theoretical underpinnings for autonomous agents in AI research, offering a framework to facilitate rapid agent development, though it appears incremental as it builds on existing LLM capabilities and cognitive theories.
The paper tackles the lack of a theoretical foundation for building human-level autonomous agents based on large language models (LLMs) by proposing the Unified Mind Model (UMM), a novel cognitive architecture that leverages LLMs to enable agents with abilities like perception, planning, and reasoning, and develops MindOS, an engine for creating domain-specific agents without programming.
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.