Can Mental Imagery Improve the Thinking Capabilities of AI Systems?

2025-07-16

AI Summary

Current AI systems rely on explicit inputs and lack autonomous cognitive initiation and cross-domain knowledge integration capabilities, rendering them incapable of emulating human-like internal reasoning grounded in mental imagery. To address this, we propose the first machine thinking framework explicitly integrating mental imagery, comprising four synergistic components: cognitive thinking units, multimodal input units, need-driven units, and mental imagery units. The framework employs natural language sentences and hand-drawn sketches as representational media, and combines cognitive computational models with mental simulation mechanisms to enable autonomous reasoning over internally generated, multisensory mental representations. Experimental evaluation demonstrates that our framework effectively triggers autonomous cognitive initiation in AI systems, substantially reduces dependence on external queries, and significantly enhances cross-domain knowledge integration capacity. This work establishes a novel paradigm for developing embodied, self-motivated AI agents.

Technology Category

• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Intelligent Robots: Embodied AI
• 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
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Agentic search

Abstract

Although existing models can interact with humans and provide satisfactory responses, they lack the ability to act autonomously or engage in independent reasoning. Furthermore, input data in these models is typically provided as explicit queries, even when some sensory data is already acquired. In addition, AI agents, which are computational entities designed to perform tasks and make decisions autonomously based on their programming, data inputs, and learned knowledge, have shown significant progress. However, they struggle with integrating knowledge across multiple domains, unlike humans. Mental imagery plays a fundamental role in the brain's thinking process, which involves performing tasks based on internal multisensory data, planned actions, needs, and reasoning capabilities. In this paper, we investigate how to integrate mental imagery into a machine thinking framework and how this could be beneficial in initiating the thinking process. Our proposed machine thinking framework integrates a Cognitive thinking unit supported by three auxiliary units: the Input Data Unit, the Needs Unit, and the Mental Imagery Unit. Within this framework, data is represented as natural language sentences or drawn sketches, serving both informative and decision-making purposes. We conducted validation tests for this framework, and the results are presented and discussed.

Problem

• AI lacks autonomous reasoning and independent action capabilities
• AI struggles with cross-domain knowledge integration like humans
• Mental imagery integration in AI thinking framework needs exploration

Innovation

• Integrates mental imagery into machine thinking framework
• Uses Cognitive unit with three auxiliary units
• Represents data as language or sketches