Simulating phenomenal consciousness using generative agents based on large language models

Abstract

Large Language Models (LLMs) still face challenges in tasks requiring understanding implicit instructions and applying common-sense knowledge. In such scenarios, LLMs may require multiple attempts to achieve human-level performance, potentially leading to inaccurate responses or inferences in practical environments, affecting their long-term consistency and behavior. This paper introduces the Internal Time-Consciousness Machine (ITCM), a computational consciousness structure to simulate the process of human consciousness. We further propose the ITCM-based Agent (ITCMA), which supports action generation and reasoning in open-world settings, and can independently complete tasks. ITCMA enhances LLMs’ ability to understand implicit instructions and apply common-sense knowledge by considering agents’ interaction and reasoning with the environment. The trained ITCMA performs better than state-of-the-art (SOTA) in the seen set. Even untrained ITCMA can achieve higher task completion rates than SOTA on the seen set, indicating its superiority over traditional intelligent agents in utility and generalization. In real-world tasks with quadruped robots, the task completion rate of untrained ITCMA is close to its performance in the unseen set, demonstrating its comparable utility and universality in real-world settings. CCS Concepts: ∙ Human-centered computing → Interactive systems and tools; ∙ Computing methodologies → Natural language processing.