ITCMA: A Generative Agent Based on a Computational Consciousness Structure

TL;DR

This paper introduces ITCMA, a novel agent based on a computational consciousness structure that improves language models' understanding and reasoning in open-world tasks, outperforming state-of-the-art methods in various environments.

Contribution

The paper proposes ITCMA, an agent integrating a computational consciousness model to enhance reasoning and implicit instruction understanding in language models.

Findings

ITCMA outperforms SOTA by 9% on seen tasks in Alfworld.

Untrained ITCMA achieves 96% task completion rate, surpassing SOTA.

In real-world robot tasks, ITCMA achieves 85% success, demonstrating utility and generalization.

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. Evaluations in the Alfworld environment show that trained ITCMA outperforms the state-of-the-art (SOTA) by 9% on the seen set. Even untrained ITCMA achieves a 96% task completion rate on the seen set, 5% higher than SOTA, indicating its superiority over traditional intelligent agents in utility and generalization. In real-world tasks with quadruped robots, the untrained ITCMA achieves an 85% task completion rate, which is close to its performance in the unseen set, demonstrating its comparable utility and universality in real-world settings.