Simulating Human-like Daily Activities with Desire-driven Autonomy

TL;DR

This paper presents a Desire-driven Autonomous Agent (D2A) that enables large language models to autonomously generate human-like daily activities based on multi-dimensional desires, improving behavioral diversity and contextual relevance.

Contribution

The paper introduces a novel desire-driven framework for LLM agents, inspired by human needs, allowing autonomous task proposal and selection without explicit instructions.

Findings

Generates coherent and contextually relevant daily activities.

Exhibits variability and adaptability similar to humans.

Enhances rationality of activity simulation compared to other LLM agents.

Abstract

Desires motivate humans to interact autonomously with the complex world. In contrast, current AI agents require explicit task specifications, such as instructions or reward functions, which constrain their autonomy and behavioral diversity. In this paper, we introduce a Desire-driven Autonomous Agent (D2A) that can enable a large language model (LLM) to autonomously propose and select tasks, motivated by satisfying its multi-dimensional desires. Specifically, the motivational framework of D2A is mainly constructed by a dynamic Value System, inspired by the Theory of Needs. It incorporates an understanding of human-like desires, such as the need for social interaction, personal fulfillment, and self-care. At each step, the agent evaluates the value of its current state, proposes a set of candidate activities, and selects the one that best aligns with its intrinsic motivations. We conduct experiments on Concordia, a text-based simulator, to demonstrate that our agent generates coherent, contextually relevant daily activities while exhibiting variability and adaptability similar to human behavior. A comparative analysis with other LLM-based agents demonstrates that our approach significantly enhances the rationality of the simulated activities.