Autonomous Question Formation for Large Language Model-Driven AI Systems

TL;DR

This paper introduces a framework for autonomous question formation in LLM-driven AI systems, enhancing their ability to adaptively identify problems and improve decision-making in dynamic environments.

Contribution

It presents a novel human-simulation-based approach that enables AI to autonomously generate questions and set tasks, incorporating environment and inter-agent awareness.

Findings

Environment-aware prompting reduces no-eat events significantly.

Inter-agent-aware prompting further decreases cumulative no-eat events by over 60%.

The framework improves adaptability and decision quality over time.

Abstract

Large language model (LLM)-driven AI systems are increasingly important for autonomous decision-making in dynamic and open environments. However, most existing systems rely on predefined tasks and fixed prompts, limiting their ability to autonomously identify what problems should be solved when environmental conditions change. In this paper, we propose a human-simulation-based framework that enables AI systems to autonomously form questions and set tasks by reasoning over their internal states, environmental observations, and interactions with other AI systems. The proposed method treats question formation as a first-class decision process preceding task selection and execution, and integrates internal-driven, environment-aware, and inter-agent-aware prompting scopes to progressively expand cognitive coverage. In addition, the framework supports learning the question-formation process from experience, allowing the system to improve its adaptability and decision quality over time. xperimental results in a multi-agent simulation environment show that environment-aware prompting significantly reduces no-eat events compared with the internal-driven baseline, and inter-agent-aware prompting further reduces cumulative no-eat events by more than 60% over a 20-day simulation, with statistically significant improvements (p < 0.05).