Abstract
The use of Large Language Models (LLMs) across diverse areas of human activity aims to enhance decision-making effectiveness with minimal human feedback. It also seeks to align decisions with human expectations, preferences, and needs while mitigating risks associated with AI non-determinism. However, humans frequently over- or under-rely on AI recommendations, and current AI systems remain poorly calibrated to human expectations.
To address these challenges, we introduce a human-AI collaborative decision-making framework designed to augment human capabilities and align AI agents with human preferences and expectations. Specifically, this paper (a) formulates the collaborative decision-making task as a stochastic game between an AI agent and a human player, and (b) proposes the Human-Centric Reflective Architecture (HCRA), which integrates human-calibrated models with reinforcement learning agents that leverage linguistic feedback in an iterative, reflective process.
Evaluation results demonstrate that HCRA enhances decision-making effectiveness and delivers high-quality recommendations.
Blogger's Review: The HCRA framework proposed in this paper offers a fresh perspective on human-AI collaborative decision-making, emphasizing the significance of human feedback in AI systems. This approach not only improves decision quality but also provides a more human-centric solution for future AI applications, warranting further exploration and implementation.