Human-Centric Reflective Architecture for Human-AI Collaborative Decision-Making
Andreas Kouridakis, Dimitrios Patiniotis Spyropoulos, George Vouros
Why It Matters
What makes this one worth your time
This research addresses critical challenges in aligning AI recommendations with human expectations, which is essential for effective human-AI collaboration in various applications.
A novel framework for improving human-AI collaboration in decision-making.
Summary
The paper introduces a Human-Centric Reflective Architecture (HCRA) that formulates human-AI collaborative decision-making as a stochastic game, integrating human-calibrated models with reinforcement learning to enhance decision-making effectiveness.
Key contributions
- Introduction of the Human-Centric Reflective Architecture (HCRA) for decision-making.
- Formulation of the collaborative decision-making task as a stochastic game.
- Integration of human-calibrated models with reinforcement learning agents.
Notable insights
- The use of stochastic games to model the interaction between AI agents and human players is a clever approach that may yield more adaptive decision-making processes.
- Integrating linguistic feedback into reinforcement learning could enhance the calibration of AI systems to better align with human preferences.
Possible limitations
- Not stated in the abstract.
Abstract
arXiv:2607.03025v1 Announce Type: new Abstract: The use of Large Language Models (LLMs) across diverse areas of human activity-ranging from everyday tasks to safety-critical applications-aims to enhance decision-making effectiveness with minimal human feedback. Concurrently, it 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.