Human-Centric Reflective Architecture for Human-AI Collaborative Decision-Making
Quick Answer
This paper shows that The Human-Centric Reflective Architecture (HCRA) enhances human-AI collaborative decision-making by integrating human-calibrated models with reinforcement learning, improving decision effectiveness and alignment with human preferences.
Quick Take
The Human-Centric Reflective Architecture (HCRA) enhances human-AI collaborative decision-making by integrating human-calibrated models with reinforcement learning, improving decision effectiveness and alignment with human preferences. This framework addresses the challenges of AI non-determinism and human reliance on AI recommendations, demonstrating superior performance in evaluations.
Key Points
- HCRA formulates decision-making as a stochastic game between AI and humans.
- The framework incorporates linguistic feedback in an iterative, reflective process.
- Evaluation results show enhanced decision-making effectiveness and high-quality recommendations.
- Addresses issues of over- and under-reliance on AI recommendations.
- Aligns AI decisions with human expectations and preferences.
Paper Resources
📖 Reader Mode
~2 min readAbstract: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.
| Subjects: | Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA) |
| Cite as: | arXiv:2607.03025 [cs.AI] |
| (or arXiv:2607.03025v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2607.03025 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: George Vouros [view email]
[v1]
Fri, 3 Jul 2026 07:12:44 UTC (2,974 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →Procedural Memory Distillation: Online Reflection for Self-Improving Language Models
Procedural Memory Distillation (PMD) enhances reinforcement learning by converting cross-episode signals into reusable memory, improving Qwen3-8B and OLMo3-Instruct-7B models by 3.8-5.5% on SCIKNOWEVAL and 7.9-13.6% on . The co-evolution of policy and memory allows for more effective self-supervision, demonstrating significant performance gains when both components are active.