ValuePilot: A Two-Phase Framework for Value-Driven Decision-Making

Yitong Luo, Ziang Chen, Hou Hei Lam, Jiayu Zhan, Junqi Wang, Zhenliang Zhang, Xue Feng

Keywords: value-driven decision-making, personalized Al, human value alignment, preference modeling, interpretable agent behavior

TL;DR: We present Valuepilot, a value-driven framework for personalized Al decision-making that outperforms LLMs in aligning actions with human value preferences across unseen scenarios.

Abstract: Personalized decision-making is essential for human-AI interaction, enabling AI agents to act in alignment with individual users' value preferences. As AI systems expand into real-world applications, adapting to personalized values—beyond task completion or collective alignment—has become a critical challenge. We address this by proposing a value-driven approach to personalized decision-making. Human values serve as stable, transferable signals that support consistent and generalizable behavior across contexts. Compared to task-oriented paradigms driven by external rewards and incentives, value-driven decision-making enhances interpretability and enables agents to act appropriately even in novel scenarios. We introduce \textbf{\textit{ValuePilot}}, a two-phase framework consisting of a dataset generation toolkit (DGT) and a decision-making module (DMM). DGT constructs diverse, value-annotated scenarios from a human-LLM collaborative pipeline. DMM learns to evaluate actions based on personal value preferences, enabling context-sensitive, individualized decisions. When evaluated on previously unseen scenarios, DMM outperforms strong LLM baselines—including GPT-5, Claude-Sonnet-4, Gemini-2-flash, and Llama-3.1-70b—in aligning with human action choices. Our results demonstrate that value-driven decision-making is an effective and extensible engineering pathway toward building interpretable, personalized AI agents.

Submission Type: Research Paper (4-9 Pages)

Submission Number: 105