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

TL;DR

This paper introduces ValuePilot, a two-phase framework that enables AI agents to make personalized, value-aligned decisions in novel scenarios, improving interpretability and user alignment over traditional task-based methods.

Contribution

The paper presents a novel two-phase framework, including a dataset generation toolkit and a decision-making module, for value-driven personalized decision-making in AI systems.

Findings

DMM outperforms strong LLM baselines in aligning with human choices.

Value-driven approach enhances interpretability and generalization.

Framework effectively adapts to 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 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.