Learning to Plan with Personalized Preferences

2025-02-02

AI Summary

General-purpose AI planning methods often neglect individual user preferences and struggle to adapt to personalized collaborative requirements. Method: We propose Preference-based Planning (PbP), a novel paradigm that models preferences as a transferable abstract layer—spanning atomic actions to complex action sequences—and introduce a comprehensive PbP benchmark. PbP employs few-shot demonstration learning to infer implicit preference representations, which are then embedded into a symbolic planning framework to enable preference-guided, adaptive plan generation and execution. Contribution/Results: Experiments demonstrate that PbP significantly improves success rates of state-of-the-art planners on personalized planning tasks. Moreover, the learned preference representations exhibit strong cross-scenario generalization, establishing a scalable methodological foundation for preference-aware, embodied intelligent agents engaged in personalized collaborative planning.

Technology Category

• Humans and AI: Human-Aware Planning and Behavior Prediction
• Multiagent Systems: Multiagent Planning
• Knowledge Representation and Reasoning: Preferences

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Agentic search

Abstract

Effective integration of AI agents into daily life requires them to understand and adapt to individual human preferences, particularly in collaborative roles. Although recent studies on embodied intelligence have advanced significantly, they typically adopt generalized approaches that overlook personal preferences in planning. We address this limitation by developing agents that not only learn preferences from few demonstrations but also learn to adapt their planning strategies based on these preferences. Our research leverages the observation that preferences, though implicitly expressed through minimal demonstrations, can generalize across diverse planning scenarios. To systematically evaluate this hypothesis, we introduce Preference-based Planning (PbP) benchmark, an embodied benchmark featuring hundreds of diverse preferences spanning from atomic actions to complex sequences. Our evaluation of SOTA methods reveals that while symbol-based approaches show promise in scalability, significant challenges remain in learning to generate and execute plans that satisfy personalized preferences. We further demonstrate that incorporating learned preferences as intermediate representations in planning significantly improves the agent's ability to construct personalized plans. These findings establish preferences as a valuable abstraction layer for adaptive planning, opening new directions for research in preference-guided plan generation and execution.

Problem

• AI Personalization
• Adaptive AI
• Collaborative Planning

Innovation

• Improved AI Strategy
• Preference-based Planning
• Personalized Planning