# APRICOT: Active Preference Learning and Constraint-Aware Task Planning with LLMs

arXiv: https://arxiv.org/abs/2410.19656 · HTML: https://mlsanity.com/paper/2410.19656/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Oct 2024.

## Built on by (most cited first, 11 of 11)

- [On the Reliability of Computer Use Agents](https://mlsanity.com/paper/2604.17849/) (2026)
- [AdaPlanBench: Evaluating Adaptive Planning in Large Language Model Agents under World and User Constraints](https://mlsanity.com/paper/2606.05622/) (2026)
- [ADAPT: Actively Discovering and Adapting to Preferences for any Task](https://mlsanity.com/paper/2504.04040/) (2025)
- [Autonomous Human-Robot Interaction via Operator Imitation](https://mlsanity.com/paper/2504.02724/) (2025)
- [MCTS-EP: Empowering Embodied Planning with Online Preference Optimization](https://mlsanity.com/paper/2509.17116/) (2025)
- [Personalized Robotic Object Rearrangement from Scene Context](https://mlsanity.com/paper/2505.11108/) (2025)
- [Coloring Between the Lines: Personalization in the Null Space of Planning Constraints](https://mlsanity.com/paper/2505.15503/) (2025)
- [Casper: Inferring Diverse Intents for Assistive Teleoperation with Vision Language Models](https://mlsanity.com/paper/2506.14727/) (2025)
- [Toward Ownership Understanding of Objects: Active Question Generation with Large Language Model and Probabilistic Generative Model](https://mlsanity.com/paper/2509.12754/) (2025)
- [Adaptive Learning Systems: Personalized Curriculum Design Using LLM-Powered Analytics](https://mlsanity.com/paper/2507.18949/) (2025)
- [Explaining Why Things Go Where They Go: Interpretable Constructs of Human Organizational Preferences](https://mlsanity.com/paper/2512.24829/) (2025)

## Abstract (arXiv)

Home robots performing personalized tasks must adeptly balance user preferences with environmental affordances. We focus on organization tasks within constrained spaces, such as arranging items into a refrigerator, where preferences for placement collide with physical limitations. The robot must infer user preferences based on a small set of demonstrations, which is easier for users to provide than extensively defining all their requirements. While recent works use Large Language Models (LLMs) to learn preferences from user demonstrations, they encounter two fundamental challenges. First, there is inherent ambiguity in interpreting user actions, as multiple preferences can often explain a single observed behavior. Second, not all user preferences are practically feasible due to geometric constraints in the environment. To address these challenges, we introduce APRICOT, a novel approach that merges LLM-based Bayesian active preference learning with constraint-aware task planning. APRICOT refines its generated preferences by actively querying the user and dynamically adapts its plan to respect environmental constraints. We evaluate APRICOT on a dataset of diverse organization tasks and demonstrate its effectiveness in real-world scenarios, showing significant improvements in both preference satisfaction and plan feasibility. The project website is at https://portal-cornell.github.io/apricot/