# "I Want It That Way": Enabling Interactive Decision Support Using Large Language Models and Constraint Programming

arXiv: https://arxiv.org/abs/2312.06908 · HTML: https://mlsanity.com/paper/2312.06908/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Dec 2023.

## Built on by (most cited first, 19 of 19)

- [Understanding Information Storage and Transfer in Multi-modal Large Language Models](https://mlsanity.com/paper/2406.04236/) (2024)
- [OptiMUS-0.3: Using Large Language Models to Model and Solve Optimization Problems at Scale](https://mlsanity.com/paper/2407.19633/) (2024)
- [Graph-enhanced Large Language Models in Asynchronous Plan Reasoning](https://mlsanity.com/paper/2402.02805/) (2024)
- [Large Language Models for Combinatorial Optimization: A Systematic Review](https://mlsanity.com/paper/2507.03637/) (2025)
- [A Systematic Survey on Large Language Models for Evolutionary Optimization: From Modeling to Solving](https://mlsanity.com/paper/2509.08269/) (2025)
- [EquivaMap: Leveraging LLMs for Automatic Equivalence Checking of Optimization Formulations](https://mlsanity.com/paper/2502.14760/) (2025)
- [Combining Constraint Programming Reasoning with Large Language Model Predictions](https://mlsanity.com/paper/2407.13490/) (2024)
- [LLMs for Cold-Start Cutting Plane Separator Configuration](https://mlsanity.com/paper/2412.12038/) (2024)
- [OptiChat: Bridging Optimization Models and Practitioners with Large Language Models](https://mlsanity.com/paper/2501.08406/) (2025)
- [DualSchool: How Reliable are LLMs for Optimization Education?](https://mlsanity.com/paper/2505.21775/) (2025)
- [Cooperative Design Optimization through Natural Language Interaction](https://mlsanity.com/paper/2508.16077/) (2025)
- [Let's Have a Conversation: Designing and Evaluating LLM Agents for Interactive Optimization](https://mlsanity.com/paper/2604.02666/) (2026)
- [LISTEN to Your Preferences: An LLM Framework for Multi-Objective Selection](https://mlsanity.com/paper/2510.25799/) (2025)
- [Applying Cognitive Design Patterns to General LLM Agents](https://mlsanity.com/paper/2505.07087/) (2025)
- [FLARE: Verifying MILP Reformulations with LLM-Based Theorem Proving](https://mlsanity.com/paper/2608.25220/) (2026)
- [Who Does What? Archetypes of Roles Assigned to LLMs During Human-AI Decision-Making](https://mlsanity.com/paper/2602.11924/) (2026)
- [Text2Model: Modeling Copilots for Text-to-Model Translation](https://mlsanity.com/paper/2604.12955/) (2026)
- [Ontology-Mediated Neurosymbolic Constraint Acquisition from Multiple Stakeholders](https://mlsanity.com/paper/2609.29876/) (2026)
- [Neuro-symbolic AI for Industrial Configuration](https://mlsanity.com/paper/2609.29947/) (2026)

## Abstract (arXiv)

A critical factor in the success of decision support systems is the accurate modeling of user preferences. Psychology research has demonstrated that users often develop their preferences during the elicitation process, highlighting the pivotal role of system-user interaction in developing personalized systems. This paper introduces a novel approach, combining Large Language Models (LLMs) with Constraint Programming to facilitate interactive decision support. We study this hybrid framework through the lens of meeting scheduling, a time-consuming daily activity faced by a multitude of information workers. We conduct three studies to evaluate the novel framework, including a diary study (n=64) to characterize contextual scheduling preferences, a quantitative evaluation of the system's performance, and a user study (n=10) with a prototype system. Our work highlights the potential for a hybrid LLM and optimization approach for iterative preference elicitation and design considerations for building systems that support human-system collaborative decision-making processes.