Personalized Medication Planning via Direct Domain Modeling and LLM-Generated Heuristics

2026-01-07

arXiv.org

AI Summary

This work proposes a novel approach to personalized medication planning that integrates procedural modeling of the medical domain with large language model (LLM)-generated, problem-specific heuristics to enable efficient planning via greedy best-first search (GBFS). Personalized treatment regimens require tailored drug combinations and dosages, yet existing methods are limited to handling at most seven drugs, falling short of clinical requirements. By combining explicit domain modeling with LLM-derived heuristics, the proposed method overcomes the scalability limitations of conventional generic heuristics, extending support from seven to at least twenty-eight drug types. This advancement significantly improves both planning coverage and computational efficiency, representing a substantial step toward the clinical practicality of personalized medication planning.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Search and Optimization: Heuristic Search
• Multiagent Systems: Multiagent Planning

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• 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

Personalized medication planning involves selecting medications and determining a dosing schedule to achieve medical goals specific to each individual patient. Previous work successfully demonstrated that automated planners, using general domain-independent heuristics, are able to generate personalized treatments, when the domain and problems are modeled using a general domain description language (\pddlp). Unfortunately, this process was limited in practice to consider no more than seven medications. In clinical terms, this is a non-starter. In this paper, we explore the use of automatically-generated domain- and problem-specific heuristics to be used with general search, as a method of scaling up medication planning to levels allowing closer work with clinicians. Specifically, we specify the domain programmatically (specifying an initial state and a successor generation procedure), and use an LLM to generate a problem specific heuristic that can be used by a fixed search algorithm (GBFS). The results indicate dramatic improvements in coverage and planning time, scaling up the number of medications to at least 28, and bringing medication planning one step closer to practical applications.

Problem

• Personalized Medication Planning
• Scalability
• Multi-drug Therapy
• Automated Planning
• Clinical Applicability

Innovation

• LLM-generated heuristics
• personalized medication planning
• domain-specific heuristics
• programmatic domain modeling
• GBFS