# Prompt or Policy? Optimizing Physician Slate Presentations with LLM User Simulators

arXiv: https://arxiv.org/abs/2610.18309 · HTML: https://mlsanity.com/paper/2610.18309/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 36 references that are in the map.
- First posted on arXiv 13 Oct 2026.

## Builds on (most cited first, 21 of 21)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Scaling Laws for Reward Model Overoptimization](https://mlsanity.com/paper/2210.10760/) (2022)
- [Large Language Models as Optimizers](https://mlsanity.com/paper/2309.03409/) (2023)
- [Automatic Prompt Optimization with "Gradient Descent" and Beam Search](https://mlsanity.com/paper/2305.03495/) (2023)
- [On Generative Agents in Recommendation](https://mlsanity.com/paper/2310.10108/) (2023)
- [Fine-Tuning and Prompt Optimization: Two Great Steps that Work Better Together](https://mlsanity.com/paper/2407.10930/) (2024)
- [PatientSim: A Persona-Driven Simulator for Realistic Doctor-Patient Interactions](https://mlsanity.com/paper/2505.17818/) (2025)
- [ConvApparel: A Benchmark Dataset and Validation Framework for User Simulators in Conversational Recommenders](https://mlsanity.com/paper/2602.16938/) (2026)
- [Dr.Copilot: A Multi-Agent Prompt Optimized Assistant for Improving Patient-Doctor Communication in Romanian](https://mlsanity.com/paper/2507.11299/) (2025)
- [A Zero-shot Explainable Doctor Ranking Framework with Large Language Models](https://mlsanity.com/paper/2503.02298/) (2025)
- [Automatic Prompt Optimization for Dataset-Level Feature Discovery](https://mlsanity.com/paper/2601.13922/) (2026)
- [From Ranked Lists to Carousels: A Carousel Click Model](https://mlsanity.com/paper/2209.13426/) (2022)
- [Evaluating the Effectiveness of Black-Box Prompt Optimization as the Scale of LLMs Continues to Grow](https://mlsanity.com/paper/2505.08303/) (2025)
- [PromptBridge: Cross-Model Prompt Transfer for Large Language Models](https://mlsanity.com/paper/2512.01420/) (2025)
- [UserSimCRS v2: Simulation-Based Evaluation for Conversational Recommender Systems](https://mlsanity.com/paper/2512.04588/) (2025)
- [Validating Search Query Simulations: A Taxonomy of Measures](https://mlsanity.com/paper/2601.11412/) (2026)
- [LLM-as-a-Judge in Healthcare: A Scoping Analysis of Applications, Methods, and Human Alignment](https://mlsanity.com/paper/2605.25273/) (2026)
- [Doctor Recommendation in Online Health Forums via Expertise Learning](https://mlsanity.com/paper/2203.02932/) (2022)
- [Improving Medical Communication using Rubric-Guided Counterfactual Recommendations](https://mlsanity.com/paper/2606.18889/) (2026)
- [Persona Conditioning as an Assessor-Sensitivity Probe for LLM-Based IR Evaluation](https://mlsanity.com/paper/2608.10385/) (2026)

## Abstract (arXiv)

Choosing the right physician is a key challenge for patients seeking medical care. Physician recommendation systems identify relevant doctors, but patients still find it difficult to compare their profiles to make a decision. We formulate slate presentation optimization: given a patient's medical case and a fixed, ranked list of physicians, we generate short, case-specific summaries that make doctors easier to compare, while remaining grounded in the information in their profiles. To optimize physician presentations without relying on real patient interactions, we develop an offline framework that uses persona-conditioned LLMs to simulate patient choices. We generate patient personas from attributes extracted from each medical case and evaluate presentations for factual accuracy, relevance, naturalness and simulated patient choice. We also use a second LLM judge, unseen during optimization, to assess simulator-specific overfitting. We compare automatic prompt-level optimization with GEPA, parameter-level optimization with GRPO, and their combination across two model sizes. GRPO substantially outperforms GEPA in satisfying the full set of constraints, and its gains in simulated conversion persist under the unseen judge. GEPA alone brings smaller improvements, but using its optimized prompt to initialize GRPO speeds up training and achieves the highest simulated conversion. These results show that prompt-level and parameter-level optimization play complementary roles in improving how physician recommendations are presented.