# ProCARE: Real-World Study Automation via Profile-Grounded Evidence Contracts

arXiv: https://arxiv.org/abs/2610.16175 · HTML: https://mlsanity.com/paper/2610.16175/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 66 references that are in the map.
- First posted on arXiv 12 Oct 2026.

## Builds on (most cited first, 23 of 23)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023)
- [Large Language Models Encode Clinical Knowledge](https://mlsanity.com/paper/2212.13138/) (2022)
- [Agent Laboratory: Using LLM Agents as Research Assistants](https://mlsanity.com/paper/2501.04227/) (2025)
- [Scalable and accurate deep learning for electronic health records](https://mlsanity.com/paper/1801.07860/) (2018)
- [Data Interpreter: An LLM Agent For Data Science](https://mlsanity.com/paper/2402.18679/) (2024)
- [InfiAgent-DABench: Evaluating Agents on Data Analysis Tasks](https://mlsanity.com/paper/2401.05507/) (2024)
- [DSBench: How Far Are Data Science Agents from Becoming Data Science Experts?](https://mlsanity.com/paper/2409.07703/) (2024)
- [TableGPT2: A Large Multimodal Model with Tabular Data Integration](https://mlsanity.com/paper/2411.02059/) (2024)
- [MedAgentBench: A Realistic Virtual EHR Environment to Benchmark Medical LLM Agents](https://mlsanity.com/paper/2501.14654/) (2025)
- [SheetCopilot: Bringing Software Productivity to the Next Level through Large Language Models](https://mlsanity.com/paper/2305.19308/) (2023)
- [DataSciBench: An LLM Agent Benchmark for Data Science](https://mlsanity.com/paper/2502.13897/) (2025)
- [TableRAG: Million-Token Table Understanding with Language Models](https://mlsanity.com/paper/2410.04739/) (2024)
- [Large Language Models for Scientific Synthesis, Inference and Explanation](https://mlsanity.com/paper/2310.07984/) (2023)
- [Limitations of Large Language Models in Clinical Problem-Solving Arising from Inflexible Reasoning](https://mlsanity.com/paper/2502.04381/) (2025)
- [TableRAG: A Retrieval Augmented Generation Framework for Heterogeneous Document Reasoning](https://mlsanity.com/paper/2506.10380/) (2025)
- [FHIR-AgentBench: Benchmarking LLM Agents for Realistic Interoperable EHR Question Answering](https://mlsanity.com/paper/2509.19319/) (2025)
- [Overview of the EHRSQL 2024 Shared Task on Reliable Text-to-SQL Modeling on Electronic Health Records](https://mlsanity.com/paper/2405.06673/) (2024)
- [Unveiling Challenges for LLMs in Enterprise Data Engineering](https://mlsanity.com/paper/2504.10950/) (2025)
- [EHRStruct: A Comprehensive Benchmark Framework for Evaluating Large Language Models on Structured Electronic Health Record Tasks](https://mlsanity.com/paper/2511.08206/) (2025)
- [Can LLM Agents Generate Real-World Evidence? Evaluating Observational Studies in Medical Databases](https://mlsanity.com/paper/2603.22767/) (2026)

## Abstract (arXiv)

Real-world studies (RWS) analyze routinely collected healthcare data, such as electronic health records and insurance claims, to estimate treatment effects, monitor safety, and identify risk factors outside randomized trials. Automating RWS with large language model agents is appealing but brittle: valid analyses depend on dataset-specific clinical semantics, including index dates, follow-up windows, patient/event-level units, and outcome boundaries that are often implicit in observational data. This leads to schema mismatches, temporal errors, inconsistent analytical granularity, and unsupported clinical claims. We present ProCARE, a profile-grounded framework that reformulates RWS automation as constrained compilation. ProCARE converts heterogeneous data profiles into Evidence Contracts specifying available variables, temporal attributes, distributions, and evidentiary limits, and compiles study objectives into RWS-IR, a strongly typed intermediate representation for variables, time relations, analysis units, and statistical tasks. Deterministic validation and localized repair then check and revise generated workflows across schema mapping, cohort construction, variable derivation, analysis, and interpretation. On 36 EHR-based benchmark tasks, ProCARE outperforms strong LLM-agent baselines in code executability, semantic consistency, and conclusion traceability, with automated violation diagnoses showing moderate-to-substantial agreement with blinded expert review.