mlsanityData to 14 Oct 2026

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

arXiv 2610.16175 ↗First posted 12 Oct 2026cs.AIcited by 0

Not on the map. Why?

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.

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

23 of 66 references.

References · 23

  1. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  2. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
  3. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,988
  4. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,947
  5. 2022Large Language Models Encode Clinical Knowledgecited by 1,830
  6. 2025Agent Laboratory: Using LLM Agents as Research Assistantscited by 425
  7. 2018Scalable and accurate deep learning for electronic health recordscited by 280
  8. 2024Data Interpreter: An LLM Agent For Data Sciencecited by 225
  9. 2024InfiAgent-DABench: Evaluating Agents on Data Analysis Taskscited by 140
  10. 2024DSBench: How Far Are Data Science Agents from Becoming Data Science Experts?cited by 125
  11. 2024TableGPT2: A Large Multimodal Model with Tabular Data Integrationcited by 72
  12. 2025MedAgentBench: A Realistic Virtual EHR Environment to Benchmark Medical LLM Agentscited by 62
11 more
  1. 2023SheetCopilot: Bringing Software Productivity to the Next Level through Large Language Modelscited by 57
  2. 2025DataSciBench: An LLM Agent Benchmark for Data Sciencecited by 57
  3. 2024TableRAG: Million-Token Table Understanding with Language Modelscited by 41
  4. 2023Large Language Models for Scientific Synthesis, Inference and Explanationcited by 39
  5. 2025Limitations of Large Language Models in Clinical Problem-Solving Arising from Inflexible Reasoningcited by 31
  6. 2025TableRAG: A Retrieval Augmented Generation Framework for Heterogeneous Document Reasoningcited by 24
  7. 2025FHIR-AgentBench: Benchmarking LLM Agents for Realistic Interoperable EHR Question Answeringcited by 22
  8. 2024Overview of the EHRSQL 2024 Shared Task on Reliable Text-to-SQL Modeling on Electronic Health Recordscited by 11
  9. 2025Unveiling Challenges for LLMs in Enterprise Data Engineeringcited by 9
  10. 2025EHRStruct: A Comprehensive Benchmark Framework for Evaluating Large Language Models on Structured Electronic Health Record Taskscited by 6
  11. 2026Can LLM Agents Generate Real-World Evidence? Evaluating Observational Studies in Medical Databasescited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026From Statistical Fidelity to Clinical Consistency: Scalable Generation and Auditing of Synthetic Patient Trajectories
  2. 2026Synthetic Hospital: An Open, Verifiable, Physician-Validated Longitudinal EHR Benchmark
  3. 2026FastOMOP: A Foundational Architecture for Reliable Agentic Real-World Evidence Generation on OMOP CDM data
  4. 2026EHRWorld: A Patient-Centric Medical World Model for Long-Horizon Clinical Trajectories
  5. 2026PhysicianBench: Evaluating LLM Agents in Real-World EHR Environments
  6. 2026MedProbeBench: Systematic Benchmarking at Deep Evidence Integration for Expert-level Medical Guideline
  7. 2026MedHarnessBench: A Unified Benchmark for Healthcare Agent Evaluation
  8. 2026CliniCARE-Bench: Clinical Calibrated Audit of Medical Reasoning in EHR