# CarePilot: A Multi-Agent Framework for Long-Horizon Computer Task Automation in Healthcare

arXiv: https://arxiv.org/abs/2603.24157 · HTML: https://mlsanity.com/paper/2603.24157/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Medical and scientific domain agents, one of 16 directions in LLM agents and tool use.
- Builds on 36 of its 52 references that are in the map.
- First posted on arXiv 25 Mar 2026.

## Placed in

- LLM agents and tool use / [Medical and scientific domain agents](https://mlsanity.com/agents/medical-and-scientific-domain-agents/)

## Builds on (most cited first, 30 of 36)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [WebArena: A Realistic Web Environment for Building Autonomous Agents](https://mlsanity.com/paper/2307.13854/) (2023)
- [Mind2Web: Towards a Generalist Agent for the Web](https://mlsanity.com/paper/2306.06070/) (2023)
- [OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments](https://mlsanity.com/paper/2404.07972/) (2024)
- [Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models](https://mlsanity.com/paper/2303.04671/) (2023)
- [UI-TARS: Pioneering Automated GUI Interaction with Native Agents](https://mlsanity.com/paper/2501.12326/) (2025)
- [GPT-4V(ision) is a Generalist Web Agent, if Grounded](https://mlsanity.com/paper/2401.01614/) (2024)
- [AppAgent: Multimodal Agents as Smartphone Users](https://mlsanity.com/paper/2312.13771/) (2023)
- [Augmented Language Models: a Survey](https://mlsanity.com/paper/2302.07842/) (2023)
- [AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agents](https://mlsanity.com/paper/2407.18901/) (2024)
- [Scalable and accurate deep learning for electronic health records](https://mlsanity.com/paper/1801.07860/) (2018)
- [Actor-Attention-Critic for Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1810.02912/) (2018)
- [AgentClinic: a multimodal agent benchmark to evaluate AI in simulated clinical environments](https://mlsanity.com/paper/2405.07960/) (2024)
- [GUIOdyssey: A Comprehensive Dataset for Cross-App GUI Navigation on Mobile Devices](https://mlsanity.com/paper/2406.08451/) (2024)
- [TaskMatrix.AI: Completing Tasks by Connecting Foundation Models with Millions of APIs](https://mlsanity.com/paper/2303.16434/) (2023)
- [JARVIS-1: Open-World Multi-task Agents with Memory-Augmented Multimodal Language Models](https://mlsanity.com/paper/2311.05997/) (2023)
- [Large Language Model-Brained GUI Agents: A Survey](https://mlsanity.com/paper/2411.18279/) (2024)
- [AndroidEnv: A Reinforcement Learning Platform for Android](https://mlsanity.com/paper/2105.13231/) (2021)
- [Foundational Models in Medical Imaging: A Comprehensive Survey and Future Vision](https://mlsanity.com/paper/2310.18689/) (2023)
- [Exploring the Frontier of Vision-Language Models: A Survey of Current Methodologies and Future Directions](https://mlsanity.com/paper/2404.07214/) (2024)
- [Hierarchical Memory for High-Efficiency Long-Term Reasoning in LLM Agents](https://mlsanity.com/paper/2507.22925/) (2025)
- [CLIPSyntel: CLIP and LLM Synergy for Multimodal Question Summarization in Healthcare](https://mlsanity.com/paper/2312.11541/) (2023)
- [MedSumm: A Multimodal Approach to Summarizing Code-Mixed Hindi-English Clinical Queries](https://mlsanity.com/paper/2401.01596/) (2024)
- [NVIDIA Nemotron Nano V2 VL](https://mlsanity.com/paper/2511.03929/) (2025)
- [SANSKRITI: A Comprehensive Benchmark for Evaluating Language Models' Knowledge of Indian Culture](https://mlsanity.com/paper/2506.15355/) (2025)
- [Chiron-o1: Igniting Multimodal Large Language Models towards Generalizable Medical Reasoning via Mentor-Intern Collaborative Search](https://mlsanity.com/paper/2506.16962/) (2025)
- [DRISHTIKON: A Multimodal Multilingual Benchmark for Testing Language Models' Understanding on Indian Culture](https://mlsanity.com/paper/2509.19274/) (2025)

## Built on by (most cited first, 4 of 4)

- [When Background Matters: Breaking Medical Vision Language Models by Transferable Attack](https://mlsanity.com/paper/2604.17318/) (2026)
- [M3 QuestionIng: Multi-modal Multi-span Medical Question Answering](https://mlsanity.com/paper/2606.28329/) (2026)
- [PersuaRL: Reinforcement Learning-Driven Multi-Expert Selection for Persuasive Dialogue Generation in Insurance](https://mlsanity.com/paper/2609.01188/) (2026)
- [MEA: A Reward-Driven Multi-Agent System for Faithful Model Explanations](https://mlsanity.com/paper/2610.02480/) (2026)

## Abstract (arXiv)

Multimodal agentic pipelines are transforming human-computer interaction by enabling efficient and accessible automation of complex, real-world tasks. However, recent efforts have focused on short-horizon or general-purpose applications (e.g., mobile or desktop interfaces), leaving long-horizon automation for domain-specific systems, particularly in healthcare, largely unexplored. To address this, we introduce CareFlow, a high-quality human-annotated benchmark comprising complex, long-horizon software workflows across medical annotation tools, DICOM viewers, EHR systems, and laboratory information systems. On this benchmark, existing vision-language models (VLMs) perform poorly, struggling with long-horizon reasoning and multi-step interactions in medical contexts. To overcome this, we propose CarePilot, a multi-agent framework based on the actor-critic paradigm. The Actor integrates tool grounding with dual-memory mechanisms (long-term and short-term experience) to predict the next semantic action from the visual interface and system state. The Critic evaluates each action, updates memory based on observed effects, and either executes or provides corrective feedback to refine the workflow. Through iterative agentic simulation, the Actor learns to perform more robust and reasoning-aware predictions during inference. Our experiments show that CarePilot achieves state-of-the-art performance, outperforming strong closed-source and open-source multimodal baselines by approximately 15.26% and 3.38%, respectively, on our benchmark and out-of-distribution dataset.