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

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.

MedSPOT: A Workflow-Aware Sequential Grounding Benchmark for Clinical GUI

Despite the rapid progress of Multimodal Large Language Models (MLLMs), their ability to perform reliable visual grounding in high-stakes clinical software environments remains underexplored. Existing GUI benchmarks largely focus on isolated, single-step grounding queries, overlooking the sequential, workflow-driven reasoning required in real-world medical interfaces, where tasks evolve across independent steps and dynamic interface states. We introduce MedSPOT, a workflow-aware sequential grounding benchmark for clinical GUI environments. Unlike prior benchmarks that treat grounding as a standalone prediction task, MedSPOT models procedural interaction as a sequence of structured spatial decisions. The benchmark comprises 216 task-driven videos with 597 annotated keyframes, in which each task consists of 2 to 3 interdependent grounding steps within realistic medical workflows. This design captures interface hierarchies, contextual dependencies, and fine-grained spatial precision under evolving conditions. To evaluate procedural robustness, we propose a strict sequential evaluation protocol that terminates task assessment upon the first incorrect grounding prediction, explicitly measuring error propagation in multi-step workflows. We further introduce a comprehensive failure taxonomy, including edge bias, small-target errors, no prediction, near miss, far miss, and toolbar confusion, to enable systematic diagnosis of model behavior in clinical GUI settings. By shifting evaluation from isolated grounding to workflow-aware sequential reasoning, MedSPOT establishes a realistic and safety-critical benchmark for assessing multimodal models in medical software environments. Code and data are available at: https://github.com/Tajamul21/MedSPOT.

QTrack: Query-Driven Reasoning for Multi-modal MOT

Multi-object tracking (MOT) has traditionally focused on estimating trajectories of all objects in a video, without selectively reasoning about user-specified targets under semantic instructions. In this work, we introduce a query-driven tracking paradigm that formulates tracking as a spatiotemporal reasoning problem conditioned on natural language queries. Given a reference frame, a video sequence, and a textual query, the goal is to localize and track only the target(s) specified in the query while maintaining temporal coherence and identity consistency. To support this setting, we construct RMOT26, a large-scale benchmark with grounded queries and sequence-level splits to prevent identity leakage and enable robust evaluation of generalization. We further present QTrack, an end-to-end vision-language model that integrates multimodal reasoning with tracking-oriented localization. Additionally, we introduce a Temporal Perception-Aware Policy Optimization strategy with structured rewards to encourage motion-aware reasoning. Extensive experiments demonstrate the effectiveness of our approach for reasoning-centric, language-guided tracking. Code and data are available at https://github.com/gaash-lab/QTrack

GroundedSurg: A Multi-Procedure Benchmark for Language-Conditioned Surgical Tool Segmentation

Clinically reliable perception of surgical scenes is essential for advancing intelligent, context-aware intraoperative assistance such as instrument handoff guidance, collision avoidance, and workflow-aware robotic support. Existing surgical tool benchmarks primarily evaluate category-level segmentation, requiring models to detect all instances of predefined instrument classes. However, real-world clinical decisions often require resolving references to a specific instrument instance based on its functional role, spatial relation, or anatomical interaction capabilities not captured by current evaluation paradigms. We introduce GroundedSurg, the first language-conditioned, instance-level surgical grounding benchmark. Each instance pairs a surgical image with a natural-language description targeting a single instrument, accompanied by structured spatial grounding annotations including bounding boxes and point-level anchors. The dataset spans ophthalmic, laparoscopic, robotic, and open procedures, encompassing diverse instrument types, imaging conditions, and operative complexities. By jointly evaluating linguistic reference resolution and pixel-level localization, GroundedSurg enables a systematic and realistic evaluation of vision-language models in clinically realistic multi-instrument scenes. Extensive experiments demonstrate substantial performance gaps across modern segmentation and VLMs, highlighting the urgent need for clinically grounded vision-language reasoning in surgical AI systems. Code and data are publicly available at https://github.com/gaash-lab/GroundedSurg

MATRIX: Multimodal Agent Tuning for Robust Tool-Use Reasoning

Vision language models (VLMs) are increasingly deployed as controllers with access to external tools for complex reasoning and decision-making, yet their effectiveness remains limited by the scarcity of high-quality multimodal trajectories and the cost of manual annotation. We address this challenge with a vision-centric agent tuning framework that automatically synthesizes multimodal trajectories, generates step-wise preference pairs, and trains a VLM controller for robust tool-use reasoning. Our pipeline first constructs M-TRACE, a large-scale dataset of 28.5K multimodal tasks with 177K verified trajectories, enabling imitation-based trajectory tuning. Building on this, we develop MATRIX Agent, a controller finetuned on M-TRACE for step-wise tool reasoning. To achieve finer alignment, we further introduce Pref-X, a set of 11K automatically generated preference pairs, and optimize MATRIX on it via step-wise preference learning. Across three benchmarks, Agent-X, GTA, and GAIA, MATRIX consistently surpasses both open- and closed-source VLMs, demonstrating scalable and effective multimodal tool use. Our data and code is avaliable at https://github.com/mbzuai-oryx/MATRIX.

MIRA: A Novel Framework for Fusing Modalities in Medical RAG

Multimodal Large Language Models (MLLMs) have significantly advanced AI-assisted medical diagnosis, but they often generate factually inconsistent responses that deviate from established medical knowledge. Retrieval-Augmented Generation (RAG) enhances factual accuracy by integrating external sources, but it presents two key challenges. First, insufficient retrieval can miss critical information, whereas excessive retrieval can introduce irrelevant or misleading content, disrupting model output. Second, even when the model initially provides correct answers, over-reliance on retrieved data can lead to factual errors. To address these issues, we introduce the Multimodal Intelligent Retrieval and Augmentation (MIRA) framework, designed to optimize factual accuracy in MLLM. MIRA consists of two key components: (1) a calibrated Rethinking and Rearrangement module that dynamically adjusts the number of retrieved contexts to manage factual risk, and (2) A medical RAG framework integrating image embeddings and a medical knowledge base with a query-rewrite module for efficient multimodal reasoning. This enables the model to effectively integrate both its inherent knowledge and external references. Our evaluation of publicly available medical VQA and report generation benchmarks demonstrates that MIRA substantially enhances factual accuracy and overall performance, achieving new state-of-the-art results. Code is released at https://github.com/mbzuai-oryx/MIRA.

TITAN: Query-Token based Domain Adaptive Adversarial Learning

We focus on the source-free domain adaptive object detection (SF-DAOD) problem when source data is unavailable during adaptation and the model must adapt to an unlabeled target domain. The majority of approaches for the problem employ a self-supervised approach using a student-teacher (ST) framework where pseudo-labels are generated via a source-pretrained model for further fine-tuning. We observe that the performance of a student model often degrades drastically, due to the collapse of the teacher model, primarily caused by high noise in pseudo-labels, resulting from domain bias, discrepancies, and a significant domain shift across domains. To obtain reliable pseudo-labels, we propose a Target-based Iterative Query-Token Adversarial Network (TITAN), which separates the target images into two subsets: those similar to the source (easy) and those dissimilar (hard). We propose a strategy to estimate variance to partition the target domain. This approach leverages the insight that higher detection variances correspond to higher recall and greater similarity to the source domain. Also, we incorporate query-token-based adversarial modules into a student-teacher baseline framework to reduce the domain gaps between two feature representations. Experiments conducted on four natural imaging datasets and two challenging medical datasets have substantiated the superior performance of TITAN compared to existing state-of-the-art (SOTA) methodologies. We report an mAP improvement of +22.7, +22.2, +21.1, and +3.7 percent over the current SOTA on C2F, C2B, S2C, and K2C benchmarks, respectively.

Agent-X: Evaluating Deep Multimodal Reasoning in Vision-Centric Agentic Tasks

Deep reasoning is fundamental for solving complex tasks, especially in vision-centric scenarios that demand sequential, multimodal understanding. However, existing benchmarks typically evaluate agents with fully synthetic, single-turn queries, limited visual modalities, and lack a framework to assess reasoning quality over multiple steps as required in real-world settings. To address this, we introduce Agent-X, a large-scale benchmark for evaluating vision-centric agents multi-step and deep reasoning capabilities in real-world, multimodal settings. Agent- X features 828 agentic tasks with authentic visual contexts, including images, multi-image comparisons, videos, and instructional text. These tasks span six major agentic environments: general visual reasoning, web browsing, security and surveillance, autonomous driving, sports, and math reasoning. Our benchmark requires agents to integrate tool use with explicit, stepwise decision-making in these diverse settings. In addition, we propose a fine-grained, step-level evaluation framework that assesses the correctness and logical coherence of each reasoning step and the effectiveness of tool usage throughout the task. Our results reveal that even the best-performing models, including GPT, Gemini, and Qwen families, struggle to solve multi-step vision tasks, achieving less than 50% full-chain success. These findings highlight key bottlenecks in current LMM reasoning and tool-use capabilities and identify future research directions in vision-centric agentic reasoning models. Our data and code are publicly available at https://github.com/mbzuai-oryx/Agent-X

ATR-Bench: A Federated Learning Benchmark for Adaptation, Trust, and Reasoning

Federated Learning (FL) has emerged as a promising paradigm for collaborative model training while preserving data privacy across decentralized participants. As FL adoption grows, numerous techniques have been proposed to tackle its practical challenges. However, the lack of standardized evaluation across key dimensions hampers systematic progress and fair comparison of FL methods. In this work, we introduce ATR-Bench, a unified framework for analyzing federated learning through three foundational dimensions: Adaptation, Trust, and Reasoning. We provide an in-depth examination of the conceptual foundations, task formulations, and open research challenges associated with each theme. We have extensively benchmarked representative methods and datasets for adaptation to heterogeneous clients and trustworthiness in adversarial or unreliable environments. Due to the lack of reliable metrics and models for reasoning in FL, we only provide literature-driven insights for this dimension. ATR-Bench lays the groundwork for a systematic and holistic evaluation of federated learning with real-world relevance. We will make our complete codebase publicly accessible and a curated repository that continuously tracks new developments and research in the FL literature.

Context Aware Grounded Teacher for Source Free Object Detection

We focus on the Source Free Object Detection (SFOD) problem, when source data is unavailable during adaptation, and the model must adapt to the unlabeled target domain. In medical imaging, several approaches have leveraged a semi-supervised student-teacher architecture to bridge domain discrepancy. Context imbalance in labeled training data and significant domain shifts between domains can lead to biased teacher models that produce inaccurate pseudolabels, degrading the student model's performance and causing a mode collapse. Class imbalance, particularly when one class significantly outnumbers another, leads to contextual bias. To tackle the problem of context bias and the significant performance drop of the student model in the SFOD setting, we introduce Grounded Teacher (GT) as a standard framework. In this study, we model contextual relationships using a dedicated relational context module and leverage it to mitigate inherent biases in the model. This approach enables us to apply augmentations to closely related classes, across and within domains, enhancing the performance of underrepresented classes while keeping the effect on dominant classes minimal. We further improve the quality of predictions by implementing an expert foundational branch to supervise the student model. We validate the effectiveness of our approach in mitigating context bias under the SFOD setting through experiments on three medical datasets supported by comprehensive ablation studies. All relevant resources, including preprocessed data, trained model weights, and code, are publicly available at this https://github.com/Tajamul21/Grounded_Teacher.