DoctorAgents is proposed, an agentic AI framework that autonomously constructs and optimizes end-to-end ML pipelines through specialized large language model (LLM) agents for generation, validation, and refinement.
Abstract
Clinical machine learning (ML) has the potential to support high-stakes medical decision-making, but reliable deployment is often constrained by scarce, heterogeneous, and temporal complexity. Developing effective ML pipelines for such data remains time-consuming and error-prone, while existing automated machine learning (AutoML) systems only partially address this challenge because they largely rely on brute-force search over predefined spaces and lack explicit reasoning and memory. We therefore reformulate AutoML for small clinical data from exhaustive search to reasoning-driven refinement. We propose DoctorAgents, an agentic AI framework that autonomously constructs and optimizes end-to-end ML pipelines through specialized large language model (LLM) agents for generation, validation, and refinement. DoctorAgents backpropagates natural-language feedback through textual gradient descent to perform targeted updates without exhaustive search. Experiments across diverse clinical tasks show that DoctorAgents consistently outperforms established AutoML baselines while producing more interpretable task-specific representations.
Large language model (LLM) agents are beginning to automate machine learning engineering (MLE) by coupling planning, code execution, debugging, and empirical feedback. Translating this capability to medical imaging remains difficult because each task imposes modality-specific experimentation and strict requirements for validation protocols and prediction artifacts. Here we introduce AMID, an autonomous multi-agent framework for medical imaging model development. AMID first proposes Data-Conditioned Method Planning, which refines coarse task-level search spaces into executable, parallelizable method lanes grounded in task-specific data analysis and runnable medical-imaging resources. It then develops Verification-Guided Two-Stage Optimization, moving from broad early exploration of diverse method lanes to selective exploitation of promising candidates while enforcing strict verification of validation protocols, metric computation, and prediction artifacts throughout the optimization. Across 20 medical imaging challenge tasks spanning diverse modalities and prediction types, AMID outperformed evaluated general-purpose MLE systems and, on several tasks, approached or matched strong human-designed challenge solutions. These results suggest that AMID can turn task-specific medical imaging model development from bespoke manual engineering into an agentic workflow for producing high-performing and auditable model artifacts across heterogeneous tasks.
Shengyuan Liu, Jiaxuan Jiang, Boyun Zheng et al.· arXiv.org· 0 citations
Clinical modeling experience is established as a promising collaborative object beyond conventional parameter-centric FL and point toward federated autonomous clinical intelligence.
Experimental results on a broad range of MLE tasks with diverse model types and scales demonstrate that Matryoshka Agent is an effective and scalable paradigm for long-horizon MLE tasks and complex agentic problem solving.
Rushi Qiang, Changhao Li, Haotian Sun et al.· arXiv.org· 0 citations
This work introduces AgentSearch, a cost-aware Monte Carlo Tree Search (MCTS) framework that constructs agentic workflows through deliberative lookahead search and attains single-episode success while reducing computational costs by up to 47%, thereby eliminating the trial-and-error exploration required by previous adaptive methods.
D. Attota, Ying Xie· International Conference on...· 0 citations
This survey provides a structured synthesis of how recent work connects foundation models to governable biomedical agentic systems and distills the recurring challenges and directions identified in the literature for reliable, accountable deployment.
Ali Abdollahi, Mohammad Amin Rezaei, Xi Wang et al.· IEEE Reviews in Biomedical E...· 1 citation
A scoping review with systematic evidence mapping across five electronic sources, screened 1,649 exportable records, and provisionally included 557 unique studies that met predefined criteria for goal-directed task execution, tool use, interaction with external resources, feedback-based refinement, or multi-agent collaboration.
Zheng Tong, Yang Liu, Wan-Shu Fan et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
