clinical-reasoning

Cura 1T is a healthcare-specialized LLM trained via a human-gated self-evolution loop that iteratively improves on patient consultation, clinical reasoning, and agentic healthcare tasks, achieving top performance on medical benchmarks while maintaining general reasoning ability.

The paper develops an agentic evaluation framework for clinical reasoning in hematologic oncology, finding that LLMs primarily fail due to systematic information-seeking deficits rather than insufficient knowledge, with error patterns resembling cognitive biases in novice clinicians.

This paper evaluates retrieval-augmented generation (RAG) versus long-context prompting for clinical reasoning tasks over electronic health records, finding RAG to be token-efficient and competitive, especially for imaging extraction and antibiotic timeline reconstruction.

This paper presents HCC-STAR, a clinically aligned large language model for risk stratification and treatment guidance in hepatocellular carcinoma, aiming to improve precision therapy by leveraging electronic medical records.

AegisDx is a safety-oriented framework that uses specialized LLM components and verification gates for hypothetico-deductive clinical reasoning, improving differential diagnosis accuracy by 7-17 percentage points over standalone LLMs on medical case reports.

CLExEval introduces a human-in-the-loop framework for evaluating LLM clinical reasoning under progressive information masking, revealing failure patterns such as verbosity bias, hidden knowledge paradox, and reasoning-to-output mismatch in models like GPT-4o-mini and HuatuoGPT-o1.

Introduces MRPO, a reinforcement learning algorithm that uses step-wise process rewards to mitigate cascading errors in clinical multimodal reasoning, outperforming existing methods on medical VQA benchmarks.

This paper introduces SkeMex, a self-evolving framework that enhances medical agents by distilling interaction trajectories into structured skill memory, enabling better long-term clinical reasoning through context-dependent utility estimation and governance.

ChatHealthAI is a multimodal reasoning framework that aligns structured EHR representations with a frozen LLM to enable grounded clinical reasoning while maintaining predictive performance.

MedGuideX transforms clinical practice guidelines into executable decision logic to generate factual and counterfactual QA data for training medical LLMs, achieving a 10.28% relative improvement in average accuracy across clinical reasoning benchmarks.

SEMA-RAG is a self-evolving multi-agent RAG framework for medical question answering that decouples interpretation, exploration, and adjudication into three specialist agents, achieving significant accuracy improvements over baselines across multiple benchmarks.

ClinSeekAgent is an automated agentic framework that enables large language models to actively acquire and synthesize multimodal clinical evidence from raw data sources, improving decision-making accuracy in both text-only and multimodal tasks. It introduces the ClinSeek-Bench benchmark and a distilled model ClinSeek-35B-A3B that achieves strong performance on agentic clinical reasoning.

This paper introduces Checkup2Action, a multimodal dataset and benchmark for generating patient-oriented action cards from clinical check-up reports, addressing the interpretability gap for laypersons.