arXiv:2609.01202v1 Announce Type: cross Abstract: Clinical trials are essential for advancing cancer care and drug development, but many fail because of insufficient patient enrollment. While there i...
The paper introduces a retrieval‑augmented multi‑agent framework that automatically generates instance‑specific evaluation rubrics for medical language models. By retrieving authoritative medical evidence, decomposing it into atomic facts, and combining these with user interaction constraints, the system produces fine‑grained criteria that outperform GPT‑4o on HealthBench and LLMEval‑Med. The generated rubrics also guide response refinement, improving medical LLM output quality by 9.2%.
arXiv:2609.21859v1 Announce Type: new Abstract: Nearly 90% of drugs entering clinical development ultimately fail, despite billions of dollars in investment. Pharmaceutical companies therefore rely o...
arXiv:2608.22062v1 Announce Type: new Abstract: Longitudinal clinical event-relation verification determines whether a patient record supports a specified relation among two or more clinical events....
arXiv:2608. 07796v1 Announce Type: new Abstract: Large language models perform strongly on medical knowledge benchmarks, but reliable clinical deployment requires agents to conduct defensible investigations over heterogeneous, longitudinal records: determining what evidence is needed, retrieving and reconciling structured and free-text data, grounding conclusions in verifiable evidence, and deferring cases that cannot be resolved reliably.
FD‑SCoPE is a language‑model framework that answers clinicians’ questions about systematic review evidence tables, exposing the underlying query, selected trials, and derivation rule for each answer. It handles both directly recorded attributes and derived attributes, achieving high accuracy on an oncology evidence table of 159 immune‑checkpoint inhibitor trials. After incorporating expert corrections, its performance on unseen questions improved from 77.9% to 84.9% F1.
arXiv:2603. 10494v2 Announce Type: replace-cross Abstract: Evidence-grounded generation produces summaries whose claims should be supported by supplied evidence, but claim-level verifiers provide noisy feedback and can reward models that simply say less.
arXiv:2610.16175v1 Announce Type: new Abstract: Real-world studies (RWS) analyze routinely collected healthcare data, such as electronic health records and insurance claims, to estimate treatment eff...
arXiv:2607. 09932v1 Announce Type: cross Abstract: Large language models are increasingly used to summarize clinical trial results for healthcare providers, patients, and payers, but their tendency to hallucinate poses significant risks in this high-stakes context.
arXiv:2610.41710v1 Announce Type: new Abstract: Clinical trial failures are a major barrier to efficient drug development, incurring substantial costs and delaying patient access to effective therapi...
arXiv:2604. 08849v2 Announce Type: replace-cross Abstract: Many important retrieval problems are not merely problems of semantic similarity, but problems of constraint satisfaction: a retrieved item should be topically relevant to a query and satisfy explicit requirements involving negation, temporal conditions, numeric thresholds, exceptions, ontological relations, and incomplete evidence.
VirtualTrialHarness (VTHarness) is an agent framework designed to streamline the operationalization of virtual trial protocols by selecting reusable procedural skills for each workflow stage and using explicit contracts to ensure consistent study decisions. It introduces VTBenchmark for evaluating source selection and cohort construction, achieving 95.1% workflow success after requirement clarification versus 60.4% with a standard procedural corpus. The framework demonstrated improved source recovery across language models, increased overlap with analyst code in Mayo Clinic cases, and enabled reference‑matched cohort execution across multiple MIMIC‑IV tasks, supporting investigator review within the Mayo Clinic Virtual Trials Program.