Related papers: PathWISE: Multi-Agent Cancer Pathway Triaging Onto…
Matching cancer patients to clinical trials is essential for advancing treatment and patient care. However, the inconsistent format of medical free text documents and complex trial eligibility criteria make this process extremely…
Monitoring Machine Learning (ML) models in production environments is crucial, yet traditional approaches often yield verbose, low-interpretability outputs that hinder effective decision-making. We propose a cognitive architecture for ML…
Symbolic execution is a widely used technique for test generation, offering systematic exploration of program paths through constraint solving. However, it is fundamentally constrained by the capability to model the target code, including…
Scientific algorithm discovery is iterative: hypotheses are proposed, implemented, stress-tested, and revised. Current LLM-guided search systems accelerate proposal generation, but often under-represent scientific structure by optimizing…
The use of knowledge graphs for grounding agents in real-world Q&A applications has become increasingly common. Answering complex queries often requires multi-hop reasoning and the ability to navigate vast relational structures. Standard…
Despite strong results on many tasks, multimodal large language models (MLLMs) still underperform on visual mathematical problem solving, especially in reliably perceiving and interpreting diagrams. Inspired by human problem-solving, we…
Cancer staging is critical for patient prognosis and treatment planning, yet extracting pathologic TNM staging from unstructured pathology reports poses a persistent challenge. Existing natural language processing (NLP) and machine learning…
Clinical decision making (CDM) is a complex, dynamic process crucial to healthcare delivery, yet it remains a significant challenge for artificial intelligence systems. While Large Language Model (LLM)-based agents have been tested on…
LLM API calls are becoming a ubiquitous program construct, yet they create a boundary that no existing program analysis can cross: runtime values enter a natural-language prompt, undergo opaque processing inside the LLM, and re-emerge as…
Retrieval-augmented generation (RAG) mitigates hallucination in Large Language Models (LLMs) by using query pipelines to retrieve relevant external information and grounding responses in retrieved knowledge. However, query pipeline…
Lipidomics generates large data that makes manual annotation and interpretation challenging. Lipid chemical and structural diversity with structural isomers further complicates annotation. Although, several commercial and open-source…
Computational Workflows are widely used in data analysis, enabling innovation and decision-making. In many domains (bioinformatics, image analysis, & radio astronomy) the analysis components are numerous and written in multiple different…
Automatically filling Case Report Forms (CRFs) from clinical notes is challenging due to noisy language, strict output contracts, and the high cost of false positives. We describe our CL4Health 2026 submission for Dyspnea CRF filling (134…
Recent progress in large language models (LLMs) has made knowledge-grounded reasoning increasingly practical, yet KG-based QA systems often pay a steep price in efficiency and transparency. In typical pipelines, symbolic paths are scored by…
Recent advances in large language models (LLMs) transform how machine learning (ML) pipelines are developed and evaluated. LLMs enable a new type of workload, agentic pipeline search, in which autonomous or semi-autonomous agents generate,…
Automating scientific discovery requires more than generating papers from ideas. Real research is iterative: hypotheses are challenged from multiple perspectives, experiments fail and inform the next attempt, and lessons accumulate across…
Addressing the critical need for accurate prognostic biomarkers in cancer treatment, quantifying tumor-infiltrating lymphocytes (TILs) in non-small cell lung cancer (NSCLC) presents considerable challenges. Manual TIL quantification in…
Clinical decision-making depends on expert reasoning, which is guided by standardized, evidence-based guidelines. However, translating these guidelines into automated clinical decision support systems risks inaccuracy and importantly, loss…
Most existing LLM diagnoses are evaluated on static, single-turn settings where complete patient information is provided upfront, an oversimplification of real clinical practice. We study active diagnosis: the real-life clinical process of…
Clinical trials are notorious for their high failure rates and steep costs, leading to wasted time and resources spend, prolonged development timelines, and delayed patient access to new therapies. A key contributor to these failures is…