The paper presents a pipeline that uses Large Language Models (LLMs) to extract information from 536 peer‑reviewed agent‑based modeling papers for systematic literature reviews (SLRs). GPT‑4.1 achieves about 77.95% paper‑level accuracy, while GPT‑5.0 reaches 81.67%. Field‑level accuracy varies widely, and the study notes that agreement between LLMs can signal output quality, with low agreement indicating hallucinations and high agreement with low accuracy suggesting noise in the human dataset.
By Orhan Yagizer Cinar, Timur Emre Ozkose, Emma Von Hoene, Amira Roess, Taylor Anderson, Hamdi Kavak
arXiv:2606.16149v5 Announce Type: replace
Abstract: Rare disease diagnosis depends on expert reasoning that is scarce and difficult to transfer. Large language models rank the correct disease first i...
By Minh-Ha Nguyen, Erica Gray, Bryce A. Schuler, Kevin W. Byram, Chih-Ting Yang, Fan Ma, Hua Xu, Wu-Chen Su, Chao Yan, Wei-Qi Wei, Adam Wright, Lisa Bastarache, Josh F. Peterson, Lingyao Li, Siyuan Ma, Undiagnosed Diseases Network, Rizwan Hamid, Thomas A. Cassini, Cathy Shyr
The paper investigates how large language models can extract contextualized data from scientific literature. It presents four workflows: expert‑written prompts, self‑generated prompts, autonomous literature discovery, and dataset creation from guidelines. While models perform well with prompts, they struggle with context, hallucinate references, and still need human oversight for final validation.
By Valentin Romanov, Monique Bax, Steven Niederer
The paper evaluates browser-based large language models (LLMs) for extracting detailed, contextualized data from scientific papers. It presents four workflows: (1) expert-curated prompts yield good extraction but struggle with nuance; (2) LLMs can generate effective prompts from simple instructions; (3) autonomous literature discovery is challenging, with missing or hallucinated references; (4) LLMs can build new datasets from guidelines that align closely with human experts, yet still need human oversight. The study outlines a practical, auditable workflow where experts set standards, models cross-check extractions, and researchers resolve disputes, enabling scalable scientific data curation.
arXiv:2509. 23426v3 Announce Type: replace Abstract: AI scientists are emerging computational systems that serve as collaborative partners in discovery.
By Shanghua Gao, Richard Zhu, Pengwei Sui, Zhenglun Kong, Sufian Aldogom, Yepeng Huang, Ayush Noori, Reza Shamji, Krishna Parvataneni, Theodoros Tsiligkaridis, Marinka Zitnik
arXiv:2606. 28363v1 Announce Type: cross Abstract: Objective: To describe the architecture and design rationale of meta-pipe, an open-source large language model (LLM)-agent pipeline that integrates the complete systematic review and meta-analysis (SR/MA) workflow -- from literature search through statistical analysis, manuscript generation, and quality assurance -- with mandatory human oversight at critical decision points.
By Hsieh-Ting Lin, Jiunn-Tyng Yeh
arXiv:2608.30912v1 Announce Type: new
Abstract: Artificial intelligence (AI) and natural language processing (NLP) are increasingly used to extract, integrate, and interpret biomedical knowledge rele...
By Bahar \.Ilgen, Yiannos Tolias, Denise K\"uhnert, Paraskevi Papadopoulou, Magnus Westerlund, Dominik Heider, Katharina Ladewig, Georges Hattab
arXiv:2607. 21173v1 Announce Type: new Abstract: While automated research systems promise to accelerate empirical analysis, they are prone to silent failures: instances in which analysis code executes successfully yet relies on invalid causal assumptions.
By Irena Girshovitz, Dan Zeltzer, Ran Gilad-Bachrach
The paper presents an autonomous AI agent that combines ReAct and Retrieval-Augmented Generation to classify the severity of genetic diseases using 10,211 Human Phenotype Ontology terms. It applies ACMG severity guidelines and ACOG quality-of-life criteria, retrieving PubMed literature to produce interpretable reasoning chains and verify claims. The agent achieved 93.55% accuracy on phenotype-level classification and identified 3,283 autosomal recessive gene pairs with severe presentations, with 95.2% concordance in external validation.
By Tohid Ghasemnejad, Ahmadreza Argha, Mark Grosser, John Wang, Min Yang, Thantrira Porntaveetus, Tony Roscioli, Nigel H. Lovell, Mahmoud Aarabi, Hamid Alinejad-Rokny
Large language models (LLMs) increasingly support science, but they can also convert hazardous scientific knowledge into actionable misuse guidance. Existing benchmarks often rely on templated queries disconnected from real-world hazards, and employ LLM-as-a-Judge paradigms without domain grounding.
The paper introduces SRBench, a benchmark dataset comprising 45,064 labeled entries from 32 curated secondary studies, designed to evaluate large language model performance in systematic review screening while addressing class imbalance. It also presents PromptSR, a tool that facilitates prompt experimentation, experiment management, and result analysis for LLM-based screening. A use case demonstrates the practical application of both SRBench and PromptSR.
By Gauransh Kumar, Luciano Marchezan, Guillaume Genois, K\'evin Delcourt, Eugene Syriani
EviStreams is a live, open‑source, no‑code web platform that enables systematic review teams to control AI‑assisted data extraction at three stages: program design, field specification, and extracted predictions. Reviewers use a form builder to define typed fields, run extraction on PDFs, inspect AI‑generated values with supporting passages, and perform blinded dual review with adjudication to produce an auditable consensus export. An evaluation across four clinical corpora and three model families shows that extraction quality depends more on field specification than on the model choice.
By Sai Karthik Kosuri, Ankita Shashikant Bhosale, Michael Glick, Alonso Carrasco-Labra, Chris Callison-Burch