Self-Reflective Chain-of-Thought (SRCoT) is a modular architecture that structures text generation as a closed Retrieve–Reflect–Revise loop, separating environment state, persistent knowledge, accumulated experience, and short-term memory into provenance-labeled stores. BM25 retrieval supplies local context, while subsequent passes expose intermediate drafts, missing-information markers, follow-up queries, and optional claim–evidence mappings to inform retrieval, revision, clarification, or abstention decisions. The authors demonstrate the approach in synthetic emergency medical and simulation scenarios, showing source-labeled documentation, explicit gap marking, and structured dispatch-style outputs, while also noting provenance-assignment errors, incomplete evidence coverage, and unsafe assumptions that persist despite prompting constraints.
By Fabian Broszio, Michael Hoffmann, Adrian Paschke
arXiv:2605.11533v4 Announce Type: replace
Abstract: Routine clinical check-up reports combine laboratory measurements, physiological assessments, imaging findings and visually structured information,...
By Sike Xiang, Shuang Chen, Kevin Qinghong Lin, Jialin Yu, Yijia Sun, Philip Torr, Amir Atapour-Abarghouei
arXiv:2409. 07314v3 Announce Type: replace-cross Abstract: While Large Language Models (LLMs) achieve superhuman performance on standardized medical licensing exams, these static benchmarks have become saturated and increasingly disconnected from the functional requirements of clinical workflows.
By Praveenkumar Kanithi, Cl\'ement Christophe, Marco AF Pimentel, Tathagata Raha, Prateek Munjal, Nada Saadi, Hamza A Javed, Svetlana Maslenkova, Nasir Hayat, Ronnie Rajan, Shadab Khan
arXiv:2606. 09500v1 Announce Type: new Abstract: Objective.
By Yoojin Nam, Jinhoon Jeong, Namkug Kim
The paper introduces Clinical System One (CS1), a 4‑billion‑parameter decision model that rapidly produces typed judgments from clinical records. Trained on 12.4 million Q&A pairs from 3.6 million patients, CS1 can answer multiple questions in a single forward pass, providing probability estimates for uncertain cases. In evaluations on 963,408 held‑out patients and 21 external datasets, CS1 outperformed larger open models and, when paired with a language‑model agent, efficiently identified trial‑eligible patients with far fewer tokens.
By Andrew Zhang, Trinh T. L. Vuong, Sophia J. Wagner, Dongmin Bang, Tong Ding, Yuchang Su, Mary Cipperman, Christina S. Chen, Judith Lefkes, Ramin Kahidi, Ming Y. Lu, Caiwei Tian, Tianhao Luo, Jingnan Ma, Rowland Pettit, Long Phi Le, Faisal Mahmood
VeriPhy is an auditable physical‑verification system that evaluates generated video by compiling prompts into typed physical obligations and a statically validated execution plan before any frames are observed. During execution, it gates calls to frozen low‑level experts (e.g., segmentation, tracking, counting, depth, OCR, audio‑event detection) and returns provenance‑carrying evidence records, which are mapped to a three‑valued state (supported, contradicted, unknown) with full traceability. On a 1,500‑clip corpus of human‑annotated flaw records, VeriPhy accounts for 228 failures out of 304, outperforming a published question‑decomposition evaluator that accounts for 164, while also providing auditable evidence for each verdict.
arXiv:2508. 14817v2 Announce Type: replace-cross Abstract: Objective: To evaluate whether retrieval-augmented generation (RAG) can serve as an efficient alternative to long-context prompting for clinical reasoning over electronic health records (EHRs).
By Skatje Myers, Dmitriy Dligach, Timothy A. Miller, Samantha Barr, James Landefeld, Yanjun Gao, Matthew Churpek, Anoop Mayampurath, Majid Afshar
VeriPhy is an auditable physical‑verification system that transforms a text prompt into typed physical obligations and a statically validated execution plan before any video frames are generated. During execution, it gates calls to frozen low‑level experts (segmentation, tracking, counting, depth, OCR, audio‑event detection, etc.) and records provenance‑carrying evidence for each action. The system maps these records to a three‑valued state—supported, contradicted, or unknown—providing traceable verdicts that can be used to refine generation models.
By Wenzhuo Xu, Yuchen Zhu, Chongjian Ge, Xuan Shen, Jing Shi, Jason Kuen, Yongxin Chen, Molei Tao, Christopher McComb, Noelia Grande Guti\'errez, Jiuxiang Gu
The paper introduces CERTA, a decision‑level statistical certificate that decides when a quantized clinical language model can replace its native BF16 reference and escalates uncertain decisions to the reference model. Across eleven instruction‑tuned models (7‑72 B parameters) and 2,500 clinical‑verification decisions from 2,484 de‑identified patients, 8‑bit quantization achieved 99.8‑100% coverage, while 4‑bit configurations cut deployment costs to roughly 26–28% of the BF16 baseline with peak memory below a 48 GB accelerator. On external named‑entity benchmarks, the chosen NF4 settings showed only a 0.045 mean absolute F1 change, indicating minimal performance loss.
whyItMatters":"CERTA enables risk‑controlled deployment of smaller, cheaper models for clinical decision support, potentially making advanced language models more accessible in resource‑constrained healthcare settings."
By Ali H. Lazem, William Teahan
GLoC-EHR is a multimodal language model that processes electronic health records by combining a fixed-size global memory of the entire patient trajectory with a local memory of selected events. It generates hospital-course summaries and masked concept descriptions, then is fine‑tuned to cite evidence before answering clinical questions, using group relative policy optimization to reward correct, evidence‑supported responses. On MIMIC‑IV outcome tasks, GLoC‑EHR achieves the highest macro AUROC among compared models when answering directly, and maintains strong performance with evidence‑cited reasoning while adding distinct supported findings from the local memory.
By Chaiho Shin, Kwangsoo Kim
The paper surveys open, non‑proprietary large language models (LLMs) and AI foundation models (AIFMs) for clinical use, presenting a taxonomy of current state‑of‑the‑art models. It empirically tests open‑weight LLMs on a personalized‑prescription task, finding that they match or surpass a proprietary baseline in overall suitability accuracy, especially when combined with Retrieval‑Augmented Generation (RAG). A subjective evaluation by blinded raters shows mixed effects of RAG on perceived suitability across multiple dimensions, and the authors discuss ethical risks and the need for responsible deployment.
By Mahdi Alkaeed, Sofiat Abioye, Adnan Qayyum, Yosra Magdi Mekki, Ilhem Berrou, Mohamed Abdallah, Ala Al-Fuqaha, Muhammad Bilal, Junaid Qadir
arXiv:2607. 06802v1 Announce Type: cross Abstract: Open physiological corpora are heterogeneous: they use different sensors, labels, sampling rates, recording settings, and clinical endpoints.
By Dovy Paukstys