❌

Normal view

Received — 20 January 2026 ⏭ Favourites

LLM-driven collaborative framework for knowledge-enhanced cancer pain assessment and management

✇npj Digital Medicine
By: Haixiao Liu · Yue Hu · Dongtao Li · Boyuan Shi · Yupeng Niu · Xinche Zhang · Guangda Zheng · Changlin Li · Lingyun Wang · Yanju Bao
19 January 2026 at 08:00

npj Digital Medicine, Published online: 19 January 2026; doi:10.1038/s41746-026-02362-6

LLM-driven collaborative framework for knowledge-enhanced cancer pain assessment and management
Received — 13 January 2026 ⏭ Favourites

PulseMind: A Multi-Modal Medical Model for Real-World Clinical Diagnosis

✇cs.AI, q-bio.NC updates on arXiv.org
By: Jiao Xu · Junwei Liu · Jiangwei Lao · Qi Zhu · Yunpeng Zhao · Congyun Jin · Shinan Liu · Zhihong Lu · Lihe Zhang · Xin Chen · Jian Wang · Ping Wang
13 January 2026 at 13:00
arXiv:2601.07344v1 Announce Type: cross Abstract: Recent advances in medical multi-modal models focus on specialized image analysis like dermatology, pathology, or radiology. However, they do not fully capture the complexity of real-world clinical diagnostics, which involve heterogeneous inputs and require ongoing contextual understanding during patient-physician interactions. To bridge this gap, we introduce PulseMind, a new family of multi-modal diagnostic models that integrates a systematically curated dataset, a comprehensive evaluation benchmark, and a tailored training framework. Specifically, we first construct a diagnostic dataset, MediScope, which comprises 98,000 real-world multi-turn consultations and 601,500 medical images, spanning over 10 major clinical departments and more than 200 sub-specialties. Then, to better reflect the requirements of real-world clinical diagnosis, we develop the PulseMind Benchmark, a multi-turn diagnostic consultation benchmark with a four-dimensional evaluation protocol comprising proactiveness, accuracy, usefulness, and language quality. Finally, we design a training framework tailored for multi-modal clinical diagnostics, centered around a core component named Comparison-based Reinforcement Policy Optimization (CRPO). Compared to absolute score rewards, CRPO uses relative preference signals from multi-dimensional com-parisons to provide stable and human-aligned training guidance. Extensive experiments demonstrate that PulseMind achieves competitive performance on both the diagnostic consultation benchmark and public medical benchmarks.
Received — 18 November 2025 ⏭ Favourites

Fault2Flow: An AlphaEvolve-Optimized Human-in-the-Loop Multi-Agent System for Fault-to-Workflow Automation

✇cs.AI, q-bio.NC updates on arXiv.org
By: Yafang Wang · Yangjie Tian · Xiaoyu Shen · Gaoyang Zhang · Jiaze Sun · He Zhang · Ruohua Xu · Feng Zhao
18 November 2025 at 13:00
arXiv:2511.12916v1 Announce Type: new Abstract: Power grid fault diagnosis is a critical process hindered by its reliance on manual, error-prone methods. Technicians must manually extract reasoning logic from dense regulations and attempt to combine it with tacit expert knowledge, which is inefficient, error-prone, and lacks maintainability as ragulations are updated and experience evolves. While Large Language Models (LLMs) have shown promise in parsing unstructured text, no existing framework integrates these two disparate knowledge sources into a single, verified, and executable workflow. To bridge this gap, we propose Fault2Flow, an LLM-based multi-agent system. Fault2Flow systematically: (1) extracts and structures regulatory logic into PASTA-formatted fault trees; (2) integrates expert knowledge via a human-in-the-loop interface for verification; (3) optimizes the reasoning logic using a novel AlphaEvolve module; and (4) synthesizes the final, verified logic into an n8n-executable workflow. Experimental validation on transformer fault diagnosis datasets confirms 100\% topological consistency and high semantic fidelity. Fault2Flow establishes a reproducible path from fault analysis to operational automation, substantially reducing expert workload.
Received — 28 October 2025 ⏭ Favourites

Language Ranker: A Lightweight Ranking framework for LLM Decoding

✇cs.AI, q-bio.NC updates on arXiv.org
By: Chenheng Zhang · Tianqi Du · Jizhe Zhang · Mingqing Xiao · Yifei Wang · Yisen Wang · Zhouchen Lin
28 October 2025 at 12:00
arXiv:2510.21883v1 Announce Type: cross Abstract: Conventional research on large language models (LLMs) has primarily focused on refining output distributions, while paying less attention to the decoding process that transforms these distributions into final responses. Recent advances, such as scaling the computation of inference time with reward models, have underscored the importance of decoding, but these methods often suffer from high computational costs and limited applicability. In this paper, we revisit LLM generation through the lens of recommender systems, conceptualizing the decoding process as analogous to the ranking stage in recommendation pipelines. From this perspective, we observe that both traditional decoding methods and reward models exhibit clear limitations such as redundancy. Motivated by this insight, we propose Language Ranker, a novel framework that introduces a lightweight module to rerank candidate responses using features extracted by the base model. Experiments across a wide range of tasks show that Language Ranker achieves performance comparable to large-scale reward models, while requiring only
Received — 20 October 2025 ⏭ Favourites

Systematic benchmarking of high-throughput subcellular spatial transcriptomics platforms across human tumors

✇(Multiomics OR Omics) AND (Lung OR gastric OR Hepatocellular)
By: Pengfei Ren · Rui Zhang · Yunfeng Wang · Peng Zhang · Ce Luo · Suyan Wang · Xiaohong Li · Zongxu Zhang · Yanping Zhao · Yufeng He · Haorui Zhang · Yufeng Li · Zhidong Gao · Xiuping Zhang · Yahui Zhao · Zhihua Liu · Yuanguang Meng · Zhe Zhang · Zexian Zeng
17 October 2025 at 18:00

Nat Commun. 2025 Oct 17;16(1):9232. doi: 10.1038/s41467-025-64292-3.

ABSTRACT

Recent advancements in spatial transcriptomics technologies have significantly enhanced resolution and throughput, underscoring an urgent need for systematic benchmarking. Here, we generate serial tissue sections from colon adenocarcinoma, hepatocellular carcinoma, and ovarian cancer samples for systematic evaluation. Using these uniformly processed samples, we generate spatial transcriptomics data across four high-throughput platforms with subcellular resolution: Stereo-seq v1.3, Visium HD FFPE, CosMx 6K, and Xenium 5K. To establish ground truth datasets, we profile proteins on tissue sections adjacent to all platforms using CODEX and perform single-cell RNA sequencing on the same samples. Leveraging manual nuclear segmentation and detailed annotations, we systematically assess each platform's performance across capture sensitivity, specificity, diffusion control, cell segmentation, cell annotation, spatial clustering, and concordance with adjacent CODEX. The uniformly generated and processed multi-omics dataset could advance computational method development and biological discoveries. The dataset is accessible via SPATCH, a user-friendly web server for visualization and download.

PMID:41107232 | PMC:PMC12534522 | DOI:10.1038/s41467-025-64292-3

Received — 19 May 2025 ⏭ Favourites

Tumor-derived exosomal CCT6A serves as a matchmaker introducing chemokines to tumor-associated macrophages in pancreatic ductal adenocarcinoma

✇(Multiomics OR Omics) AND (Pancreatic)
By: Tianyin Ma · Wing-Wa Guo · Minghe Zhang · Wenzhi He · Cairang Dongzhi · Xiangdong Gongye · Peng Xia · Yibo Chai · Zhang Chen · Yimin Zhu · Chengming Qu · Jie Liu · Zhiyong Yang · Weijie Ma · Ming Tian · Yufeng Yuan
15 May 2025 at 18:00

Cell Death Dis. 2025 May 15;16(1):382. doi: 10.1038/s41419-025-07720-y.

ABSTRACT

M2-polarized tumor-associated macrophages (TAMs) are a key factor contributing to the poor prognosis of pancreatic ductal adenocarcinoma (PDAC). While various factors within the tumor microenvironment (TME) drive their formation, the role of PDAC-derived exosomes in this process remains unclear. We aim to clarify the regulatory impacts of tumor-derived exosomes to TAMs. After the intratumoral injection to subcutaneous tumor of C57BL/6 mice, we demonstrated PDAC-derived exosomes exacerbate PDAC progression, accompanied with upregulated M2 phenotype of TAMs and unaffected proliferation signatures. Through intratumoral injection model and multi-Omics analyses, we identified CCT6A as a novel tumor-derived exosomal protein, bridging TAMs M2 polarization and PDAC prognosis. Co-culture with exosomes derived from CCT6Ahigh PDAC leads to greater M2 phenotype of TAMs via PI3K-AKT signaling. According to proteomics data, chemokines' abundance reduces over tenfold once exosomal CCT6A absence, including CXCL1, CXCL3, CCL20 and CCL5, whose interaction with CCT6A in PDAC cells was confirmed by interactomics data. Moreover, we found silencing CCT6A abrogated the antagonism effects of CD47 antibody immunotherapy. Our findings implied that the subunit of the T-complex protein Ring Complex (TRiC) CCT6A serves as a matchmaker during exosome-mediated chemokines transfer from PDAC to TAMs. Silencing CCT6A effectively sensitized PDAC to CD47 antibody immunotherapy in vivo.

PMID:40374617 | PMC:PMC12081750 | DOI:10.1038/s41419-025-07720-y

Received — 24 December 2024 ⏭ Favourites
There are no more articles
❌