❌

Reading view

  •  

Building from Scratch: A Multi-Agent Framework with Human-in-the-Loop for Multilingual Legal Terminology Mapping

arXiv:2512.12950v1 Announce Type: cross Abstract: Accurately mapping legal terminology across languages remains a significant challenge, especially for language pairs like Chinese and Japanese, which share a large number of homographs with different meanings. Existing resources and standardized tools for these languages are limited. To address this, we propose a human-AI collaborative approach for building a multilingual legal terminology database, based on a multi-agent framework. This approach integrates advanced large language models and legal domain experts throughout the entire process-from raw document preprocessing, article-level alignment, to terminology extraction, mapping, and quality assurance. Unlike a single automated pipeline, our approach places greater emphasis on how human experts participate in this multi-agent system. Humans and AI agents take on different roles: AI agents handle specific, repetitive tasks, such as OCR, text segmentation, semantic alignment, and initial terminology extraction, while human experts provide crucial oversight, review, and supervise the outputs with contextual knowledge and legal judgment. We tested the effectiveness of this framework using a trilingual parallel corpus comprising 35 key Chinese statutes, along with their English and Japanese translations. The experimental results show that this human-in-the-loop, multi-agent workflow not only improves the precision and consistency of multilingual legal terminology mapping but also offers greater scalability compared to traditional manual methods.
  •  

Integrative network pharmacology, transcriptomics, and microbiomics elucidate the therapeutic mechanism of <em>Polygala tenuifolia</em> Willd water extract in chronic obstructive pulmonary disease

Front Microbiol. 2025 Nov 25;16:1703853. doi: 10.3389/fmicb.2025.1703853. eCollection 2025.

ABSTRACT

BACKGROUND: Polygala tenuifolia Willd (PT) is a plant with both medicinal and edible values. Traditionally, it has been used for sedation, enhancing cognition, resolving phlegm, and relieving cough. However, its protective effects and mechanisms against chronic obstructive pulmonary disease (COPD) remain unclear.

AIM OF THE STUDY: This study aims to observe the protective effects of the water extract of Polygala tenuifolia Willd (WEPT) on COPD, and to preliminarily elucidate its potential therapeutic mechanisms by integrating network pharmacology, molecular docking, multi-omics analysis, and molecular experiments.

METHODS AND MATERIALS: HPLC quantified WEPT constituents. COPD mice models established via chronic smoke exposure underwent WEPT treatment, and the therapeutic effect was evaluated by lung function test, histopathology and cytokine profiling. Integrated multi-omics analyses (network pharmacology, transcriptomics, microbiomics) identified bioactive compounds, therapeutic targets, pathway regulations, and microbiota dynamics. Molecular docking validated compound-target interactions, while immunohistochemical/fluorescence assays confirmed key protein expression in lung tissues.

RESULTS: WEPT administration effectively reduced inflammatory cytokine levels in COPD mice, improved lung function, and alleviated histopathological damage like alveolar structural injury and airway inflammation. Network pharmacology and transcriptomic analyses identified Norhyoscyamine and Onjixanthone I as key active components, targeting PIK3CA and AKT1 via PI3K-AKT pathway regulation. Microbiome analysis showed WEPT restored gut microbiota balance. Molecular docking confirmed strong binding of bioactive compounds to core targets, while immunostaining assays demonstrated WEPT suppressed p-PI3K and p-AKT protein expression.

CONCLUSION: WEPT may exert its intervention effects on COPD through a multi-target and multi-level comprehensive regulatory mechanism.

PMID:41377050 | PMC:PMC12685879 | DOI:10.3389/fmicb.2025.1703853

  •  

A Practical Framework for Evaluating Medical AI Security: Reproducible Assessment of Jailbreaking and Privacy Vulnerabilities Across Clinical Specialties

arXiv:2512.08185v1 Announce Type: cross Abstract: Medical Large Language Models (LLMs) are increasingly deployed for clinical decision support across diverse specialties, yet systematic evaluation of their robustness to adversarial misuse and privacy leakage remains inaccessible to most researchers. Existing security benchmarks require GPU clusters, commercial API access, or protected health data -- barriers that limit community participation in this critical research area. We propose a practical, fully reproducible framework for evaluating medical AI security under realistic resource constraints. Our framework design covers multiple medical specialties stratified by clinical risk -- from high-risk domains such as emergency medicine and psychiatry to general practice -- addressing jailbreaking attacks (role-playing, authority impersonation, multi-turn manipulation) and privacy extraction attacks. All evaluation utilizes synthetic patient records requiring no IRB approval. The framework is designed to run entirely on consumer CPU hardware using freely available models, eliminating cost barriers. We present the framework specification including threat models, data generation methodology, evaluation protocols, and scoring rubrics. This proposal establishes a foundation for comparative security assessment of medical-specialist models and defense mechanisms, advancing the broader goal of ensuring safe and trustworthy medical AI systems.
  •  

AI Application in Anti-Money Laundering for Sustainable and Transparent Financial Systems

arXiv:2512.06240v1 Announce Type: new Abstract: Money laundering and financial fraud remain major threats to global financial stability, costing trillions annually and challenging regulatory oversight. This paper reviews how artificial intelligence (AI) applications can modernize Anti-Money Laundering (AML) workflows by improving detection accuracy, lowering false-positive rates, and reducing the operational burden of manual investigations, thereby supporting more sustainable development. It further highlights future research directions including federated learning for privacy-preserving collaboration, fairness-aware and interpretable AI, reinforcement learning for adaptive defenses, and human-in-the-loop visualization systems to ensure that next-generation AML architectures remain transparent, accountable, and robust. In the final part, the paper proposes an AI-driven KYC application that integrates graph-based retrieval-augmented generation (RAG Graph) with generative models to enhance efficiency, transparency, and decision support in KYC processes related to money-laundering detection. Experimental results show that the RAG-Graph architecture delivers high faithfulness and strong answer relevancy across diverse evaluation settings, thereby enhancing the efficiency and transparency of KYC CDD/EDD workflows and contributing to more sustainable, resource-optimized compliance practices.
  •  

Rethinking Bias in Generative Data Augmentation for Medical AI: a Frequency Recalibration Method

arXiv:2511.12301v1 Announce Type: cross Abstract: Developing Medical AI relies on large datasets and easily suffers from data scarcity. Generative data augmentation (GDA) using AI generative models offers a solution to synthesize realistic medical images. However, the bias in GDA is often underestimated in medical domains, with concerns about the risk of introducing detrimental features generated by AI and harming downstream tasks. This paper identifies the frequency misalignment between real and synthesized images as one of the key factors underlying unreliable GDA and proposes the Frequency Recalibration (FreRec) method to reduce the frequency distributional discrepancy and thus improve GDA. FreRec involves (1) Statistical High-frequency Replacement (SHR) to roughly align high-frequency components and (2) Reconstructive High-frequency Mapping (RHM) to enhance image quality and reconstruct high-frequency details. Extensive experiments were conducted in various medical datasets, including brain MRIs, chest X-rays, and fundus images. The results show that FreRec significantly improves downstream medical image classification performance compared to uncalibrated AI-synthesized samples. FreRec is a standalone post-processing step that is compatible with any generative model and can integrate seamlessly with common medical GDA pipelines.
  •  

Stereo-seq V2: Spatial mapping of total RNA on FFPE sections with high resolution

Stereo-seq V2 facilitates single-cell-resolution spatial RNA mapping in FFPE samples through random primer capture, uncovering ncRNAs, host-pathogen transcriptome profiling, and spatial immune repertoires in situ.
  •  

TeaRAG: A Token-Efficient Agentic Retrieval-Augmented Generation Framework

arXiv:2511.05385v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) utilizes external knowledge to augment Large Language Models' (LLMs) reliability. For flexibility, agentic RAG employs autonomous, multi-round retrieval and reasoning to resolve queries. Although recent agentic RAG has improved via reinforcement learning, they often incur substantial token overhead from search and reasoning processes. This trade-off prioritizes accuracy over efficiency. To address this issue, this work proposes TeaRAG, a token-efficient agentic RAG framework capable of compressing both retrieval content and reasoning steps. 1) First, the retrieved content is compressed by augmenting chunk-based semantic retrieval with a graph retrieval using concise triplets. A knowledge association graph is then built from semantic similarity and co-occurrence. Finally, Personalized PageRank is leveraged to highlight key knowledge within this graph, reducing the number of tokens per retrieval. 2) Besides, to reduce reasoning steps, Iterative Process-aware Direct Preference Optimization (IP-DPO) is proposed. Specifically, our reward function evaluates the knowledge sufficiency by a knowledge matching mechanism, while penalizing excessive reasoning steps. This design can produce high-quality preference-pair datasets, supporting iterative DPO to improve reasoning conciseness. Across six datasets, TeaRAG improves the average Exact Match by 4% and 2% while reducing output tokens by 61% and 59% on Llama3-8B-Instruct and Qwen2.5-14B-Instruct, respectively. Code is available at https://github.com/Applied-Machine-Learning-Lab/TeaRAG.
  •  

Know What You Don't Know: Uncertainty Calibration of Process Reward Models

arXiv:2506.09338v2 Announce Type: replace-cross Abstract: Process reward models (PRMs) play a central role in guiding inference-time scaling algorithms for large language models (LLMs). However, we observe that even state-of-the-art PRMs can be poorly calibrated. Specifically, they tend to overestimate the success probability that a partial reasoning step will lead to a correct final answer, particularly when smaller LLMs are used to complete the reasoning trajectory. To address this, we present a calibration approach -- performed via quantile regression -- that adjusts PRM outputs to better align with true success probabilities. Leveraging these calibrated success estimates and their associated confidence bounds, we introduce an \emph{instance-adaptive scaling} (IAS) framework that dynamically adjusts the compute budget based on the estimated likelihood that a partial reasoning trajectory will yield a correct final answer. Unlike conventional methods that allocate a fixed number of reasoning trajectories per query, this approach adapts to each instance and reasoning step when using our calibrated PRMs. Experiments on mathematical reasoning benchmarks show that (i) our PRM calibration method achieves small calibration error, outperforming the baseline methods, (ii) calibration is crucial for enabling effective IAS, and (iii) the proposed IAS strategy reduces inference costs while maintaining final answer accuracy, utilizing less compute on more confident problems as desired.
  •  

A full life cycle biological clock based on routine clinical data and its impact in health and diseases

Nature Medicine, Published online: 27 October 2025; doi:10.1038/s41591-025-04006-w

The biological clock model LifeClock predicts biological age across all life stages from routine clinical data, revealing distinct pediatric and adult disease risk patterns.
  •  

FieldGen: From Teleoperated Pre-Manipulation Trajectories to Field-Guided Data Generation

arXiv:2510.20774v1 Announce Type: cross Abstract: Large-scale and diverse datasets are vital for training robust robotic manipulation policies, yet existing data collection methods struggle to balance scale, diversity, and quality. Simulation offers scalability but suffers from sim-to-real gaps, while teleoperation yields high-quality demonstrations with limited diversity and high labor cost. We introduce FieldGen, a field-guided data generation framework that enables scalable, diverse, and high-quality real-world data collection with minimal human supervision. FieldGen decomposes manipulation into two stages: a pre-manipulation phase, allowing trajectory diversity, and a fine manipulation phase requiring expert precision. Human demonstrations capture key contact and pose information, after which an attraction field automatically generates diverse trajectories converging to successful configurations. This decoupled design combines scalable trajectory diversity with precise supervision. Moreover, FieldGen-Reward augments generated data with reward annotations to further enhance policy learning. Experiments demonstrate that policies trained with FieldGen achieve higher success rates and improved stability compared to teleoperation-based baselines, while significantly reducing human effort in long-term real-world data collection. Webpage is available at https://fieldgen.github.io/.
  •  

Stereo-seq V2: Spatial mapping of total RNA on FFPE sections with high resolution

Cell. 2025 Aug 22:S0092-8674(25)00922-5. doi: 10.1016/j.cell.2025.08.008. Online ahead of print.

ABSTRACT

Performing total RNA profiling on formalin-fixed, paraffin-embedded (FFPE) samples, the predominant sample conservation method in clinical practice, remains challenging for current spatial transcriptomics techniques. Here, we introduce Stereo-seq V2, which employs random primers to capture and sequence RNAs in situ on FFPE sections and provides single-cell resolution. The random-priming-based strategy offers unbiased transcript capturing and uniform gene body coverage, which increase the sensitivity to marker genes, the efficiency of non-polyadenylation (poly(A)) RNA profiling, and immune repertoire coverage. We demonstrated the robust performance of Stereo-seq V2 on clinical FFPE samples using triple-negative breast cancer (TNBC) sections and identified tumor-specific alternative splicing events. In a Mycobacterium tuberculosis (Mtb)-infected mouse model, we monitored gene expression dynamics of host and pathogen transcriptomes simultaneously by utilizing Stereo-seq V2. We also assembled immune repertoires and identified Mtb-specific BCR clones, which could also be observed in human tuberculous lung samples. These results highlight Stereo-seq V2's potential in biomedical research and personalized medicine.

PMID:40882628 | DOI:10.1016/j.cell.2025.08.008

  •  

Treatment of advanced-stage non-small cell lung cancer: Current progress and a glimpse into the future (Review)

Mol Clin Oncol. 2025 Mar 12;22(5):42. doi: 10.3892/mco.2025.2837. eCollection 2025 May.

ABSTRACT

Before the twentieth century, patients with advanced lung cancer had limited treatment options and chemotherapy was the primary form of treatment, with an overall survival often <0.5 years. However, with advances in society and medical technology, the treatment approaches for advanced non-small cell lung cancer (NSCLC) have markedly changed. Traditional chemotherapy has been gradually replaced by targeted therapy and immunotherapy, leading to the emergence of various new therapeutic options that offer patients more personalized and precise care. This raises the question of what the future holds for the treatment of NSCLC. This review provides a comprehensive analysis of the latest breakthroughs in targeted therapies, immunotherapies, and drugs for antibody-drug conjugates (ADCs), highlights advances in multimodal combination therapy strategies, and explores the causes of resistance and the challenges that exist in overcoming it. In particular, this review provides unique insights into key directions for future research in NSCLC, such as personalised treatment strategies and biomarker exploration based on multi-omics data, aiming to provide new inspiration for clinical decision-making and research.

PMID:40160297 | PMC:PMC11948471 | DOI:10.3892/mco.2025.2837

  •  
❌