❌

Normal view

Received — 12 January 2026 ⏭ Favourites

CliCARE: Grounding Large Language Models in Clinical Guidelines for Decision Support over Longitudinal Cancer Electronic Health Records

✇cs.AI, q-bio.NC updates on arXiv.org
By: Dongchen Li · Jitao Liang · Wei Li · Xiaoyu Wang · Longbing Cao · Kun Yu
12 January 2026 at 13:00
arXiv:2507.22533v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) hold significant promise for improving clinical decision support and reducing physician burnout by synthesizing complex, longitudinal cancer Electronic Health Records (EHRs). However, their implementation in this critical field faces three primary challenges: the inability to effectively process the extensive length and fragmented nature of patient records for accurate temporal analysis; a heightened risk of clinical hallucination, as conventional grounding techniques such as Retrieval-Augmented Generation (RAG) do not adequately incorporate process-oriented clinical guidelines; and unreliable evaluation metrics that hinder the validation of AI systems in oncology. To address these issues, we propose CliCARE, a framework for Grounding Large Language Models in Clinical Guidelines for Decision Support over Longitudinal Cancer Electronic Health Records. The framework operates by transforming unstructured, longitudinal EHRs into patient-specific Temporal Knowledge Graphs (TKGs) to capture long-range dependencies, and then grounding the decision support process by aligning these real-world patient trajectories with a normative guideline knowledge graph. This approach provides oncologists with evidence-grounded decision support by generating a high-fidelity clinical summary and an actionable recommendation. We validated our framework using large-scale, longitudinal data from a private Chinese cancer dataset and the public English MIMIC-IV dataset. In these settings, CliCARE significantly outperforms baselines, including leading long-context LLMs and Knowledge Graph-enhanced RAG methods. The clinical validity of our results is supported by a robust evaluation protocol, which demonstrates a high correlation with assessments made by oncologists.
Received — 9 January 2026 ⏭ Favourites

Sci-Reasoning: A Dataset Decoding AI Innovation Patterns

✇cs.AI, q-bio.NC updates on arXiv.org
By: Jiachen Liu · Maestro Harmon · Zechen Zhang
9 January 2026 at 13:00
arXiv:2601.04577v1 Announce Type: new Abstract: While AI innovation accelerates rapidly, the intellectual process behind breakthroughs -- how researchers identify gaps, synthesize prior work, and generate insights -- remains poorly understood. The lack of structured data on scientific reasoning hinders systematic analysis and development of AI research agents. We introduce Sci-Reasoning, the first dataset capturing the intellectual synthesis behind high-quality AI research. Using community-validated quality signals and an LLM-accelerated, human-verified pipeline, we trace Oral and Spotlight papers across NeurIPS, ICML, and ICLR (2023-2025) to its key predecessors, articulating specific reasoning links in a structured format. Our analysis identifies 15 distinct thinking patterns, with three dominant strategies accounting for 52.7%: Gap-Driven Reframing (24.2%), Cross-Domain Synthesis (18.0%), and Representation Shift (10.5%). The most powerful innovation recipes combine multiple patterns: Gap-Driven Reframing + Representation Shift, Cross-Domain Synthesis + Representation Shift, and Gap-Driven Reframing + Cross-Domain Synthesis. This dataset enables quantitative studies of scientific progress and provides structured reasoning trajectories for training the next generation AI research agents.
Received — 7 January 2026 ⏭ Favourites

Digital Twin AI: Opportunities and Challenges from Large Language Models to World Models

✇cs.AI, q-bio.NC updates on arXiv.org
By: Rong Zhou · Dongping Chen · Zihan Jia · Yao Su · Yixin Liu · Yiwen Lu · Dongwei Shi · Yue Huang · Tianyang Xu · Yi Pan · Xinliang Li · Yohannes Abate · Qingyu Chen · Zhengzhong Tu · Yu Yang · Yu Zhang · Qingsong Wen · Gengchen Mai · Sunyang Fu · Jiachen Li · Xuyu Wang · Ziran Wang · Jing Huang · Tianming Liu · Yong Chen · Lichao Sun · Lifang He
6 January 2026 at 13:00
arXiv:2601.01321v1 Announce Type: new Abstract: Digital twins, as precise digital representations of physical systems, have evolved from passive simulation tools into intelligent and autonomous entities through the integration of artificial intelligence technologies. This paper presents a unified four-stage framework that systematically characterizes AI integration across the digital twin lifecycle, spanning modeling, mirroring, intervention, and autonomous management. By synthesizing existing technologies and practices, we distill a unified four-stage framework that systematically characterizes how AI methodologies are embedded across the digital twin lifecycle: (1) modeling the physical twin through physics-based and physics-informed AI approaches, (2) mirroring the physical system into a digital twin with real-time synchronization, (3) intervening in the physical twin through predictive modeling, anomaly detection, and optimization strategies, and (4) achieving autonomous management through large language models, foundation models, and intelligent agents. We analyze the synergy between physics-based modeling and data-driven learning, highlighting the shift from traditional numerical solvers to physics-informed and foundation models for physical systems. Furthermore, we examine how generative AI technologies, including large language models and generative world models, transform digital twins into proactive and self-improving cognitive systems capable of reasoning, communication, and creative scenario generation. Through a cross-domain review spanning eleven application domains, including healthcare, aerospace, smart manufacturing, robotics, and smart cities, we identify common challenges related to scalability, explainability, and trustworthiness, and outline directions for responsible AI-driven digital twin systems.
Received — 4 December 2025 ⏭ Favourites

Scaling Multimodal Search and Recommendation with Small Language Models via Upside-Down Reinforcement Learning

✇cs.AI, q-bio.NC updates on arXiv.org
By: Yu-Chen Lin · Sanat Sharma · Hari Manikandan · Jayant Kumar · Tracy Holloway King · Jing Zheng
4 December 2025 at 13:00
arXiv:2502.09854v2 Announce Type: replace-cross Abstract: In this work, we investigate how small language models (SLMs) can be scaled to support multimodal search and recommendation use cases while remaining efficient enough for real-time, resource-constrained deployments. We present a framework that combines upside-down reinforcement learning with synthetic data distillation from a large language model (Llama-3) to train a 100M-parameter GPT-2 model for multitask prompt generation. Despite being up to 80 times smaller than state-of-the-art large language models (LLMs), our SLM achieves relevance and diversity scores within 6% of competitive baselines such as Llama-3 8B, Qwen3 8B, and Ministral 8B. These results demonstrate that SLMs can effectively handle multimodal search and recommendation tasks, while dramatically reducing inference latency and memory overhead. Our study highlights the potential of lightweight models as practical engines for scalable multimodal discovery, bridging the gap between cutting-edge research and real-world multimodal applications such as media recommendations and creative content generation.
Received — 21 November 2025 ⏭ Favourites

SMMILe enables accurate spatial quantification in digital pathology using multiple-instance learning

✇Nature Cancer
By: Zeyu Gao · Anyu Mao · Yuxing Dong · Hannah Clayton · Jialun Wu · Jiashuai Liu · ChunBao Wang · Kai He · Tieliang Gong · Chen Li · Mireia Crispin-Ortuzar
19 November 2025 at 08:00

Nature Cancer, Published online: 19 November 2025; doi:10.1038/s43018-025-01060-8

Gao et al. present SMMILe, a multiple-instance learning-based tool that leverages whole-slide images for accurate spatial quantification without compromising on classification performance, and show it outperforms state-of-the-art methods.
Received — 18 November 2025 ⏭ Favourites

SciAgent: A Unified Multi-Agent System for Generalistic Scientific Reasoning

✇cs.AI, q-bio.NC updates on arXiv.org
By: Xuchen Li · Ruitao Wu · Xuanbo Liu · Xukai Wang · Jinbo Hu · Zhixin Bai · Bohan Zeng · Hao Liang · Leheng Chen · Mingrui Chen · Haitian Zhong · Xuanlin Yang · Xu-Yao Zhang · Liu Liu · Jia Li · Kaiqi Huang · Jiahao Xu · Haitao Mi · Wentao Zhang · Bin Dong
18 November 2025 at 13:00
arXiv:2511.08151v2 Announce Type: replace Abstract: Recent advances in large language models have enabled AI systems to achieve expert-level performance on domain-specific scientific tasks, yet these systems remain narrow and handcrafted. We introduce SciAgent, a unified multi-agent system designed for generalistic scientific reasoning-the ability to adapt reasoning strategies across disciplines and difficulty levels. SciAgent organizes problem solving as a hierarchical process: a Coordinator Agent interprets each problem's domain and complexity, dynamically orchestrating specialized Worker Systems, each composed of interacting reasoning Sub-agents for symbolic deduction, conceptual modeling, numerical computation, and verification. These agents collaboratively assemble and refine reasoning pipelines tailored to each task. Across mathematics and physics Olympiads (IMO, IMC, IPhO, CPhO), SciAgent consistently attains or surpasses human gold-medalist performance, demonstrating both domain generality and reasoning adaptability. Additionally, SciAgent has been tested on the International Chemistry Olympiad (IChO) and selected problems from the Humanity's Last Exam (HLE) benchmark, further confirming the system's ability to generalize across diverse scientific domains. This work establishes SciAgent as a concrete step toward generalistic scientific intelligence-AI systems capable of coherent, cross-disciplinary reasoning at expert levels.
Received — 12 November 2025 ⏭ Favourites

SciAgent: A Unified Multi-Agent System for Generalistic Scientific Reasoning

✇cs.AI, q-bio.NC updates on arXiv.org
By: Xuchen Li · Ruitao Wu · Xuanbo Liu · Xukai Wang · Jinbo Hu · Zhixin Bai · Bohan Zeng · Hao Liang · Leheng Chen · Mingrui Chen · Haitian Zhong · Xuanlin Yang · Xu-Yao Zhang · Liu Liu · Jia Li · Kaiqi Huang · Jiahao Xu · Haitao Mi · Wentao Zhang · Bin Dong
12 November 2025 at 13:00
arXiv:2511.08151v1 Announce Type: new Abstract: Recent advances in large language models have enabled AI systems to achieve expert-level performance on domain-specific scientific tasks, yet these systems remain narrow and handcrafted. We introduce SciAgent, a unified multi-agent system designed for generalistic scientific reasoning-the ability to adapt reasoning strategies across disciplines and difficulty levels. SciAgent organizes problem solving as a hierarchical process: a Coordinator Agent interprets each problem's domain and complexity, dynamically orchestrating specialized Worker Systems, each composed of interacting reasoning Sub-agents for symbolic deduction, conceptual modeling, numerical computation, and verification. These agents collaboratively assemble and refine reasoning pipelines tailored to each task. Across mathematics and physics Olympiads (IMO, IMC, IPhO, CPhO), SciAgent consistently attains or surpasses human gold-medalist performance, demonstrating both domain generality and reasoning adaptability. Additionally, SciAgent has been tested on the International Chemistry Olympiad (IChO) and selected problems from the Humanity's Last Exam (HLE) benchmark, further confirming the system's ability to generalize across diverse scientific domains. This work establishes SciAgent as a concrete step toward generalistic scientific intelligence-AI systems capable of coherent, cross-disciplinary reasoning at expert levels.
Received — 11 November 2025 ⏭ Favourites

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

✇cs.AI, q-bio.NC updates on arXiv.org
By: Chao Zhang · Yuhao Wang · Derong Xu · Haoxin Zhang · Yuanjie Lyu · Yuhao Chen · Shuochen Liu · Tong Xu · Xiangyu Zhao · Yan Gao · Yao Hu · Enhong Chen
10 November 2025 at 13:00
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.
Received — 31 October 2025 ⏭ Favourites

Vital Insight: Assisting Experts' Context-Driven Sensemaking of Multi-modal Personal Tracking Data Using Visualization and Human-In-The-Loop LLM

✇cs.AI, q-bio.NC updates on arXiv.org
By: Jiachen Li · Xiwen Li · Justin Steinberg · Akshat Choube · Bingsheng Yao · Xuhai Xu · Dakuo Wang · Elizabeth Mynatt · Varun Mishra
31 October 2025 at 12:00
arXiv:2410.14879v4 Announce Type: replace-cross Abstract: Passive tracking methods, such as phone and wearable sensing, have become dominant in monitoring human behaviors in modern ubiquitous computing studies. While there have been significant advances in machine-learning approaches to translate periods of raw sensor data to model momentary behaviors, (e.g., physical activity recognition), there still remains a significant gap in the translation of these sensing streams into meaningful, high-level, context-aware insights that are required for various applications (e.g., summarizing an individual's daily routine). To bridge this gap, experts often need to employ a context-driven sensemaking process in real-world studies to derive insights. This process often requires manual effort and can be challenging even for experienced researchers due to the complexity of human behaviors. We conducted three rounds of user studies with 21 experts to explore solutions to address challenges with sensemaking. We follow a human-centered design process to identify needs and design, iterate, build, and evaluate Vital Insight (VI), a novel, LLM-assisted, prototype system to enable human-in-the-loop inference (sensemaking) and visualizations of multi-modal passive sensing data from smartphones and wearables. Using the prototype as a technology probe, we observe experts' interactions with it and develop an expert sensemaking model that explains how experts move between direct data representations and AI-supported inferences to explore, question, and validate insights. Through this iterative process, we also synthesize and discuss a list of design implications for the design of future AI-augmented visualization systems to better assist experts' sensemaking processes in multi-modal health sensing data.
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 — 8 February 2025 ⏭ Favourites

Cell-free epigenomes enhanced fragmentomics-based model for early detection of lung cancer

✇Omics In Lung
By: Yadong Wang · Qiang Guo · Zhicheng Huang · Liyang Song · Fei Zhao · Tiantian Gu · Zhe Feng · Haibo Wang · Bowen Li · Daoyun Wang · Bin Zhou · Chao Guo · Yuan Xu · Yang Song · Zhibo Zheng · Zhongxing Bing · Haochen Li · Xiaoqing Yu · Ka Luk Fung · Heqing Xu · Jianhong Shi · Meng Chen · Shuai Hong · Haoxuan Jin · Shiyuan Tong · Sibo Zhu · Chen Zhu · Jinlei Song · Jing Liu · Shanqing Li · Hefei Li · Xueguang Sun · Naixin Liang
5 February 2025 at 19:00

Clin Transl Med. 2025 Feb;15(2):e70225. doi: 10.1002/ctm2.70225.

ABSTRACT

BACKGROUND: Lung cancer is a leading cause of cancer mortality, highlighting the need for innovative non-invasive early detection methods. Although cell-free DNA (cfDNA) analysis shows promise, its sensitivity in early-stage lung cancer patients remains a challenge. This study aimed to integrate insights from epigenetic modifications and fragmentomic features of cfDNA using machine learning to develop a more accurate lung cancer detection model.

METHODS: To address this issue, a multi-centre prospective cohort study was conducted, with participants harbouring suspicious malignant lung nodules and healthy volunteers recruited from two clinical centres. Plasma cfDNA was analysed for its epigenetic and fragmentomic profiles using chromatin immunoprecipitation sequencing, reduced representation bisulphite sequencing and low-pass whole-genome sequencing. Machine learning algorithms were then employed to integrate the multi-omics data, aiding in the development of a precise lung cancer detection model.

RESULTS: Cancer-related changes in cfDNA fragmentomics were significantly enriched in specific genes marked by cell-free epigenomes. A total of 609 genes were identified, and the corresponding cfDNA fragmentomic features were utilised to construct the ensemble model. This model achieved a sensitivity of 90.4% and a specificity of 83.1%, with an AUC of 0.94 in the independent validation set. Notably, the model demonstrated exceptional sensitivity for stage I lung cancer cases, achieving 95.1%. It also showed remarkable performance in detecting minimally invasive adenocarcinoma, with a sensitivity of 96.2%, highlighting its potential for early detection in clinical settings.

CONCLUSIONS: With feature selection guided by multiple epigenetic sequencing approaches, the cfDNA fragmentomics-based machine learning model demonstrated outstanding performance in the independent validation cohort. These findings highlight its potential as an effective non-invasive strategy for the early detection of lung cancer.

KEYPOINTS: Our study elucidated the regulatory relationships between epigenetic modifications and their effects on fragmentomic features. Identifying epigenetically regulated genes provided a critical foundation for developing the cfDNA fragmentomics-based machine learning model. The model demonstrated exceptional clinical performance, highlighting its substantial potential for translational application in clinical practice.

PMID:39909829 | PMC:PMC11798665 | DOI:10.1002/ctm2.70225

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