arXiv:2511.10788v1 Announce Type: new Abstract: Recent advances in large language models (LLMs) have made reasoning a central benchmark for evaluating intelligence. While prior surveys focus on efficiency by examining how to shorten reasoning chains or reduce computation, this view overlooks a fundamental challenge: current LLMs apply uniform reasoning strategies regardless of task complexity, generating long traces for trivial problems while failing to extend reasoning for difficult tasks. This survey reframes reasoning through the lens of {adaptivity}: the capability to allocate reasoning effort based on input characteristics such as difficulty and uncertainty. We make three contributions. First, we formalize deductive, inductive, and abductive reasoning within the LLM context, connecting these classical cognitive paradigms with their algorithmic realizations. Second, we formalize adaptive reasoning as a control-augmented policy optimization problem balancing task performance with computational cost, distinguishing learned policies from inference-time control mechanisms. Third, we propose a systematic taxonomy organizing existing methods into training-based approaches that internalize adaptivity through reinforcement learning, supervised fine-tuning, and learned controllers, and training-free approaches that achieve adaptivity through prompt conditioning, feedback-driven halting, and modular composition. This framework clarifies how different mechanisms realize adaptive reasoning in practice and enables systematic comparison across diverse strategies. We conclude by identifying open challenges in self-evaluation, meta-reasoning, and human-aligned reasoning control.

Background: Digital lifestyle interventions hold promise in supporting healthy gestational weight gain (GWG) during pregnancy. However, clarity on their key design and implementation features remains limited. The prevalence of excessive GWG and its associated maternal and infant health risks makes understanding the landscape of digital intervention characteristics critical. Objective: This scoping review aimed to map current literature on digital lifestyle interventions designed to promote healthy GWG and to identify intervention characteristics, including behavior change techniques (BCTs), employed across these interventions, with particular attention to patterns in design and implementation features across studies reporting positive outcomes. Methods: Following PRISMA-ScR guidelines, we systematically searched PubMed, Embase, Cochrane, and Web of Science for peer-reviewed studies published between 2014 and 2024. Studies were included if they described interventions with at least one digital component targeting GWG. Studies on high-risk pregnancies, non-human subjects, protocols without results, abstracts, gray literature, and non-English publications were excluded. Data extraction covered study characteristics, theoretical frameworks, timing, duration, frequency, delivery modes, and BCTs applied. The landscape of intervention characteristics was mapped, including descriptive analysis of features that appeared across different study outcomes. Results: A total of 44 studies met inclusion criteria: 23 primary data articles (pilot studies, randomized controlled trials, etc) and 21 secondary data articles (meta-analyses, systematic reviews, etc). Primary studies showed that interventions were more likely to achieve intended outcomes when they started earlier, lasted longer and combined digital and in-person components. Five BCTs were commonly present across interventions achieving positive outcomes: Goal setting (outcome) (71%), Discrepancy between current behavior and goal (43%), Self-monitoring of behavior (86%), Social support (unspecified) (71%), and Credible source (71%). Secondary studies supported these findings, identifying several helpful features: starting before mid-pregnancy, long duration with high intensity, in-person contact, and BCTs related to goal setting, action planning, feedback on and monitoring of behavior. However, primary studies showed gaps in reporting practices, with many details lacking about design and implementation features, such as BCTs. This converged with secondary studies reporting insufficient detail in reviewed primary literature, limiting interpretation and replication potential. Conclusions: This scoping review maps digital interventions for GWG and identifies key patterns in intervention design and implementation. Evidence suggests that interventions may be more promising when combining digital delivery with in-person components and incorporating BCTs related to goal setting, self-monitoring, and social support. This review provides comprehensive mapping of BCT usage and other intervention features highlighting approaches associated with positive outcomes. However, significant gaps in reporting practices limit evidence synthesis. The findings can inform design of digital interventions for managing GWG by identifying potentially successful design and implementation features. Future research should prioritize standardized reporting practices and evaluate interventions in underserved populations, including healthcare desert communities, to enhance the evidence base.

arXiv:2511.09247v1 Announce Type: new Abstract: Clinical time series derived from electronic health records (EHRs) are inherently irregular, with asynchronous sampling, missing values, and heterogeneous feature dynamics. While numerical laboratory measurements are highly informative, existing embedding strategies usually combine feature identity and value embeddings through additive operations, which constrains their ability to capture value-dependent feature interactions. We propose MedFuse, a framework for irregular clinical time series centered on the MuFuse (Multiplicative Embedding Fusion) module. MuFuse fuses value and feature embeddings through multiplicative modulation, preserving feature-specific information while modeling higher-order dependencies across features. Experiments on three real-world datasets covering both intensive and chronic care show that MedFuse consistently outperforms state-of-the-art baselines on key predictive tasks. Analysis of the learned representations further demonstrates that multiplicative fusion enhances expressiveness and supports cross-dataset pretraining. These results establish MedFuse as a generalizable approach for modeling irregular clinical time series.

arXiv:2511.08637v1 Announce Type: cross Abstract: The internet has become the main source of data to train modern text-to-image or vision-language models, yet it is increasingly unclear whether web-scale data collection practices for training AI systems adequately respect data owners' wishes. Ignoring the owner's indication of consent around data usage not only raises ethical concerns but also has recently been elevated into lawsuits around copyright infringement cases. In this work, we aim to reveal information about data owners' consent to AI scraping and training, and study how it's expressed in DataComp, a popular dataset of 12.8 billion text-image pairs. We examine both the sample-level information, including the copyright notice, watermarking, and metadata, and the web-domain-level information, such as a site's Terms of Service (ToS) and Robots Exclusion Protocol. We estimate at least 122M of samples exhibit some indication of copyright notice in CommonPool, and find that 60\% of the samples in the top 50 domains come from websites with ToS that prohibit scraping. Furthermore, we estimate 9-13\% with 95\% confidence interval of samples from CommonPool to contain watermarks, where existing watermark detection methods fail to capture them in high fidelity. Our holistic methods and findings show that data owners rely on various channels to convey data consent, of which current AI data collection pipelines do not entirely respect. These findings highlight the limitations of the current dataset curation/release practice and the need for a unified data consent framework taking AI purposes into consideration.

arXiv:2511.08721v1 Announce Type: cross Abstract: In behavioral sciences, experiments such as the ultimatum game are conducted to assess preferences for fairness or self-interest of study participants. In the dictator game, a simplified version of the ultimatum game where only one of two players makes a single decision, the dictator unilaterally decides how to split a fixed sum of money between themselves and the other player. Although recent studies have explored behavioral patterns of AI agents based on Large Language Models (LLMs) instructed to adopt different personas, we question the robustness of these results. In particular, many of these studies overlook the role of the system prompt - the underlying instructions that shape the model's behavior - and do not account for how sensitive results can be to slight changes in prompts. However, a robust baseline is essential when studying highly complex behavioral aspects of LLMs. To overcome previous limitations, we propose the LLM agent behavior study (LLM-ABS) framework to (i) explore how different system prompts influence model behavior, (ii) get more reliable insights into agent preferences by using neutral prompt variations, and (iii) analyze linguistic features in responses to open-ended instructions by LLM agents to better understand the reasoning behind their behavior. We found that agents often exhibit a strong preference for fairness, as well as a significant impact of the system prompt on their behavior. From a linguistic perspective, we identify that models express their responses differently. Although prompt sensitivity remains a persistent challenge, our proposed framework demonstrates a robust foundation for LLM agent behavior studies. Our code artifacts are available at https://github.com/andreaseinwiller/LLM-ABS.

arXiv:2511.09294v1 Announce Type: cross Abstract: Federated learning (FL) enables privacy-preserving collaborative model training but remains vulnerable to adversarial behaviors that compromise model utility or fairness across sensitive groups. While extensive studies have examined attacks targeting either objective, strategies that simultaneously degrade both utility and fairness remain largely unexplored. To bridge this gap, we introduce the Dual-Facet Attack (DFA), a novel threat model that concurrently undermines predictive accuracy and group fairness. Two variants, Synchronous DFA (S-DFA) and Split DFA (Sp-DFA), are further proposed to capture distinct real-world collusion scenarios. Experimental results show that existing robust FL defenses, including hybrid aggregation schemes, fail to resist DFAs effectively. To counter these threats, we propose GuardFed, a self-adaptive defense framework that maintains a fairness-aware reference model using a small amount of clean server data augmented with synthetic samples. In each training round, GuardFed computes a dual-perspective trust score for every client by jointly evaluating its utility deviation and fairness degradation, thereby enabling selective aggregation of trustworthy updates. Extensive experiments on real-world datasets demonstrate that GuardFed consistently preserves both accuracy and fairness under diverse non-IID and adversarial conditions, achieving state-of-the-art performance compared with existing robust FL methods.

arXiv:2510.10675v2 Announce Type: replace Abstract: Generative Agentic AI systems are emerging as a powerful paradigm for automating complex, multi-step tasks. However, many existing frameworks for building these systems introduce significant complexity, a steep learning curve, and substantial boilerplate code, hindering rapid prototyping and deployment. This paper introduces simpliflow, a lightweight, open-source Python framework designed to address these challenges. simpliflow enables the rapid development and orchestration of linear, deterministic agentic workflows through a declarative, JSON-based configuration. Its modular architecture decouples agent management, workflow execution, and post-processing, promoting ease of use and extensibility. By integrating with LiteLLM, it supports over 100 Large Language Models (LLMs) out-of-the-box. We present the architecture, operational flow, and core features of simpliflow, demonstrating its utility through diverse use cases ranging from software development simulation to real-time system interaction. A comparative analysis with prominent frameworks like LangChain and AutoGen highlights simpliflow's unique position as a tool optimized for simplicity, control, and speed in deterministic workflow environments.

arXiv:2410.15281v4 Announce Type: replace-cross Abstract: With the broader adoption and highly successful development of Large Language Models (LLMs), there has been growing interest and demand for applying LLMs to autonomous driving technology. Driven by their natural language understanding and reasoning capabilities, LLMs have the potential to enhance various aspects of autonomous driving systems, from perception and scene understanding to interactive decision-making. In this paper, we first introduce the novel concept of designing Large Language Models for Autonomous Driving (LLM4AD), followed by a review of existing LLM4AD studies. Then, we propose a comprehensive benchmark for evaluating the instruction-following and reasoning abilities of LLM4AD systems, which includes LaMPilot-Bench, CARLA Leaderboard 1.0 Benchmark in simulation and NuPlanQA for multi-view visual question answering. Furthermore, we conduct extensive real-world experiments on autonomous vehicle platforms, examining both on-cloud and on-edge LLM deployment for personalized decision-making and motion control. Next, we explore the future trends of integrating language diffusion models into autonomous driving, exemplified by the proposed ViLaD (Vision-Language Diffusion) framework. Finally, we discuss the main challenges of LLM4AD, including latency, deployment, security and privacy, safety, trust and transparency, and personalization.

arXiv:2410.21348v3 Announce Type: replace-cross Abstract: With the increasing application of large language models (LLMs) in the medical domain, evaluating these models' performance using benchmark datasets has become crucial. This paper presents a comprehensive survey of various benchmark datasets employed in medical LLM tasks. These datasets span multiple modalities including text, image, and multimodal benchmarks, focusing on different aspects of medical knowledge such as electronic health records (EHRs), doctor-patient dialogues, medical question-answering, and medical image captioning. The survey categorizes the datasets by modality, discussing their significance, data structure, and impact on the development of LLMs for clinical tasks such as diagnosis, report generation, and predictive decision support. Key benchmarks include MIMIC-III, MIMIC-IV, BioASQ, PubMedQA, and CheXpert, which have facilitated advancements in tasks like medical report generation, clinical summarization, and synthetic data generation. The paper summarizes the challenges and opportunities in leveraging these benchmarks for advancing multimodal medical intelligence, emphasizing the need for datasets with a greater degree of language diversity, structured omics data, and innovative approaches to synthesis. This work also provides a foundation for future research in the application of LLMs in medicine, contributing to the evolving field of medical artificial intelligence.

arXiv:2508.01159v2 Announce Type: replace-cross Abstract: This study evaluates the capacity of large language models (LLMs) to generate structured clinical consultation templates for electronic consultation. Using 145 expert-crafted templates developed and routinely used by Stanford's eConsult team, we assess frontier models -- including o3, GPT-4o, Kimi K2, Claude 4 Sonnet, Llama 3 70B, and Gemini 2.5 Pro -- for their ability to produce clinically coherent, concise, and prioritized clinical question schemas. Through a multi-agent pipeline combining prompt optimization, semantic autograding, and prioritization analysis, we show that while models like o3 achieve high comprehensiveness (up to 92.2\%), they consistently generate excessively long templates and fail to correctly prioritize the most clinically important questions under length constraints. Performance varies across specialties, with significant degradation in narrative-driven fields such as psychiatry and pain medicine. Our findings demonstrate that LLMs can enhance structured clinical information exchange between physicians, while highlighting the need for more robust evaluation methods that capture a model's ability to prioritize clinically salient information within the time constraints of real-world physician communication.

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.

Background: In recent years, large language models (LLMs) have experienced rapid development. LLM-based virtual patients have begun to gain attention, offering new opportunities for simulations in medical education. Objective: This study aims to systematically analyze the current applications, research trends, and challenges of LLM-based virtual patients in medical education and to explore potential future directions for development. Methods: This study adheres to the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) guidelines. Five databases (Web of Science Core Collection, PubMed, IEEE Xplore, Embase, and Scopus) were searched from January 1, 2018, to June 24, 2025, to identify studies related to the application of LLM-based virtual patients in medical education. A comprehensive analysis of LLM-based virtual patients from research design to application and evaluation was conducted. Results: A total of 28 studies were included in this scoping review. Analysis revealed that 92.9% (26/28) of the studies were published in the past 2 years, indicating that LLM-based virtual patient research is still in its early stages. The research primarily focuses on medical training and spans a wide range of medical disciplines. When using LLMs, advanced technologies such as social robots, virtual reality, and mixed reality are used to present LLM-based virtual patients. Combining these technologies with various supplementary tools enhances the realism of LLM-based virtual patients and improves user interaction. The evaluation of LLM-based virtual patients mainly emphasizes user experience. However, evaluation methods lack standardization, and only 13% (3/23) of studies used validated tools in assessing LLM-based virtual patients, while only 21.7% (5/23) of studies objectively measured learning outcomes facilitated by LLM-based virtual patients. All included studies expressed a positive attitude toward LLM-based virtual patients; however, they overlook privacy and security considerations in practical applications. Conclusions: LLM-based virtual patients hold significant innovation potential in medical education and are still in the early stages of development. They are primarily applied in medical training and show promise in communication skills training, although they cannot replace real-world interactions. Moreover, the heterogeneity of research designs, the absence of nonverbal cues in interactions, and concerns regarding privacy and security limit their broader implementation. Future research should focus on improving the reliability, realism, safety, and scientific efficacy of LLM-based virtual patients. Trial Registration: Open Science Framework Registries 10.17605/OSF.IO/DMC9Q; https://osf.io/DMC9Q/overview

npj Digital Medicine, Published online: 12 November 2025; doi:10.1038/s41746-025-02013-2

Equipping mathematical models for hospital dynamics using information theory

Nature, Published online: 12 November 2025; doi:10.1038/d41586-025-03681-6

The milestone makes machine-learning trailblazer Yoshua Bengio the most cited researcher on Google Scholar.

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.

arXiv:2511.07998v1 Announce Type: cross Abstract: Structured data question answering (QA), including table QA, Knowledge Graph (KG) QA, and temporal KG QA, is a pivotal research area. Advances in large language models (LLMs) have driven significant progress in unified structural QA frameworks like TrustUQA. However, these frameworks face challenges when applied to small-scale LLMs since small-scale LLMs are prone to errors in generating structured queries. To improve the structured data QA ability of small-scale LLMs, we propose a self-correction distillation (SCD) method. In SCD, an error prompt mechanism (EPM) is designed to detect errors and provide customized error messages during inference, and a two-stage distillation strategy is designed to transfer large-scale LLMs' query-generation and error-correction capabilities to small-scale LLM. Experiments across 5 benchmarks with 3 structured data types demonstrate that our SCD achieves the best performance and superior generalization on small-scale LLM (8B) compared to other distillation methods, and closely approaches the performance of GPT4 on some datasets. Furthermore, large-scale LLMs equipped with EPM surpass the state-of-the-art results on most datasets.

arXiv:2411.18212v3 Announce Type: replace-cross Abstract: Path planning under wireless performance constraints is a complex challenge in robot navigation. However, naively incorporating such constraints into classical planning algorithms often incurs prohibitive search costs. In this paper, we propose SCoTT, a wireless-aware path planning framework that leverages vision-language models (VLMs) to co-optimize average path gains and trajectory length using wireless heatmap images and ray-tracing data from a digital twin (DT). At the core of our framework is Strategic Chain-of-Thought Tasking (SCoTT), a novel prompting paradigm that decomposes the exhaustive search problem into structured subtasks, each solved via chain-of-thought prompting. To establish strong baselines, we compare classical A* and wireless-aware extensions of it, and derive DP-WA*, an optimal, iterative dynamic programming algorithm that incorporates all path gains and distance metrics from the DT, but at significant computational cost. In extensive experiments, we show that SCoTT achieves path gains within 2% of DP-WA* while consistently generating shorter trajectories. Moreover, SCoTT's intermediate outputs can be used to accelerate DP-WA* by reducing its search space, saving up to 62% in execution time. We validate our framework using four VLMs, demonstrating effectiveness across both large and small models, thus making it applicable to a wide range of compact models at low inference cost. We also show the practical viability of our approach by deploying SCoTT as a ROS node within Gazebo simulations. Finally, we discuss data acquisition pipelines, compute requirements, and deployment considerations for VLMs in 6G-enabled DTs, underscoring the potential of natural language interfaces for wireless-aware navigation in real-world applications.

Two experienced investors share their tips for founders and operators hoping to nail product-market fit at their AI startups.

Background: Social determinants of health (SDOH) strongly influence clinical outcomes. Social needs are the individual-level, actionable facets of the broader SDOH framework, including food security, stable housing, and access to essential services. When these needs go unmet, they adversely affect wellbeing and quality of care. Systematically detecting social needs is therefore critical, and emerging digital tools now offer efficient, scalable approaches for screening and identification. Objective: This scoping review aims to examine digital health technology (DHT) use or interventions documented for screening and identifying unmet social needs within high-need populations. We explore trends, effects, challenges, and limitations of identified technologies. Methods: Following PRISMA-ScR guidelines, we searched databases including MEDLINE, Embase, Scopus, ACM Digital Library, and Web of Science for studies published from 2010 to 2025. Eligible studies used technology to screen for and identify unmet social needs in populations with health and socioeconomic challenges. Data extraction focused on the types of technology, screening processes, and social needs identified. Results: Our findings highlight a limited yet evolving landscape of technological applications. We identified 14 studies using tools like self-assessment surveys, tablet-based systems, and electronic portals. These tools were applied across diverse groups, such as refugees and patients in emergency departments. Innovative approaches, such as chatbots and multi-dimensional risk appraisal systems for older adults, showed potential. However, challenges included single-site studies, small samples, and integration issues with medical records. The effectiveness of these tools in screening for unmet social needs shows mixed outcomes. Conclusions: DHTs play a pivotal role in improving the identification of unmet social needs. The findings underscore the need for broader, more integrated research to fully understand the impact of technology-based assessments and screening processes for social needs. Future efforts should focus on facilitated screening using technology both within and outside of the visit, ensuring the linkage to appropriate resources and care.