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.

Leaked documents reveal how much OpenAI paid Microsoft under a revenue-share agreement. They also indicate inference costs.

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.

Nature Medicine, Published online: 14 November 2025; doi:10.1038/s41591-025-04052-4

A new study reveals that as patients approach the end stages of their disease, cancer may exploit the body’s largest highways — infiltrating major blood vessels and unleashing clusters of tumor cells into the circulation.

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:2511.09378v1 Announce Type: new Abstract: The capacity of Large Language Models (LLMs) for reasoning remains an active area of research, with the capabilities of frontier models continually advancing. We provide an updated evaluation of the end-to-end planning performance of three frontier LLMs as of 2025, where models are prompted to generate a plan from PDDL domain and task descriptions. We evaluate DeepSeek R1, Gemini 2.5 Pro, GPT-5 and as reference the planner LAMA on a subset of domains from the most recent Learning Track of the International Planning Competition. Our results show that on standard PDDL domains, the performance of GPT-5 in terms of solved tasks is competitive with LAMA. When the PDDL domains and tasks are obfuscated to test for pure reasoning, the performance of all LLMs degrades, though less severely than previously reported for other models. These results show substantial improvements over prior generations of LLMs, reducing the performance gap to planners on a challenging benchmark.

arXiv:2511.08609v1 Announce Type: cross Abstract: The energy transition is a key theme of the last decades to determine a future of eco-sustainability, and an area of such importance cannot disregard digitization, innovation and the new technological tools available. This is the context in which the Generative Artificial Intelligence models described in this paper are positioned, developed by Engineering Ingegneria Informatica SpA in order to automate the plant structures acquisition of SNAM energy infrastructure, a leading gas transportation company in Italy and Europe. The digitization of a gas plant consists in registering all its relevant information through the interpretation of the related documentation. The aim of this work is therefore to design an effective solution based on Artificial Intelligence techniques to automate the extraction of the information necessary for the digitization of a plant, in order to streamline the daily work of MGM users. The solution received the P&ID of the plant as input, each one in pdf format, and uses OCR, Vision LLM, Object Detection, Relational Reasoning and optimization algorithms to return an output consisting of two sets of information: a structured overview of the relevant design data and the hierarchical framework of the plant. To achieve convincing results, we extend a state-of-the-art model for Scene Graph Generation introducing a brand new Transformer architecture with the aim of deepening the analysis of the complex relations between the plant's components. The synergistic use of the listed AI-based technologies allowed to overcome many obstacles arising from the high variety of data, due to the lack of standardization. An accuracy of 91\% has been achieved in the extraction of textual information relating to design data. Regarding the plants topology, 93\% of components are correctly identified and the hierarchical structure is extracted with an accuracy around 80\%.

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:2510.00229v4 Announce Type: replace Abstract: The deployment of Large Language Models (LLMs) as agentic orchestrators has revolutionized task automation, but the need for privacy-preserving, cost-effective solutions demands on-device inference capabilities. However, local LLMs consistently underperform compared to frontier models in tool calling scenarios, struggling with both tool selection from large tool sets and accurate argument generation for complex parameter structures. We introduce a methodology that disaggregates a tool-calling task into two distinct subtasks: tool selection and argument generation. We propose "decoupled fine-tuning", a novel post-training approach that employs LoRA fine-tuning to create dedicated LoRA adapters for tool selection and tool-specific argument generation using separate loss masking for each of the subtasks. Furthermore, we present AgentFlux, an inference framework that leverages the LoRA adapters created using decoupled fine-tuning to perform efficient agent orchestration with the help of local models on end-user devices. AgentFlux decomposes the tool-call generation step into tool selection and argument generation, and dynamically loads the corresponding LoRA adapters to generate tool calls. Additionally, AgentFlux implements hierarchical orchestration to restrict the number of tools required for tool selection. Our experiments on the MCP-Bench benchmark demonstrate that the Qwen-2.5-7B model trained using decoupled fine-tuning improves the tool calling accuracy of the base model by 46%, and outperforms other local reasoning, non-reasoning and fine-tuned models of similar size in all cases, and models that are 2x larger, in most cases.

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

Last week, we hosted EmTech MIT, MIT Technology Review’s annual flagship conference in Cambridge, Massachusetts. Over the course of three days of main-stage sessions, I learned about innovations in AI, biotech, and robotics. 

But as you might imagine, some of this climate reporter’s favorite moments came in the climate sessions. I was listening especially closely to my colleague James Temple’s discussion with Lucia Tian, head of advanced energy technologies at Google. 

They spoke about the tech giant’s growing energy demand and what sort of technologies the company is looking to to help meet it. In case you weren’t able to join us, let’s dig into that session and consider how the company is thinking about energy in the face of AI’s rapid rise. 

I’ve been closely following Google’s work in energy this year. Like the rest of the tech industry, the company is seeing ballooning electricity demand in its data centers. That could get in the way of a major goal that Google has been talking about for years. 

See, back in 2020, the company announced an ambitious target: by 2030, it aimed to run on carbon-free energy 24-7. Basically, that means Google would purchase enough renewable energy on the grids where it operates to meet its entire electricity demand, and the purchases would match up so the electricity would have to be generated when the company was actually using energy. (For more on the nuances of Big Tech’s renewable-energy pledges, check out James’s piece from last year.)

Google’s is an ambitious goal, and on stage, Tian said that the company is still aiming for it but acknowledged that it’s looking tough with the rise of AI. 

“It was always a moonshot,” she said. “It’s something very, very hard to achieve, and it’s only harder in the face of this growth. But our perspective is, if we don’t move in that direction, we’ll never get there.”

Google’s total electricity demand more than doubled from 2020 to 2024, according to its latest Environmental Report. As for that goal of 24-7 carbon-free energy? The company is basically treading water. While it was at 67% for its data centers in 2020, last year it came in at 66%. 

Not going backwards is something of an accomplishment, given the rapid growth in electricity demand. But it still leaves the company some distance away from its finish line.

To close the gap, Google has been signing what feels like constant deals in the energy space. Two recent announcements that Tian talked about on stage were a project involving carbon capture and storage at a natural-gas plant in Illinois and plans to reopen a shuttered nuclear power plant in Iowa. 

Let’s start with carbon capture. Google signed an agreement to purchase most of the electricity from a new natural-gas plant, which will capture and store about 90% of its carbon dioxide emissions. 

That announcement was controversial, with critics arguing that carbon capture keeps fossil-fuel infrastructure online longer and still releases greenhouse gases and other pollutants into the atmosphere. 

One question that James raised on stage: Why build a new natural-gas plant rather than add equipment to an already existing facility? Tacking on equipment to an operational plant would mean cutting emissions from the status quo, rather than adding entirely new fossil-fuel infrastructure. 

The company did consider many existing plants, Tian said. But, as she put it, “Retrofits aren’t going to make sense everywhere.” Space can be limited at existing plants, for example, and many may not have the right geology to store carbon dioxide underground. 

“We wanted to lead with a project that could prove this technology at scale,” Tian said. This site has an operational Class VI well, the type used for permanent sequestration, she added, and it also doesn’t require a big pipeline buildout. 

Tian also touched on the company’s recent announcement that it’s collaborating with NextEra Energy to reopen Duane Arnold Energy Center, a nuclear power plant in Iowa. The company will purchase electricity from that plant, which is scheduled to reopen in 2029. 

As I covered in a story earlier this year, Duane Arnold was basically the final option in the US for companies looking to reopen shuttered nuclear power plants. “Just a few years back, we were still closing down nuclear plants in this country,” Tian said on stage. 

While each reopening will look a little different, Tian highlighted the groups working to restart the Palisades plant in Michigan, which was the first reopening to be announced, last spring. “They’re the real heroes of the story,” she said.

I’m always interested to get a peek behind the curtain at how Big Tech is thinking about energy. I’m skeptical but certainly interested to see how Google’s, and the rest of the industry’s, goals shape up over the next few years. 

This article is from The Spark, MIT Technology Review’s weekly climate newsletter. To receive it in your inbox every Wednesday, sign up here.