arXiv:2610.26913v1 Announce Type: new
Abstract: The adoption of Large Language Models for radiology report structuring has been largely dominated by either proprietary cloud-based models or large open models requiring high-end GPUs for deployment, which is a critical bottleneck for clinical adoption in radiology workflows that demand data privacy and offline operation. To address this, we present MedPAO-Assist, an edge-deployable agentic framework that generates structured radiology reports directly from radiologist dictation and voice commands, requiring only $\approx3.3$ GB peak RAM and achieving an average end-to-end latency of $\approx31$ seconds on a standard laptop CPU through an asynchronous, multi-threaded execution pipeline. The system currently supports four major imaging modalities -- Chest X-ray, Chest CT, Abdomen CT, and Brain MRI. To our knowledge, it is among the earliest agentic systems to run its entire pipeline with a Small Language Model (SLM) in the 0.6B-parameter range. This multi-agent architecture, built around an Extract-Ground-Generate paradigm, performs concept extraction, SNOMED-CT grounding, and structured report generation, followed by a speech-driven human-in-the-loop correction phase, together forming a fully "no-touch" reporting workflow that requires no keyboard input, external API calls, or internet connectivity. We evaluate each pipeline stage individually -- concept extraction, ontology grounding, and concept categorization and report hardware profiling results demonstrating the system's feasibility for real-time, CPU-only clinical deployment.
Shrish Shrinath Vaidya, Minmini Selvam, Ganapathy Krishnamurthi
arXiv:2610.26904v1 Announce Type: new
Abstract: Recent studies have proposed reinforcement learning with verifiable rewards (RLVR) methods that enable LLMs to generate high-quality RTL circuits from natural-language specifications. Existing approaches optimize circuit PPA (Power, Performance, Area) by aggregating multiple objectives into a single scalar reward, making it difficult to simultaneously generate diverse Pareto-optimal solutions across different trade-offs such as low power, low latency, and small area. However, in practical design, the relative importance of each objective varies depending on product requirements and design constraints; thus, obtaining a diverse and high-quality candidate set is beneficial in that designers can choose a preferred trade-off a posteriori. In this work, we are the first to propose a learning method for LLM-based circuit generation that optimizes, not the quality of a single circuit, but the quality and diversity of the entire circuit set obtained through multiple generations in the PPA objective space. The proposed method consists of (1) a generation-based training pipeline that reformulates coverage improvement of the entire Pareto solution set into a sequential circuit generation problem, and (2) a reward function based on Hypervolume Contribution (HVC) that measures how much a generated circuit contributes to the Pareto front. Evaluation on the RTLLM v2 benchmark shows that the proposed method achieves +13.3 percentage points in relative Hypervolume over a baseline without PPA optimization and +14.4 percentage points over a single-objective reinforcement learning method, while also demonstrating superiority in circuit diversity.
Koki Takeshita, Kenji Uebayashi, Hikaru Tomonari, Masaya Tsunokake, Koichiro Yawata, Tatsuya Sasaki, Yusuke Ohtsubo, Kota Dohi, Yasuhiro Sogawa
arXiv:2610.26899v1 Announce Type: new
Abstract: Due to the rapid growth of the global population, traditional construction methods are gradually unable to meet the current housing demand. The advancement of machine learning algorithms has encouraged researchers to explore their applications in the construction industry, leading to more intelligent and efficient building processes. In particular, the rise of large language models in recent years has provided more possibilities for the transformation from traditional construction to smart construction. In this study, a large language model and reinforcement learning based autonomous construction method is proposed. An enhanced soft actor-critic reinforcement learning algorithm is developed to plan actions for a mobile crane according to construction tasks. Robot kinematics and control algorithms are used to ensure that the actions generated by the reinforcement learning algorithm can be executed by the crane. In addition, a customized embedding model is developed to extract information from the construction environment according to user interests. Then, a large language model, ChatGPT 5, is used to update construction progress, provide safety information to control system, and generate construction progress reports. The feasibility of proposed method is verified through several full-scall retaining wall construction experiments.
Yifei Xiao, Huasheng Lin, T. Y. Yang
arXiv:2610.26887v1 Announce Type: new
Abstract: Large language model (LLM) agents are evolving from conversational assistants into Cowork Agents capable of autonomous planning, tool use, and complex task execution. Financial analysis requires these agents to integrate cross-document evidence and perform multistep numerical reasoning, but expert task authoring is costly, while direct LLM synthesis struggles to produce challenging tasks with reliable answers. We introduce Navalia, a framework for Cowork Agents that combines verifiable task synthesis with long-horizon post-training. Using corporate financial reports as its data source, Navalia semantically selects supporting evidence from complete fact sets and constructs executable computation chains to generate analytical tasks with traceable evidence and actual data dependencies between steps. We further use independent LLM review and programmatic checks to verify evidence consistency and answer correctness. The verified tasks are then used for trajectory collection, cold-start supervised fine-tuning (SFT), and reinforcement learning (RL) to improve long-horizon task execution. Navalia, initialized from Qwen3.6-35B-A3B, achieves consistent gains over the base model across all five benchmarks: OfficeQA Pro, FinSearchComp, Finance Agent Benchmark, APEX-Agents-AA, and Workspace-Bench-Lite. These results demonstrate that Navalia improves evidence integration, tool use, and long-horizon task execution capabilities and generalizes to broader Cowork settings, including general office tasks.
Hengqi Liu, Ziyuan Liu, Yang Qin, Wanting Zhou, Zichuan Wang, Jiachen Liang, Xu Chu, Shaowei Chen, Zhaokai Luo, Mu Chuan
Teléfonos como el iPhone Duo o el Galaxy Z Fold8 prometen una pantalla como la de una tablet sin renunciar a llevar el teléfono en el bolsillo. Analizamos qué hay que sacrificar a cambio
Amazon Web Services logged attempts to leverage the internet-melting PHP2Shell bugs four days ago. They’re now being “broadly exploited” across the internet.
Uber is rolling out ChatGPT Work to more than 30,000 employees, helping teams research, analyze data, create presentations, and complete complex workflows.
Google tiene algunas prácticas cuestionables para espiar a sus usuarios, aunque la última de Chrome podría molestar a más de uno. La tecnológica anunció una función de su navegador que vigila el texto que copias en el portapapeles para detectar amenazas. Esta medida está diseñada para combatir las estafas y se aplicará únicamente cuando se […]
Seguir leyendo: Si usas Chrome, Google empezará a vigilar todo el texto que copias en tu equipo
Meta’s board feared that its CEO’s departure could disrupt the company’s AI ambitions. A new stock agreement gives him financial incentives to stay put.
Some hosts are threatening to strike, while others are plotting ways around Airbnb’s new restrictions. Guests, meanwhile, are celebrating.
A un día de anunciar la llegada de la Inteligencia Personalizada a Android Auto, Google vuelve a la carga. El gigante tecnológico confirmó que la integración de Gemini en Google Maps ya está disponible para Apple CarPlay. Esta función transformará la forma en la que interactuamos con la aplicación, sustituyendo los comandos tradicionales por una […]
Seguir leyendo: Olvídate de Android Auto: la IA de Gemini llega a CarPlay para que hables con tu coche
Los resultados de las pruebas confirmaron su diagnóstico de adenocarcinoma de pulmón localizado.
Los resultados de las pruebas confirmaron su diagnóstico de adenocarcinoma de pulmón localizado.
Los resultados de las pruebas confirmaron su diagnóstico de adenocarcinoma de pulmón localizado.
Los resultados de las pruebas confirmaron su diagnóstico de adenocarcinoma de pulmón localizado.
"Ya acabamos con las pandillas en El Salvador, y también podemos acabar con ustedes", escribió el mandatario en X en un mensaje dirigido a los líderes pandilleros que habrían secuestrado a los salvadoreños.
"Ya acabamos con las pandillas en El Salvador, y también podemos acabar con ustedes", escribió el mandatario en X en un mensaje dirigido a los líderes pandilleros que habrían secuestrado a los salvadoreños.
