arXiv:2601.16392v1 Announce Type: new Abstract: With the advent of agentic AI, Software Engineering is transforming to a new era dubbed Software Engineering 3.0. Software project management (SPM) must also evolve with such transformations to boost successful project completion, while keeping humans at the heart of it. Building on our preliminary ideas of “agentic SPM”, and supporting literature, we present our vision of an “Agentic Project Manager (PM)” as a multi-agent system for SPM 3.0. They will work like […]

Ver mais

arXiv:2601.20906v1 Announce Type: new Abstract: Precision oncology requires forecasting clinical events and trajectories, yet modeling sparse, multi-modal clinical time series remains a critical challenge. We introduce TwinWeaver, an open-source framework that serializes longitudinal patient histories into text, enabling unified event prediction as well as forecasting with large language models, and use it to build Genie Digital Twin (GDT) on 93,054 patients across 20 cancer types. In benchmarks, GDT significantly reduces forecasting error, achieving a median Mean Absolute Scaled […]

Ver mais

Recent progress in reinforcement learning with verifiable rewards (RLVR) shows that small, specialized language models (SLMs) can exhibit structured reasoning without relying on large monolithic LLMs. We introduce soft hidden-state collaboration, where multiple heterogeneous frozen SLM experts are integrated through their internal representations via a trainable attention interface. Experiments on Reasoning Gym and GSM8K show that this latent integration is competitive with strong single-model RLVR baselines. Ablations further reveal a dual mechanism of expert utilization: for simpler arithmetic […]

Ver mais

arXiv:2508.04444v2 Announce Type: replace-cross Abstract: In this paper, we propose new randomized algorithms for estimating the two-to-infinity and one-to-two norms in a matrix-free setting, using only matrix-vector multiplications. Our methods are based on appropriate modifications of Hutchinson’s diagonal estimator and its Hutch++ version. We provide oracle complexity bounds for both modifications. We further illustrate the practical utility of our algorithms for Jacobian-based regularization in deep neural network training on image classification tasks. We also demonstrate that our methodology […]

Ver mais

arXiv:2601.02157v2 Announce Type: replace-cross Abstract: We propose a graph-based, multi-fidelity learning framework for the prediction of stationary Navier–Stokes solutions in non-parametrized two-dimensional geometries. The method is designed to guide the learning process through successive approximations, starting from reduced-order and full Stokes models, and progressively approaching the Navier–Stokes solution. To effectively capture both local and long-range dependencies in the velocity and pressure fields, we combine graph neural networks with Transformer and Mamba architectures. While Transformers achieve the highest accuracy, […]

Ver mais

arXiv:2602.07100v1 Announce Type: new Abstract: Automated floorplan generation aims to improve design quality, architectural efficiency, and sustainability by jointly modeling global spatial organization and precise geometric detail. However, existing approaches operate in raster space and rely on post hoc vectorization, which introduces structural inconsistencies and hinders end-to-end learning. Motivated by compositional spatial reasoning, we propose TLC-Plan, a hierarchical generative model that directly synthesizes vector floorplans from input boundaries, aligning with human architectural workflows based on modular and reusable […]

Ver mais

Although most of the automated theorem-proving approaches depend on formal proof systems, informal theorem proving can align better with large language models’ (LLMs) strength in natural language processing. In this work, we identify a primary bottleneck in informal theorem proving as a lack of insight, namely the difficulty of recognizing the core techniques required to solve complex problems. To address this, we propose a novel framework designed to cultivate this essential reasoning skill and enable LLMs to perform […]

Ver mais

I’ve spent some time recently building an RL agent to play competitive Pokémon (Generation 9 Random Battles on Pokémon Showdown). I wanted to share the architecture, the training pipeline, and some thoughts on the MCTS vs. pure-network approaches in this specific environment. Why Pokémon? From an RL perspective, a Pokémon battle is a great proxy for real-world, messy decision-making. It combines three massive headaches: Simultaneous Action: Both agents lock in actions concurrently. You are trying to approximate Nash […]

Ver mais

arXiv:2603.05637v1 Announce Type: new Abstract: The rapid adoption of foundation models has significantly expanded the capabilities of software systems, enabling them to perform complex language, reasoning, and interaction tasks that were previously difficult to automate. However, this progress has also introduced novel challenges that were largely absent in previous generations of software. In particular, the increasing integration of foundation models with external tools and resources raises new concerns regarding reliability, security, and robustness. The Model Context Protocol (MCP) […]

Ver mais