Tootfinder

Revolutionizing Reinforcement Learning Framework for Diffusion Large Language Models
Yinjie Wang, Ling Yang, Bowen Li, Ye Tian, Ke Shen, Mengdi Wang
https://arxiv.org/abs/2509.06949

Revolutionizing Reinforcement Learning Framework for Diffusion Large Language Models
We propose TraceRL, a trajectory-aware reinforcement learning framework for diffusion language models (DLMs) that incorporates preferred inference trajectory into post-training, and is applicable across different architectures. Equipped with a diffusion-based value model that enhances training stability, we demonstrate improved reasoning performance on complex math and coding tasks. Besides, it can also be applied to adapt block-specific models to larger blocks, which improves sampling flexibil…

Reinforcement Learning for Clinical Reasoning: Aligning LLMs with ACR Imaging Appropriateness Criteria
Anni Tziakouri, Filippo Menolascina
https://arxiv.org/abs/2510.05194 https…

Reinforcement Learning for Clinical Reasoning: Aligning LLMs with ACR Imaging Appropriateness Criteria
Medical imaging has revolutionized diagnosis, yet unnecessary procedures are rising, exposing patients to radiation and stress, limiting equitable access, and straining healthcare systems. The American College of Radiology Appropriateness Criteria, developed through extensive multidisciplinary review, provide evidence-based guidance but remain underutilized. Leveraging advances in LLM reasoning, we introduce a Reasoning Agent trained with Reinforcement Learning (RL), specifically Group Relative…

SmartFlow: A CFD-solver-agnostic deep reinforcement learning framework for computational fluid dynamics on HPC platforms
Maochao Xiao, Yuning Wang, Felix Rodach, Bernat Font, Marius Kurz, Pol Su\'arez, Di Zhou, Francisco Alc\'antara-\'Avila, Ting Zhu, Junle Liu, Ricard Montal\`a, Jiawei Chen, Jean Rabault, Oriol Lehmkuhl, Andrea Beck, Johan Larsson, Ricardo Vinuesa, Sergio Pirozzoli

SmartFlow: A CFD-solver-agnostic deep reinforcement learning framework for computational fluid dynamics on HPC platforms
Deep reinforcement learning (DRL) is emerging as a powerful tool for fluid-dynamics research, encompassing active flow control, autonomous navigation, turbulence modeling and discovery of novel numerical schemes. We introduce SmartFlow, a CFD-solver-agnostic framework for both single- and multi-agent DRL algorithms that can easily integrate with MPI-parallel CPU and GPU-accelerated solvers. Built on Relexi and SmartSOD2D, SmartFlow uses the SmartSim infrastructure library and our newly develope…

Gerade konnte ich im aktuellen Augustin eine "Stadt unterm Radar" vorstellen und schon bereise ich die nächste - die außerhalb Österreichs gelegene Geburtsstadt eines von der habsburgischen Militärgerichtsbarkeit hingerichteten Revolutionärs, an den auf dem nach ihm benannten Platz eine 1958 errichtete Statue erinnert. Ein Tipp: Schriftsteller*innen wie Friedrich Wolf, Franz Fleischhacker und Eva Priester haben sich den Taten des hier Gewürdigten und seiner Genossen gewidmet.

Hierarchical Reinforcement Learning Framework for Adaptive Walking Control Using General Value Functions of Lower-Limb Sensor Signals
Sonny T. Jones, Grange M. Simpson, Patrick M. Pilarski, Ashley N. Dalrymple
https://arxiv.org/abs/2507.16983

Hierarchical Reinforcement Learning Framework for Adaptive Walking Control Using General Value Functions of Lower-Limb Sensor Signals
Rehabilitation technology is a natural setting to study the shared learning and decision-making of human and machine agents. In this work, we explore the use of Hierarchical Reinforcement Learning (HRL) to develop adaptive control strategies for lower-limb exoskeletons, aiming to enhance mobility and autonomy for individuals with motor impairments. Inspired by prominent models of biological sensorimotor processing, our investigated HRL approach breaks down the complex task of exoskeleton contro…

I have extended thoughts on a few nuances of burnout, resilience, and employment
Before taking time off for burnout, my skip manager reminded me to read the strongly positive 360 feedback from my reports. That's both a shallow and a deep reinforcement of resilience, first and foremost by rebuilding and grounding self-confidence. Reading positive feedback provides evidence that I'm capable and effective at my job.
Beyond self-confidence, I have other needs in a workplace, …

Knowledge Defined Networking for 6G: A Reinforcement Learning Example for Resource Management
Erol Ko\c{c}o\u{g}lu, Mehmet Ozdem, Tu\u{g}\c{c}e Bilen
https://arxiv.org/abs/2509.26075

Knowledge Defined Networking for 6G: A Reinforcement Learning Example for Resource Management
6G networks are expected to revolutionize connectivity, offering significant improvements in speed, capacity, and smart automation. However, existing network designs will struggle to handle the demands of 6G, which include much faster speeds, a huge increase in connected devices, lower energy consumption, extremely quick response times, and better mobile broadband. To solve this problem, incorporating the artificial intelligence (AI) technologies has been proposed. This idea led to the concept …

Deep Reinforcement Learning for Active Flow Control around a Three-Dimensional Flow-Separated Wing at Re = 1,000
R. Montal\`a, B. Font, P. Su\'arez, J. Rabault, O. Lehmkuhl, R. Vinuesa, I. Rodriguez
https://arxiv.org/abs/2509.10195

Deep Reinforcement Learning for Active Flow Control around a Three-Dimensional Flow-Separated Wing at Re = 1,000
This study explores the use of deep reinforcement learning (DRL) for active flow control (AFC) to reduce flow separation on wings at high angles of attack. Concretely, here the DRL agent controls the flow over the three-dimensional NACA0012 wing section at the Reynolds number Re = 1,000 and angle of attack AoA = 20 degrees, autonomously identifying optimal control actions through real-time flow data and a reward function focused on improving aerodynamic performance. The framework integrates the…

Learning in an Echo Chamber: Online Learning with Replay Adversary
Daniil Dmitriev, Harald Eskelund Franck, Carolin Heinzler, Amartya Sanyal
https://arxiv.org/abs/2509.25135 htt…

Learning in an Echo Chamber: Online Learning with Replay Adversary
As machine learning systems increasingly train on self-annotated data, they risk reinforcing errors and becoming echo chambers of their own beliefs. We model this phenomenon by introducing a learning-theoretic framework: Online Learning in the Replay Setting. In round $t$, the learner outputs a hypothesis $\hat{h}_t$; the adversary then reveals either the true label $f^\ast(x_t)$ or a replayed label $\hat{h}_i(x_t)$ from an earlier round $i < t$. A mistake is counted only when the true label is…

Discovering Flow Separation Control Strategies in 3D Wings via Deep Reinforcement Learning
R. Montal\`a, B. Font, P. Su\'arez, J. Rabault, O. Lehmkuhl, R. Vinuesa, I. Rodriguez
https://arxiv.org/abs/2509.10185

Discovering Flow Separation Control Strategies in 3D Wings via Deep Reinforcement Learning
In this work, deep reinforcement learning (DRL) is applied to active flow control (AFC) over a threedimensional SD7003 wing at a Reynolds number of Re = 60,000 and angle of attack of AoA = 14 degrees. In the uncontrolled baseline case, the flow exhibits massive separation and a fully turbulent wake. Using a GPU-accelerated CFD solver and multi-agent training, DRL discovers control strategies that enhance lift (79%), reduce drag (65%), and improve aerodynamic efficiency (408%). Flow visualizatio…