arXiv preprints from January 1, 2026 through September 14, 2026 — 15:48:19 EST
Reinforcement Learning with Verifiable Rewards (RLVR) elicits long chain-of-thought reasoning in large language models (LLMs), but outcome-based rewards lead to coarse-grained advantage estimation. While existing approaches improve RLVR via token-level entropy or sequence-level length control, they lack a semantically grounded,...
Researchers face a persistent barrier when applying computational algorithms with parameter configuration typically demanding programming skills, interfaces differing across environments, and settings rarely persisting between sessions. This fragmentation forces repetitive input, slows iterative exploration, and undermines...
Large language models (LLMs) can achieve strong reasoning performance with sufficient computation, but they do not inherently know how much computation a task requires. We study budgeted inference-time reasoning for multiple tasks under a strict global token constraint and formalize it as a Ordered Stochastic Multiple-Choice Knapsack...
Deep learning optimization exhibits structure that is not captured by worst-case gradient bounds. Empirically, gradients along training trajectories are often temporally predictable and evolve within a low-dimensional subspace. In this work we formalize this observation through a measurable framework for predictable gradient...
This paper proposes a conceptual framework in which intelligence and consciousness emerge from relational structure rather than from prediction or domain-specific mechanisms. Intelligence is defined as the capacity to form and integrate causal connections between signals, actions, and internal states. Through context enrichment,...
Weather and climate models rely on parametrisations to represent unresolved sub-grid processes. Traditional schemes rely on fixed coefficients that are weakly constrained and tuned offline, contributing to persistent biases that limit their ability to adapt to underlying physics. This study presents a framework that learns components...
Error-correcting codes are combinatorial objects designed to cope with the problem of reliable transmission of information on a noisy channel. A fundamental problem in coding theory and practice is to efficiently decode the received word with errors to obtain the transmitted codeword. In this paper, we consider the decoding problem of...
To efficiently combat the spread of LLM-generated misinformation, we present RADAR, a Retrieval-Augmented Detector with Adversarial Refinement for robust fake news detection. Our approach employs a generator that rewrites real articles with factual perturbations, paired with a lightweight detector that verifies claims using dense...
The continued promise of Large Language Models (LLMs), particularly in their natural language understanding and generation capabilities, has driven a rapidly increasing interest in identifying and developing LLM use cases. In an effort to complement the ingrained "knowledge" of LLMs, Retrieval-Augmented Generation (RAG) techniques...
We present a rigorous, human-in-the-loop evaluation framework for assessing the performance of AI agents on the task of Air Traffic Control, grounded in a regulator-certified simulator-based curriculum used for training and testing real-world trainee controllers. By leveraging legally regulated assessments and involving expert human...
Despite the fact that cancer survivability rates vary greatly between stages, traditional survival prediction models have frequently been trained and assessed using examples from all combined phases of the disease. This method may result in an overestimation of performance and ignore the stage-specific variations. Using the SEER...
Allowing less capable devices to offload computational tasks to more powerful devices or servers enables the development of new applications that may not run correctly on the device itself. Deciding where and why to run each of those applications is a complex task. Therefore, different approaches have been adopted to make offloading...
Recent commercial systems such as Suno demonstrate strong capabilities in long-form song generation, while academic research remains largely non-reproducible due to the lack of publicly available training data, hindering fair comparison and progress. To this end, we release a fully open-source system for long-form song generation with...
PHP's dominance in web development is undermined by security challenges: static analysis lacks semantic depth, causing high false positives; dynamic analysis is computationally expensive; and automated vulnerability localization suffers from coarse granularity and imprecise context. Additionally, the absence of large-scale PHP...
Large reasoning models enhanced by reinforcement learning with verifiable rewards have achieved significant performance gains by extending their chain-of-thought. However, this paradigm incurs substantial deployment costs as models often exhibit excessive verbosity on simple queries. Existing efficient reasoning methods relying on...
We introduce online action-stacking, an inference-time wrapper for reinforcement learning policies that produces realistic air traffic control commands while allowing training on a much smaller discrete action space. Policies are trained with simple incremental heading or level adjustments, together with an action-damping penalty that...
Objective: Stroke is one of the leading causes of disabilities. One promising approach is to extend the rehabilitation with self-initiated robot-assisted movement therapy. To enable this, it is required to detect the patient's intention to move to trigger the assistance of a robotic device. This intention to move can be detected from...
Escalating air traffic demand is driving the adoption of automation to support air traffic controllers, but existing approaches face a trade-off between safety assurance and interpretability. Optimisation-based methods such as reinforcement learning offer strong performance but are difficult to verify and explain, while rules-based...
Hands are central to interacting with our surroundings and conveying gestures, making their inclusion essential for full-body motion synthesis. Despite this, existing human motion synthesis methods fall short: some ignore hand motions entirely, while others generate full-body motions only for narrowly scoped tasks under highly...
Reliable connectivity is critical for Public Protection and Disaster Relief operations, especially in rural or compromised environments where terrestrial infrastructure is unavailable. In such scenarios, NTNs, and specifically UAVs, are promising candidates to provide on-demand and rapid connectivity on the ground, serving as aerial...
Recent Vision-Language Models (VLMs) have demonstrated significant potential in robotic planning. However, they typically function as semantic reasoners, lacking an intrinsic understanding of the specific robot's physical capabilities. This limitation is particularly critical in interactive navigation, where robots must actively...
Existing 1D visual tokenizers for autoregressive (AR) generation largely follow the design principles of language modeling, as they are built directly upon transformers whose priors originate in language, yielding single-hierarchy latent tokens and treating visual data as flat sequential token streams. However, this language-like...
Every surface that is intrinsically polyhedral can be represented by a portalgon: a collection of polygons in the Euclidean plane with some pairs of equally long edges abstractly identified. While this representation is arguably simpler than meshes (flat polygons in R3 forming a surface), it has unbounded happiness: a shortest path in...
Reinforcement Learning (RL) has enabled Large Language Models (LLMs) to achieve remarkable reasoning in domains like mathematics and coding, where verifiable rewards provide clear signals. However, extending this paradigm to financial decision is challenged by the market's stochastic nature: rewards are verifiable but inherently...
We introduce Arctic-ABSA, a collection of powerful models for real-life aspect-based sentiment analysis (ABSA). Our models are tailored to commercial needs, trained on a large corpus of public data alongside carefully generated synthetic data, resulting in a dataset 20 times larger than SemEval14. We extend typical ABSA models by...