Related papers: STARS: Skill-Triggered Audit for Request-Condition…

The popularity of automatic speech recognition (ASR) systems nowadays leads to an increasing need for improving their accessibility. Handling stuttering speech is an important feature for accessible ASR systems. To improve the accessibility…

When language model agents tackle complex software engineering tasks, they often degrade over long trajectories, which we define as *agent drift*. We focus on two recurring failure modes *overthinking* and *overacting*, i.e., where the…

Autonomous vehicles (AV) depend on the sensors like RADAR and camera for the perception of the environment, path planning, and control. With the increasing autonomy and interactions with the complex environment, there have been growing…

Assistive devices must determine both what a user intends to do and how reliable that prediction is before providing support. We introduce a safety-critical triggering framework based on calibrated probabilities for multimodal next-action…

Test-time scaling has become a standard way to improve performance and boost reliability of neural network models. However, its behavior on agentic, multi-step tasks remains less well-understood: small per-step errors can compound over long…

While Large Reasoning Models (LRMs) have achieved remarkable performance by scaling test-time compute, they frequently suffer from Cognitive Inertia, a failure pattern manifesting as either overthinking (inertia of motion) or reasoning…

Computer-Using Agents (CUAs) are rapidly extending large language models (LLMs) beyond text-based reasoning toward action execution in more complex environments, such as web browsers and graphical user interfaces (GUIs). However, existing…

This report examines the synergy between Large Language Models (LLMs) and Static Application Security Testing (SAST) to improve vulnerability discovery. Traditional SAST tools, while effective for proactive security, are limited by high…

Designing effective task-level prompts is crucial for improving the performance of Large Language Models (LLMs). While prior work on instruction induction demonstrates that LLMs can infer better instructions with limited examples, existing…

We investigate the problem of safe control synthesis for systems operating in environments with uncontrollable agents whose dynamics are unknown but coupled with those of the controlled system. This scenario naturally arises in various…

The computational burden of attention in long-context language models has motivated two largely independent lines of work: sparse attention mechanisms that reduce complexity by attending to selected tokens, and gated attention variants that…

The companion paper introduced a four-level verification lattice on agent-skill manifests (unverified, declared, tested, formal) and left the top level aspirational. This paper closes that gap. We give a precise semantics for skill…

Reinforcement learning post-training has substantially improved the reasoning accuracy of vision-language models, yet the resulting policies remain poorly calibrated. Terminal correctness rewards provide no gradient that penalizes confident…

Knowledge-based systems reason over some knowledge base. Hence, an important issue for such systems is how to acquire the knowledge needed for their inference. This paper assesses active learning methods for acquiring knowledge for "static…

Agentic search enables language models to solve knowledge-intensive tasks by adaptively acquiring external evidence over multiple steps. Reinforcement learning with verifiable rewards (RLVR) has emerged as a widely adopted training paradigm…

The calibration and training of a neural network is a complex and time-consuming procedure that requires significant computational resources to achieve satisfactory results. Key obstacles are a large number of hyperparameters to select and…

Patient safety training is essential for preparing healthcare professionals to identify, investigate, and prevent adverse events. However, conventional simulation-based approaches often require substantial faculty time, physical resources,…

Simulation-based testing has become a standard approach to validating autonomous driving agents prior to real-world deployment. A high-quality validation campaign will exercise an agent in diverse contexts comprised of varying static…

The Multisource AI Scorecard Table (MAST) is a checklist tool based on analytic tradecraft standards to inform the design and evaluation of trustworthy AI systems. In this study, we evaluate whether MAST is associated with people's trust…

SAST (Static Application Security Testing) tools are among the most widely used techniques in defensive cybersecurity, employed by commercial and non-commercial organizations to identify potential vulnerabilities in software. Despite their…