arXiv preprints from January 1, 2026 through July 20, 2026 — 20:54:05 EST
While Large Language Models (LLMs) enable complex autonomous behavior, current agents remain constrained by static, human-designed prompts that limit adaptability. Existing self-improving frameworks attempt to bridge this gap but typically rely on inefficient, multi-turn recursive loops that incur high computational costs. To address...
Fuzzing continues to be the most effective method for identifying security vulnerabilities in software. In the context of fuzz testing, the fuzzer supplies varied inputs to fuzz targets, which are designed to comprehensively exercise critical sections of the client code. Various studies have focused on optimizing and developing...
Intelligent surveillance systems often handle perceptual tasks such as object detection, facial recognition, and emotion analysis independently, but they lack a unified, adaptive runtime scheduler that dynamically allocates computational resources based on contextual triggers. This limits their holistic understanding and efficiency on...
Existing works increasingly adopt memory-centric mechanisms to process long contexts in a segment manner, and effective memory management is one of the key capabilities that enables large language models to effectively propagate information across the entire sequence. Therefore, leveraging reward models (RMs) to automatically and...
Named Entity Recognition (NER) is an important task in natural language processing that aims to identify and extract key entities from unstructured text. We present a novel application of NER in plasma physics research articles and address the challenges of extracting specialized entities from scientific text in this domain. Research...
Despite recent advances in multimodal large language models (MLLMs), their ability to understand and interact with music remains limited. Music understanding requires grounded reasoning over symbolic scores and expressive performance audio, which general-purpose MLLMs often fail to handle due to insufficient perceptual grounding. We...
Existing reinforcement learning methods for LLM reasoning implicitly assume that the policy generating training trajectories should coincide with the one producing inference responses. We argue that this is a misleading inductive bias: the optimization-optimal trajectory distribution favors informative gradients, whereas the...
Overlapping calendar invitations force busy professionals to repeatedly decide which meetings to attend, reschedule, or decline. We refer to this preference-driven decision process as calendar conflict resolution. Automating this decision process is crucial yet challenging. Scheduling logistics can drain hours, and human delegation...
Reliable reasoning in Large Language Models (LLMs) is challenged by their propensity for hallucination. While augmenting LLMs with Knowledge Graphs (KGs) improves factual accuracy, existing KG-augmented methods fail to quantify epistemic uncertainty in both the retrieved evidence and LLMs' reasoning. To bridge this gap, we introduce...
Dynamic graphs have attracted increasing attention due to their ability to model complex and evolving relationships in real-world scenarios. Traditional approaches typically pre-train models using dynamic link prediction and directly apply the resulting node temporal embeddings to specific downstream tasks. However, the significant...
Constrained Reinforcement Learning (CRL) aims to maximize cumulative rewards while satisfying constraints. However, existing CRL algorithms often encounter significant constraint violations during training, limiting their applicability in safety-critical scenarios. In this paper, we identify the underestimation of the cost value...
Box-free model watermarking has gained significant attention in deep neural network (DNN) intellectual property protection due to its model-agnostic nature and its ability to flexibly manage high-entropy image outputs from generative models. Typically operating in a black-box manner, it employs an encoder-decoder framework for...
Existing anomaly detection methods for Wireless Sensor Networks (WSNs) generally suffer from insufficient extraction of spatio-temporal correlation features, reliance on either timedomain or frequencydomain information alone, and high computational overhead. To address these limitations, this paper proposes a topology-enhanced...
Compared with IP multicast, Overlay Multicast (OM) offers better compatibility and flexible deployment in heterogeneous, cross-domain networks. However, traditional OM struggles to adapt to dynamic traffic due to unawareness of physical resource states, and existing reinforcement learning methods fail to decouple OM's tightly coupled...
Group testing concerns itself with the accurate recovery of a set of "defective" items from a larger population via a series of tests. While most works in this area have considered the classical group testing model, where tests are binary and indicate the presence of at least one defective item in the test, we study the cascaded group...
Preterm infants (born between 28 and 37 weeks of gestation) face elevated risks of neurodevelopmental delays, making early identification crucial for timely intervention. While deep learning-based volumetric segmentation of brain MRI scans offers a promising avenue for assessing neonatal neurodevelopment, achieving accurate...
Variational quantum circuits are increasingly studied as continuous-function approximators, but quantum regression remains difficult to train when global losses, finite-shot stochasticity, and circuit-depth growth combine to produce weak or ill-conditioned gradient signals. We study this trainability problem in a controlled hybrid...
Scaling test-time compute via Long Chain-of-Thought (Long-CoT) significantly enhances reasoning capabilities, yet extended generation does not guarantee correctness: after an early wrong commitment, models may keep elaborating a self-consistent but incorrect prefix. Through fine-grained trajectory analysis, we identify Thinking Traps,...
Commercial Off-The-Shelf (COTS) hardware, such as microprocessors, are widely adopted in system design due to their ability to reduce development time and cost compared to custom solutions. However, supply chain entities involved in the design and fabrication of COTS components are considered untrusted from the consumer's standpoint...
Cloud data centers face increasing pressure to reduce operational energy consumption as big data workloads continue to grow in scale and complexity. This paper presents a workload aware and energy efficient scheduling framework that profiles CPU utilization, memory demand, and storage IO behavior to guide virtual machine placement...
The current state of event detection research has two notable re-occurring limitations that we investigate in this study. First, the unidirectional nature of decoder-only LLMs presents a fundamental architectural bottleneck for natural language understanding tasks that depend on rich, bidirectional context. Second, we confront the...
Gait recognition is emerging as a promising technology and an innovative field within computer vision, with a wide range of applications in remote human identification. However, existing methods typically rely on complex architectures to directly extract features from images and apply pooling operations to obtain sequence-level...
Image retrieval is a critical step for reducing the quadratic cost of image matching in unconstrained Structure-from-Motion (SfM). Unlike generic image retrieval, however, the relevant goal of SfM is to identify geometrically matchable image pairs rather than merely semantically similar images. Prevailing methods are largely trained...
For variable-length coding with an almost-sure distortion constraint, Zhang et al. show that for discrete sources the redundancy is upper bounded by $\log n/n$ and lower bounded (in most cases) by $\log n/(2n)$, ignoring lower order terms. For a uniform source with a distortion measure satisfying certain symmetry conditions, we show...
Machine learning enabled systems (MLS) often operate in settings where they regularly encounter uncertainties arising from changes in their surrounding environment. Without structured oversight, such changes can degrade model behavior, increase operational cost, and reduce the usefulness of deployed systems. Although Machine Learning...