arXiv preprints from January 1, 2026 through September 13, 2026 — 08:29:44 EST
Search-augmented large language models (LLMs) excel at knowledge-intensive tasks by integrating external retrieval. However, they often over-search -- unnecessarily invoking search tool even when it does not improve response quality, which leads to computational inefficiency and hallucinations by incorporating irrelevant context. In...
Users demand fast, seamless webpage experiences, yet developers often struggle to meet these expectations within tight constraints. Performance optimization, while critical, is a time-consuming and often manual process. One of the most complex tasks in this domain is modifying the Document Object Model (DOM), which is why this study...
Hybrid action space, which combines discrete choices and continuous parameters, is prevalent in domains such as robot control and game AI. However, efficiently modeling and optimizing hybrid discrete-continuous action space remains a fundamental challenge, mainly due to limited policy expressiveness and poor scalability in...
Modern wireless systems are envisioned to employ antenna architectures that not only transmit and receive electromagnetic (EM) waves, but also intentionally reflect and possibly transform incident EM waves. In this paper, we propose a mathematically rigorous framework grounded in Maxwell's equations for analyzing the complexity of EM...
With the global population ageing, it is crucial to enable individuals to live independently and safely in their homes. Using ubiquitous sensors such as Passive InfraRed sensors (PIR) and door sensors is drawing increasing interest for monitoring daily activities and facilitating preventative healthcare interventions for the elderly....
In a previous article, we have introduced the problem of local generation of languages, where the communication underlying the generation procedure is captured by a simplicial complex. We study in details this problem for the language of binary monotonic sequences. We prove general results and identify several classes of minimal...
Several interconnection networks are based on the complete graph topology. Networks with a moderate size can be based on a single complete graph. However, large-scale networks such as Dragonfly and HyperX use, respectively, a hierarchical or a multi-dimensional composition of complete graphs. The number of links in these networks is...
Transferring from a 2-year to a 4-year college is crucial for socioeconomic mobility, yet students often face challenges ensuring their credits are fully recognized, leading to delays in their academic progress and unexpected costs. Determining whether courses at different institutions are equivalent (i.e., articulation) is essential...
Motivated by the recent introduction and large-scale deployment of BBR congestion control algorithms, multiple studies have investigated the performance and fairness implications of this shift from loss-based to delay-based congestion control. Given the potential Internet-wide adoption of BBR, we must also consider its robustness in...
Large language models (LLMs) exhibit exceptional performance but pose inherent risks of generating toxic content, restricting their safe deployment. While traditional methods (e.g., alignment) adjust output preferences, they fail to eliminate underlying toxic regions in parameters, leaving models vulnerable to adversarial attacks....
The advent of transformer-based language models has reshaped how AI systems process and generate text. In software engineering (SE), these models now support diverse activities, accelerating automation and decision-making. Yet, evidence shows that these models can reproduce or amplify social biases, raising fairness concerns. Recent...
Prostate cancer is one of the most common types of cancer in men. Its diagnosis by biopsy requires a high level of expertise and precision from the surgeon, so the results are highly operator-dependent. The aim of this work is to develop a robotic system for assisted ultrasound (US) examination of the prostate, a prebiopsy step that...
Instant-messaging human social chat typically progresses through a sequence of short messages. Existing step-by-step AI chatting systems typically split a one-shot generation into multiple messages and send them sequentially, but they lack an active waiting mechanism and exhibit unnatural message pacing. In order to address these...
High-fidelity agent initialization is crucial for credible Agent-Based Modeling across diverse domains. A robust framework should be Topic-Adaptive, capturing macro-level joint distributions while ensuring micro-level individual rationality. Existing approaches fall into two categories: static data-based retrieval methods that fail to...
We propose digital signal processing techniques for nonlinearity mitigation in high power optical amplifiers used in satellite communications. The acceptable link loss increases by 6dB with negligible complexity.
We investigate the capabilities and scalability of Large Language Models (LLMs) in optimization modeling, a domain requiring structured reasoning and precise formulation. To this end, we introduce OPT-ENGINE, an extensible benchmark framework with quantifiable and controllable complexity. OPT-ENGINE spans ten canonical Operations...
Estimating the persuasiveness of messages is critical in various applications, from recommender systems to safety assessment of LLMs. While it is imperative to consider the target persuadee's characteristics, such as their values, experiences, and reasoning styles, there is currently no established systematic framework to optimize...
Existing traffic simulation frameworks for autonomous vehicles typically rely on imitation learning or game-theoretic approaches that solve for Nash or coarse correlated equilibria, implicitly assuming perfectly rational agents. However, human drivers exhibit bounded rationality, making approximately optimal decisions under cognitive...
A new geometric shaping technique, referred to as coset shaping, is proposed and analyzed for coded QAM and PAM signaling. This method can be applied to both information and parity bits without introducing additional complexity. It is shown that, as the error-correcting code length and the modulation order grow, the gap to capacity of...
Engaging learners in dialogue around controversial issues is essential for examining diverse values and perspectives in pluralistic societies. While prior research has identified productive discussion moves mainly in STEM-oriented contexts, less is known about what constitutes productive discussion in ethical and value-laden...
Wi-Fi fingerprinting remains one of the most practical solutions for indoor positioning, however, its performance is often limited by the size and heterogeneity of fingerprint datasets, strong Received Signal Strength Indicator variability, and the ambiguity introduced in large and multi-floor environments. These factors significantly...
High-dimensional dense embeddings have become central to modern Information Retrieval, but many dimensions are noisy or redundant. Recently proposed DIME (Dimension IMportance Estimation), provides query-dependent scores to identify informative components of embeddings. DIME relies on a costly grid search to select a priori a...
We reveal that transformers trained in an autoregressive manner naturally encode time-delayed causal structures in their learned representations. When predicting future values in multivariate time series, the gradient sensitivities of transformer outputs with respect to past inputs directly recover the underlying causal graph, without...
As multilingual large language models become more widely used, ensuring their safety and fairness across diverse linguistic contexts presents unique challenges. While existing research on machine unlearning has primarily focused on monolingual settings, typically English, multilingual environments introduce additional complexities due...
Large Language Models (LLMs) offer a promising solution to complement traditional teaching and address global teacher shortages that affect hundreds of millions of children, but they fail to provide grade-appropriate responses for students at different educational levels. We introduce a framework for finetuning LLMs to generate...