arXiv preprints from January 1, 2026 through September 22, 2026 — 05:52:30 EST
Optimizing communication topology in LLM-based multi-agent system is critical for enabling collective intelligence. Existing methods mainly rely on spatio-temporal interaction paradigms, where the sequential execution of multi-round dialogues incurs high latency and computation. Motivated by the recent insights that evaluation and...
Encryption and Decryption is the process of sending a message in a ciphered way that appears meaningless and could be deciphered using a key for security purposes to avoid data breaches. This paper expands on the previous work on Sudoku-based encryption methods, applying it to other forms of media including images, audio and video. It...
Broadband optical response governs light-matter interactions across photonics, plasmonics, thermal radiation, and quantum fluctuation electrodynamics, yet determining a continuous dielectric function over many decades in frequency typically requires combining multiple spectroscopies, extrapolations, and material models. Here we show...
Vision In-Context Learning (VICL) enables inpainting models to quickly adapt to new visual tasks from only a few prompts. However, existing methods suffer from two key issues: (1) selecting only the most similar prompt discards complementary cues from other high-quality prompts; and (2) failing to exploit the structured information...
Multi-robot systems can greatly enhance efficiency through coordination and collaboration, yet in practice, full-time communication is rarely available and interactions are constrained to close-range exchanges. Existing methods either maintain all-time connectivity, rely on fixed schedules, or adopt pairwise protocols, but none adapt...
Modeling yield stress fluids in complex flow scenarios presents significant challenges, particularly because conventional rheological characterization methods often yield material parameters that are not fully representative of the intricate constitutive behavior observed in complex conditions. We propose a Bayesian uncertainty...
Large language models (LLMs) are challenging to deploy for domain-specific tasks due to their massive scale. While distilling a fine-tuned LLM into a smaller student model is a promising alternative, the capacity gap between teacher and student often leads to suboptimal performance. This raises a key question: when and how can a...
We establish various upper bounds on Type-I and Type-II shifted bilinear sums with Salié sums modulo a large prime $q$. We use these bounds to study, for fixed integers $a,b\not \equiv 0 \bmod q$, the distribution ofsolutions to the congruence $x^2 \equiv ap+b \bmod q$, over primes $p\le P$. This is similar to the recently studied...
Repository aware coding agents often struggle to recover build and test structure, especially in multilingual projects where cross language dependencies are encoded across heterogeneous build systems and tooling. We introduce the Repository Intelligence Graph (RIG), a deterministic, evidence backed architectural map that represents...
Magic states are essential for universal quantum computation and are widely viewed as a key source of quantum advantage, yet in realistic devices they are inevitably noisy. In this work, we characterize how noise on injected magic resources changes the classical simulability of quantum circuits and when it induces a transition from...
This study proposes MCEMOL (Multi-Constrained Evolutionary Molecular Design Framework), a molecular optimization approach integrating rule-based evolution with molecular crossover. MCEMOL employs dual-layer evolution: optimizing transformation rules at rule level while applying crossover and mutation to molecular structures. Unlike...
Large reasoning models such as DeepSeek-R1 and their distilled variants achieve strong performance on complex reasoning tasks. Yet, distilling these models often demands large-scale data for supervised fine-tuning (SFT), motivating the pursuit of data-efficient training methods. To address this, we propose a skill-centric distillation...
Evaluating whether multimodal large language models truly understand long-form scientific papers remains challenging: answer-only metrics and synthetic "Needle-In-A-Haystack" tests often reward answer matching without requiring a causal, evidence-linked reasoning trace in the document. We propose the "Fish-in-the-Ocean" (FITO)...
Visual In-Context Learning (VICL) has emerged as a powerful paradigm, enabling models to perform novel visual tasks by learning from in-context examples. The dominant "retrieve-then-prompt" approach typically relies on selecting the single best visual prompt, a practice that often discards valuable contextual information from other...
We study prime Fano threefolds of genus 12 ($V_{22}$-varieties) with positive-dimensional automorphism groups in positive and mixed characteristic. We classify such varieties over any perfect field. In particular, we prove that $V_{22}$-varieties of Mukai-Umemura type over $k$ exist if and only if $\mathrm{char}\ k \neq 2$, $5$. We...
The rapid integration of IoT with edge computing has revolutionized various domains, particularly healthcare, by enabling real-time data sharing, remote monitoring, and decision-making. However, it introduces critical challenges, including data privacy breaches, security vulnerabilities, especially in environments dealing with...
The automated extraction of structured questions from paper-based mathematics exams is fundamental to intelligent education, yet remains challenging in real-world settings due to severe visual noise. Existing benchmarks mainly focus on clean documents or generic layout analysis, overlooking both the structural integrity of...
Interactive humanoid video generation aims to synthesize lifelike visual agents that can engage with humans through continuous and responsive video. Despite recent advances in video synthesis, existing methods often grapple with the trade-off between high-fidelity synthesis and real-time interaction requirements. In this paper, we...
Multi-agent systems built on large language models are increasingly deployed in strategic policy and governance settings, where agents representing stakeholders with conflicting interests must coordinate under shared constraints. These systems typically assign role-based personas to agents, describing their motivations and objectives....
With the incredible advancements in Large Language Models (LLMs), many people have started using them to satisfy their information needs. However, utilizing LLMs might be problematic for political issues where disagreement is common and model outputs may reflect training-data biases or deliberate alignment choices. To better...
Reeb spaces of smooth functions are fundamental and strong tools in understanding manifolds via smooth functions with mild critical points. They are defined as the natural spaces of all connected components of level sets. They are also important objects in related studies. Realization of graphs as Reeb spaces of smooth functions of...
As knowledge and semantics on the web grow increasingly complex, enhancing Large Language Models (LLMs)' comprehension and reasoning capabilities has become particularly important. Chain-of-Thought (CoT) prompting has been shown to enhance the reasoning capabilities of LLMs. However, it still falls short on logical reasoning tasks...
This paper presents a super realized gain, circularly polarized strip-crossed dipole antenna operating at 3.5 GHz. Superdirective behavior is achieved by leveraging strong inter-element mutual coupling through careful adjustment of the strip dimensions. The antenna features a single driven element, with the other element passively...
As we move towards more ubiquitous computing, the concept of pervasive augmented reality (PAR) could lead to a major evolution in the relationship between humans, computing and the world. The experience of a continuously augmented world can have both benefits and undesirable consequences for users' lives, and raises many questions in...
We consider the Lamé transmission problem in $\mathbb{R}^3$ with a bounded isotropic elastic inclusion in a high-contrast setting, where the interior-to-exterior Lamé moduli and densities scale like $1/τ$ as $τ\to0$. We study the scattering resonances of the associated self-adjoint Hamiltonian, defined as the poles of the meromorphic...