cyberintel.kalymoon.com · 2689 articles · updated every 4 hours · grows forever
arXiv:2604.12102v1 Announce Type: new Abstract: We introduce compute-grounded reasoning (CGR), a design paradigm for spatial-aware research agents in which every answerable sub-problem is resolved by …
arXiv:2604.12096v1 Announce Type: new Abstract: On online advertising platforms, newly introduced promotional ads face the cold-start problem, as they lack sufficient user feedback for model training.…
arXiv:2604.12081v1 Announce Type: new Abstract: Memory is fundamental to social interaction, enabling humans to recall meaningful past experiences and adapt their behavior accordingly based on the con…
arXiv:2604.12066v1 Announce Type: new Abstract: Large language models can increasingly adapt educational tasks to learners characteristics. In the present study, we examine a multi-agent teacher-in-th…
arXiv:2604.12034v1 Announce Type: new Abstract: Retrieval-Augmented Generation remains the dominant pattern for giving LLMs persistent memory, but a visible cluster of personal wiki-style memory archi…
arXiv:2604.12025v1 Announce Type: new Abstract: The Semantic Web standardizes concept meaning for humans and machines, enabling machine-operable content and consistent interpretation that improves adv…
arXiv:2604.12019v1 Announce Type: new Abstract: Although artificial intelligence (AI) agents are increasingly proposed to support potentially longitudinal health tasks, such as symptom management, beh…
arXiv:2604.12016v1 Announce Type: new Abstract: Large language models map semantically related prompts to similar internal representations -- a phenomenon interpretable as attractor-like dynamics. We …
arXiv:2604.12007v1 Announce Type: new Abstract: Agent memory systems accumulate experience but currently lack a principled operational metric for memory quality governance -- deciding which memories t…
arXiv:2604.11978v1 Announce Type: new Abstract: Large language model (LLM) agents perform strongly on short- and mid-horizon tasks, but often break down on long-horizon tasks that require extended, in…
arXiv:2604.11969v1 Announce Type: new Abstract: We introduce ArcDeck, a multi-agent framework that formulates paper-to-slide generation as a structured narrative reconstruction task. Unlike existing m…
arXiv:2604.11924v1 Announce Type: new Abstract: While LLMs hold significant potential to transform scientific research, we advocate for their use to augment and empower researchers rather than to auto…
arXiv:2604.11914v1 Announce Type: new Abstract: Self-monitoring capabilities -- metacognition, self-prediction, and subjective duration -- are often proposed as useful additions to reinforcement learn…
arXiv:2604.11828v1 Announce Type: new Abstract: Science is widely regarded as humanity's most reliable method for uncovering truths about the natural world. Yet the \emph{trajectory} of scientific dis…
arXiv:2604.11950v1 Announce Type: cross Abstract: While recent LLM-based agents can identify many candidate bugs in source code, their reports remain static hypotheses that require manual validation, …
arXiv:2604.11928v1 Announce Type: cross Abstract: Time-series forecasting aims to predict future values by modeling temporal dependencies in historical observations. It is a critical component of many…
arXiv:2604.12994v1 Announce Type: new Abstract: Logical vulnerabilities in software stem from flaws in program logic rather than memory safety, which can lead to critical security failures. Although e…
arXiv:2604.12986v1 Announce Type: new Abstract: Autonomous AI agents are rapidly transitioning from experimental tools to operational infrastructure, with projections that 80% of enterprise applicatio…
arXiv:2604.12954v1 Announce Type: new Abstract: Generalized Reed-Solomon (GRS) and Gabidulin codes have been proposed for various code-based cryptosystems, though most such schemes without elaborate d…
arXiv:2604.12850v1 Announce Type: new Abstract: With increasing emphasis on transparency in digital governance, users expect more than silence when their access requests are denied by a system. Howeve…
arXiv:2604.12737v1 Announce Type: new Abstract: While Federated Learning (FL) mitigates direct data exposure, the resulting trained models remain susceptible to membership inference attacks (MIAs). Th…
arXiv:2604.12601v1 Announce Type: new Abstract: Passwords still remain a dominant authentication method, yet their security is routinely subverted by predictable user choices and large-scale credentia…
arXiv:2604.12548v1 Announce Type: new Abstract: Prompt injection has emerged as a critical security threat to large language models (LLMs), yet existing studies predominantly focus on single-dimension…
arXiv:2604.12446v1 Announce Type: new Abstract: Text-to-image (T2I) diffusion models have achieved remarkable success in image synthesis, but their reliance on large-scale data and open ecosystems int…