cyberintel.kalymoon.com · 54672 articles · updated every 4 hours · grows forever
arXiv:2603.13348v1 Announce Type: new Abstract: Tool use represents a critical capability for AI agents, with recent advances focusing on leveraging reinforcement learning (RL) to scale up the explici…
arXiv:2603.13351v1 Announce Type: new Abstract: In a previous study [Jo, 2026], STAR reasoning (Situation, Task, Action, Result) raised car wash problem accuracy from 0% to 85% on Claude Sonnet 4.5, a…
arXiv:2603.13353v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly positioned as scalable tools for annotating educational data, including classroom discourse, interaction l…
arXiv:2603.13356v1 Announce Type: new Abstract: Standard approaches to Robust Reinforcement Learning assume that feedback sources are either globally trustworthy or globally adversarial. In this paper…
arXiv:2603.13359v1 Announce Type: new Abstract: Language models are commonly fine-tuned for safety alignment to refuse harmful prompts. One approach fine-tunes them to generate categorical refusal tok…
arXiv:2603.13372v1 Announce Type: new Abstract: The Abstraction and Reasoning Corpus (ARC-AGI) has become a key benchmark for fluid intelligence in AI. This survey presents the first cross-generation …
arXiv:2603.13378v1 Announce Type: new Abstract: In Arthur C. Clarke's 2010: Odyssey Two, HAL 9000's homicidal breakdown is diagnosed as a "Hofstadter-Mobius loop": a failure mode in which an autonomou…
arXiv:2603.13452v1 Announce Type: new Abstract: Research about bias in machine learning has mostly focused on outcome-oriented fairness metrics (e.g., equalized odds) and on a single protected categor…
arXiv:2603.13514v1 Announce Type: new Abstract: The Logic Theorist (LT), created by Allen Newell, J. C. Shaw, and Herbert Simon in 1955-1956, is widely regarded as the first artificial intelligence pr…
arXiv:2603.13545v1 Announce Type: new Abstract: AI development has a fiction dependency problem: models are built on massive corpora of modern fiction and desperately need more of it, yet they struggl…
arXiv:2603.13574v1 Announce Type: new Abstract: This paper presents a Probabilistic State Algebra as an extension of deterministic propositional logic, providing a computational framework for construc…
arXiv:2603.13594v1 Announce Type: new Abstract: Large language models are shifting from passive information providers to active agents intended for complex workflows. However, their deployment as reli…
arXiv:2603.13605v1 Announce Type: new Abstract: We introduce Orla, a library for constructing and running LLM-based agentic systems. Modern agentic applications consist of workflows that combine multi…
arXiv:2603.13612v1 Announce Type: new Abstract: Routing a query through an appropriate LLM is challenging, particularly when user preferences are expressed in natural language and model attributes are…
arXiv:2603.13304v1 Announce Type: new Abstract: Simulating many-body quantum systems on a classical computer is difficult due to the large number of degrees of freedom, causing the computational compl…
arXiv:2603.13322v1 Announce Type: new Abstract: While two-level systems (TLS) in superconducting qubits are known to introduce phonon-mediated energy dissipation channels, many-body TLS systems themse…
arXiv:2603.13442v1 Announce Type: new Abstract: We prove the non-existence of stabilizer absolutely maximally entangled states for systems of four six-dimensional qudits.
arXiv:2603.13454v1 Announce Type: new Abstract: Quantum control is an important logical primitive of quantum computing programs, and an important concept for equational reasoning in quantum graphical …
arXiv:2603.13460v1 Announce Type: new Abstract: Impacts from high-energy particles cause correlated errors in superconducting qubits by increasing the quasiparticle density in the vicinity of the Jose…
arXiv:2603.13462v1 Announce Type: new Abstract: The theory of open quantum systems addresses how coupling to external degrees of freedom modifies observables and quantum coherence, a situation central…
arXiv:2603.13477v1 Announce Type: new Abstract: We introduce a method for designing smooth single-qubit control pulses that implement a desired gate while suppressing the effect of unknown static erro…
arXiv:2603.13483v1 Announce Type: new Abstract: Continuous-variable quantum key distribution (CV-QKD) enables secure communication over standard telecom infrastructure, yet its scaling is stalled by b…
arXiv:2603.13485v1 Announce Type: new Abstract: The ability of modern quantum simulators--both digital and analogue--to generate large ensembles of single-shot projective "snapshots" has opened a data…
arXiv:2603.13492v1 Announce Type: new Abstract: We demonstrate an inter-species entangling Rydberg gate between rubidium (Rb) and cesium (Cs) atoms with fidelity $\mathcal F = 0.975\pm 0.002$. The two…