1307 papers
This collection explores the diverse scientific landscape spanning from the elements of Cesium to the complex structures of Macromolecules. It captures a wide spectrum of inquiry, ranging from the behavior of specific atoms in physics and chemistry to the intricate study of large biological molecules that drive life processes. These papers reveal how fundamental components interact to shape materials, medicines, and the very building blocks of our world.
Gist.Science continuously monitors arXiv to bring you every new preprint in this rapidly evolving category. Our team processes each submission as soon as it is published, offering both plain-language explanations for general readers and detailed technical summaries for specialists. This dual approach ensures that groundbreaking discoveries are not just available, but truly understandable.
Below are the latest papers covering these essential topics, curated directly from the most recent uploads on arXiv.
AgonAlpha is an autonomous alpha-mining system that searches over frozen research artifacts using adversarial review and parallel budget allocation to generate high-quality, fully verifiable trading factors with proven prompt-to-expression provenance.
This paper introduces a cohomological framework demonstrating that local verification safeguards in agentic AI are structurally incapable of detecting non-transportable conclusions arising from harmonic evidence conflicts, and proposes the Ksetra procedure to identify and gate such global inconsistencies using cycle-based statistics.
This paper argues that the choice between enhancing individual agent intelligence versus improving institutional structures depends on diagnosing specific collective reasoning failures, as institutions are most effective when they repair how a group constructs and acts on public information but lose their advantage when stronger intelligence can directly perform those transformations or when institutional signals are uninformative.
This paper introduces the Continuity Kernel (CK), a transactional control plane that ensures the safe and authorized evolution of long-lived AI agents by decoupling untrusted state proposals from atomic activation, thereby preventing stale overwrites and privilege escalation through a formally verified protocol that guarantees an unbroken, auditable lineage of state changes.
This paper proposes AgenticTwin, a framework that integrates Large Language Models with digital twin systems to enhance anomaly detection and diagnosis in cyber-physical environments through grounded reasoning and natural language interaction, validated by a new benchmark on synthetic weather sensor data.
This paper argues that securing AI agents requires shifting from unreliable, agent-centric defenses to a networking-inspired architecture that combines deterministic enforcement mechanisms with semantic, context-aware policies to ensure robust privacy and security.
This paper demonstrates a fundamental asymmetry in behavioral inference where LLM agent motivations can be recovered with near-perfect accuracy, while their underlying belief systems remain largely opaque, plateauing at low accuracy rates that suggest an architectural or intrinsic limit to what observable actions reveal about internal values.
The paper introduces TRIBE, a domain-independent framework that predicts team performance early in tasks by analyzing communication patterns to identify behavioral "tribes," demonstrating that these patterns are more effective than traditional metrics and can be optimized for speed and accuracy compared to models like Llama.
This study demonstrates that Chinese frontier LLM agents exhibit significant lab-level divergence in cooperative equilibria, with internal variation exceeding the East-West gap, thereby refuting the notion of a monolithic "Chinese model" bloc.
The paper introduces XstrAI, a multi-agent framework that generates audience-aware explainable AI narratives by treating feature attributions as immutable evidence and employing specialized agents for planning, realization, and validation to ensure faithful, appropriate communication for diverse stakeholders like patients, clinicians, and data scientists.