This collection explores the dynamic frontier of research spanning from carbon nanotubes to organic semiconductors, where chemists and materials scientists are redefining what is possible at the atomic scale. These studies investigate how molecular structures interact to create new technologies, often bridging the gap between theoretical chemistry and real-world applications like flexible electronics or advanced energy storage.

Every new preprint in this category arrives directly from arXiv, and Gist.Science immediately processes each submission to make the findings accessible to everyone. We provide both clear, plain-language overviews for general readers and detailed technical summaries for specialists, ensuring that complex discoveries in this rapidly evolving field are easy to understand and verify. Below are the latest papers exploring these groundbreaking materials and their transformative potential.

Contextual Memory Virtualisation: DAG-Based State Management and Structurally Lossless Trimming for LLM Agents

This paper proposes Contextual Memory Virtualisation (CMV), a system that models LLM session history as a version-controlled Directed Acyclic Graph (DAG) to enable state reuse across parallel sessions and employs a three-pass algorithm to structurally losslessly trim mechanical overhead, achieving significant token reduction while preserving all user and assistant content verbatim.

Cosmo Santoni2026-02-27🤖 cs.AI

AgentCgroup: Understanding and Controlling OS Resources of AI Agents

This paper presents AgentCgroup, an open-source, eBPF-based resource controller that addresses the unique, unpredictable, and tool-call-driven resource dynamics of multi-tenant AI agents by introducing intent-driven, hierarchical cgroup policies to overcome the granularity, responsiveness, and adaptability mismatches of existing OS controls.

Yusheng Zheng, Jiakun Fan, Quanzhi Fu, Yiwei Yang, Wei Zhang, Andi Quinn2026-02-24🤖 cs.AI

SPECTRE: A Hybrid System for an Adaptative and Optimised Cyber Threats Detection, Response and Investigation in Volatile Memory

This paper introduces SPECTRE, a modular cyber incident response system that leverages memory forensics, emulation, and integrated threat intelligence to detect, visualize, and investigate sophisticated file-less malware while ensuring compatibility with existing DFIR workflows.

Arslan Tariq Syed, Mohamed Chahine Ghanem, Elhadj Benkhelifa, Fauzia Idrees Abro2026-02-23💻 cs