large language models

Agreement Between Large Language Models and Humans in Research Proposal Review - Data and Scripts

Agreement Between Large Language Models and Humans in Research Proposal Review — Data and Code This repository contains the data and code required to reproduce the analyses, statistical results, and figures presented in the associated manuscript. Files are organized by function and described below. All research proposa...

Large language model driven context aware adaptive beamforming for ultra dense 6G antenna array systems

Beyond similarity retrieval: governance fidelity, consistency, and minimality in long-term conversational memory

Conversational language model systems persist user constraints, preferences, identity, commitments, and assigned roles across turns. The dominant memory architecture stores this alongside ordinary episodic content in a vector index and retrieves the top-k items by similarity to the active query. We argue that this desi...

Using Artificial Intelligence to estimate how common alcohol references and alcohol-related brand references are among influencers on Instagram

Background: Young people spend hours on social media every day, where following influencers is the norm. Influencers post frequently about alcohol and alcohol brands and there has been a rise in influencer marketing. However, prevalence estimates rely on manual analyses of only a small number of posts. We used a large...

Fault Propagation and Risk Containment in Agentic AI Systems

Agentic artificial intelligence systems differ from conventional language model applications because they can reasonover a task, select tools, invoke external systems, observe resulting state, and continue acting toward a goal. Thisaction loop creates a security and reliability problem that cannot be adequately describ...

ns3-agent: Fostering Integrated Perception-Communication-Computing Research for Agentic AI Services via Cross-Platform Co-Simulations

The rapid proliferation of Generative AI (GenAI) has catalyzed the emergence of autonomous agentic AI services, spanning large language model (LLM) or vision-language model (VLM) based digital agents to vision-language-action (VLA) based embodied intelligence. Consequently, tokens and multimodal data streams have emerg...

ns3-GenAI: Integrating Large Language Models with ns3 for AI-Native Network Simulations

Existing ns3/AI bridges target numeric reinforcement learning (RL) pipelines and cannot handle the text-centric prompt/response exchange, structured output validation, and multi-node orchestration that large language models (LLMs) require. We introduce ns3-GenAI, an open framework that augments the ns3 shared-memory in...

SCDO Agent Ledger: On-Chain Identity, Work Attestation and Settlement for Autonomous AI Agents on a Sharded PoW Blockchain

Agentic AI systems composed of multiple large-language-model (LLM) agents need verifiable agent identity, tamper-evident records of completed work, and machine-to-machine settlement. Existing agent-economy designs concentrate on registration, discovery and reputation, while consortium-chain notarisation services anchor...

Engineering AI Containment: The Case for Deterministic Boundaries Over Behavioral Guardrails

Abstract: The safety of autonomous artificial intelligence systems relies on deterministic engineering boundaries superseding natural-language instructions or heuristic prompting. Documented containment failures in frontier models—including privilege escalation and strategic compliance—stem from architectural vulnerabi...

VisLLM-Map

We propose VisLLM-Map, a framework that integrates multimodal large language models with street-level imagery for intelligent map analysis.

Physical‑Intuition‑Driven Nonlinear Ignition‑Threshold Scaling and Shell‑Aspect‑Ratio Regime Separation for 1D ICF via TreeSHAP Explainable AI

Laser-driven inertial-confinement-fusion (ICF) achieves thermonuclear ignition via spherical capsule compression, yet high-fidelity multi-dimensional radiation-hydrodynamic simulations demand prohibitive computational resources. The ignition-threshold-factor (ITF) quantifies ignition margins to constrain target-design...

Replication package for "Same prompt, different LLM: what survives a model replacement in requirement rewriting"

Replication package for a double-anonymous conference submission on rewriting natural-language requirements with large language models. It contains the prompts, the pipeline, the raw experimental outputs and the analysis that reproduces every number and figure in the paper. No API credentials are needed to check the re...