large language models

MridAI: Autonomous Edge-to-Conversational IoT for Democratising Precision Agriculture via Neuro-Symbolic Telemetry

While sensor-guided precision agriculture improves water efficiency and curtails chemical run-off, adoption across smallholder farm land in the Global South remains under 1%. Commercial telemetry systems are constrained by high capital acquisition costs (>$300) and complex, dashboard-centric mobile applications that im...

Large Language Model-Enhanced Multi-Agent Reinforcement Learning for Autonomous Enterprise Workflow Orchestration via Graph Semantic Routing

# LeMARLA **Large Language Model-Enhanced Multi-Agent Reinforcement Learning for Autonomous Enterprise Workflow Orchestration via Graph Semantic Routing.** LeMARLA couples an LLM-driven task decomposition module, a heterogeneous graph attention routing module over tasks, employees and skills, and a CTDE multi-agent rei...

EuLLM — Open-source sovereign LLM platform

EuLLM is an open-source platform for creating, distributing, and running sovereign EU-compliant Large Language Models, designed for verticalization across domains, languages, and brands while ensuring AI Act compliance. The platform consists of three components: Engine — a Rust-based inference runtime built on top of l...

Data poisoning in LLM multiagent societies: Social proof drives collective decision failure in financial deliberation

This work studies data poisoning in peer‐to‐peer agent societies using Moltbook, a deliberation test bed modeled after the agent‐only social platform, and shows that the collapse is structural rather than model‐specific.

ToshLLM: local LLM inference on Intel Macs with AMD GPUs

A native SwiftUI application that runs large language models locally on Intel Macs with AMD GPUs, a configuration mainstream inference stacks leave unsupported or incorrect. Beyond packaging, it contributes original work to the Metal backend of llama.cpp: ToshGEMM, a manually tiled matrix multiply that replaces the sim...

Generative Artificial Intelligence and Large Language Models as Methodological Support Tools in Health Research: A Bibliometric Analysis

Semantic-Conditioned Spectral Fusion for Label-Efficient Multispectral Adaptation of Frozen Remote-Sensing Vision–Language Models

Remote-sensing vision–language models (RS-VLMs) yield transferable, text-alignable representations, yet are pre-trained on three-band RGB imagery and therefore cannot exploit the red-edge, near-infrared and short-wave-infrared bands that carry much of the discriminative signal in multispectral data. Existing adaptation...

Semantic Spacetime, Semantic Gravity, and the Law of Attention

A Framework for Meaning Mass, Contextual Curvature, Attention Allocation, and Evolvable Semantic Systems Description This work develops an integrated theoretical framework for understanding how meaning, attention, and context interact across cognitive, artificial, cultural, and civilizational systems. The framework com...

An Availability-Oriented, Multi-Provider Architecture for Generative AI Services: A Fault-Injection Case Study

Applications built on third-party Generative AI APIs inherit the unreliability of those APIs. Providers rate-limit requests, exhaust free-tier quotas, deprecate models, and return server errors, any of which can break a dependent application. This paper presents an availability-oriented architecture that does not depen...

Reproducibility Artifacts for an Integrated Blockchain and Large Language Model Decision Support System for Organ Donation and Transplantation Workflows

This release adds reproducibility support for the revised evaluation: separates strict output completion, classification performance conditional on valid output, and failure-penalized end-to-end performance; adds a 20-scenario post hoc robustness suite covering safeguard boundary conditions, invalid model outputs, and...

Measuring an i+1 language tutor from the outside: one robust effect, one language-dependent null, and one failed conformance bar

Krashen's comprehensible-input hypothesis holds that acquisition happens when input sits just beyond the learner's current competence - the so-called i+1 condition. Large language models make it possible, for the first time, to generate such input on demand rather than select it from a fixed corpus. We report three res...

Auditable AI-Assisted Scientific Discovery: From Noncausal Processes to Quantum Measurement Rigidity

Large language models can accelerate scientific exploration, but generated arguments are not evidence. We report a human–AI research workflow in which model outputs are treated as conjectures and claims are admitted only after proof or deterministic, independently checked computation. The workflow is illustrated by a c...