large language models

CogniGraph: Governed Graph-of-Agents Reasoning over Knowledge Graph Topologies with Semantic SHACL Validation and Constrained F1 Evaluation

Abstract. Multi-agent large language model (LLM) systems are increasingly deployed for regulatoryand high-stakes reasoning, yet none of the prevailing flat-topology frameworks—AutoGen, CrewAI,LangGraph—enforce semantic governance over what each agent may say, in whose name, and withinwhich scope. The result is what we...

Pattern Pressure, Accuracy Drift, and False User-State Attribution

Large-language model outputs are often described as "accurate" or "inaccurate" as if a single axis were being measured. This paper argues that the umbrella word accurate collapses at least four distinct fits: fit to user intent, fit to measured fact, fit to source provenance, and fit to the local conversational pattern...

Benchmarking the safety of large language models for robotic health attendant control

Abstract Large language models (LLMs) are increasingly considered for deployment as the control component of robotic health attendants (RHAs), yet their safety in this context remains poorly characterized. We introduce a dataset of 270 harmful instructions spanning nine prohibited behaviour categories grounded in the A...

EMPIRICAL COMPARISON OF AGENT COMMUNICATION PROTOCOLS FOR TASK ORCHESTRATION

Context. The problem of comparative evaluation of communication protocols for task orchestration by large language model (LLM) agents is considered. The object of study is the process of interaction between LLM agents and external tools, as well as between autonomous LLM agents, during task orchestration.Objective. The...

Real Faults in Model Context Protocol (MCP) Software: a Comprehensive Taxonomy

The rapid adoption of foundation models has significantly expanded the capabilities of software systems, enabling them to perform complex language, reasoning, and interaction tasks that were previously difficult to automate. However, this progress has also introduced novel challenges that were largely absent in previou...

Epistemic-Boundary Misclassification in Large-Language Models: A Bounded Behavioral Hypothesis and Test Design

The proposed phenomenon is a discontinuity, not merely a bad answer. A conversation establishes a bounded analytical mode, a mixed-domain turn occurs, and the next response no longer preserves the prior mode even though the task has not changed. That sequence has been reported from the author's workflow. This version d...

On the Robustness of Vision-Language Models in Zero-Shot Privacy Classification

Seamful Design Considerations for Human-in-the-Loop Digital Phenotyping of Mental Health

Digital Phenotyping of Mental Health (DPMH) through passive sensing is a promising approach for personal health informatics and digital wellbeing. Its appeal lies in unobtrusiveness, making it appear seamless. However, this very quality leads users to find it impersonal, untrustworthy, and disengaging. To counteract ch...

AI-based procedure for extracting spatial and temporal information on rainfall-induced landslides from textual sources

Abstract Comprehensive landslide catalogues require accurate and reproducible spatial and temporal information, yet manual extraction from textual sources is time-consuming and affected by inter- and intra-operator variability. We present AIDE4LAND (Artificial Intelligence-based procedure for Data Extraction for LANDsl...

P192 REPRODUCIBILITY OF LARGE LANGUAGE MODELS’ OUTPUTS IN STRUCTURED CARDIOLOGY CLINICAL DECISION-MAKING

The Next Theory of Evolution

New evidence from large language models and animal communication challenges human linguistic exceptionalism. Drawing on historical parallels between linguistics and evolutionary biology, this comment argues that new evidence from non-human linguistic behavior could transform humanity's relationship with the natural wor...

P186 POINT-OF-CARE AI: CAN LARGE LANGUAGE MODELS DELIVER REAL-TIME GUIDELINE ANSWERS FOR CLINICIANS? A FIVE-MODEL COMPARISON USING CCS GUIDELINES