Related papers: Audit the Whisper: Detecting Steganographic Collus…

The rapid proliferation of large language model (LLM)-based agentic systems raises critical concerns regarding digital sovereignty, environmental sustainability, regulatory compliance, and ethical alignment. Whilst existing frameworks…

Large language models (LLMs) can serve as the semantic-matching engine of a content-based publish/subscribe broker for agentic AI across the edge-cloud computing continuum, bridging the vocabulary and modality gaps that defeat keyword and…

LLM agents in markets present algorithmic collusion risks. While prior work shows LLM agents reach supracompetitive prices through tacit coordination, existing research focuses on hand-crafted prompts. The emerging paradigm of prompt…

Multi-agent debates have been introduced to improve the accuracy of Large Language Models (LLMs) by having multiple agents discuss solutions to a problem over several rounds of debate. However, models often generate incorrect yet…

We present ActuBench, a multi-agent LLM pipeline for the automated generation and evaluation of advanced actuarial assessment items aligned with the International Actuarial Association (IAA) Education Syllabus. The pipeline separates four…

In our research, we introduce a new concept called "LLM Augmented Pentesting" demonstrated with a tool named "Pentest Copilot," that revolutionizes the field of ethical hacking by integrating Large Language Models (LLMs) into penetration…

When users seek social support from chatbots, they disclose their situation gradually, yet most evaluations of supportive LLMs rely on single-turn, fully specified prompts. We introduce a multi-turn simulation framework that closes this…

Large language models (LLMs) are increasingly used to translate natural-language optimization problems into mathematical formulations and solver code, but matching the reference objective value is not a reliable test of correctness: an…

Large language models (LLMs) represent a major advance in artificial intelligence (AI) research. However, the widespread use of LLMs is also coupled with significant ethical and social challenges. Previous research has pointed towards…

Large language models (LLMs) are increasingly grounded in sensor data to perceive and reason about human physiology and the physical world. However, accurately interpreting heterogeneous multimodal sensor data remains a fundamental…

Large language models are becoming increasingly pervasive and ubiquitous in society via deployment in sociotechnical systems. Yet these language models, be it for classification or generation, have been shown to be biased and behave…

In recent years, multi-agent frameworks powered by large language models (LLMs) have advanced rapidly. Despite this progress, there is still a notable absence of benchmark datasets specifically tailored to evaluate their performance. To…

Large language models are increasingly proposed as autonomous agents for high-stakes public workflows, yet we lack systematic evidence about whether they would follow institutional rules when granted authority. We present evidence that…

The deployment of large language models (LLMs) in production environments has created an urgent need for observability systems that span the full stack -- from model internals to GPU kernels. Yet existing monitoring approaches address…

Prompt specifications for multi-agent large language model (LLM) systems carry data contracts and integration logic across many interdependent files but are rarely subjected to structured-inspection rigor. This paper reports a single-system…

Domain-specific speech remains a persistent challenge for automatic speech recognition (ASR), even for state-of-the-art systems like OpenAI's Whisper. We introduce Whisper: Courtside Edition, a novel multi-agent large language model (LLM)…

The INTERSPEECH 2025 Challenge on Multilingual Conversational Speech Language Models (MLC-SLM) promotes multilingual conversational ASR with large language models (LLMs). Our previous SHNU-mASR system adopted a competitive…

Multi-agent LLM frameworks are widely used to accelerate the development of agent systems powered by large language models (LLMs). These frameworks impose distinct architectural structures that govern how agents interact, store information,…

Alignment audits aim to robustly identify hidden goals from strategic, situationally aware misaligned models. Despite this threat model, existing auditing methods have not been systematically stress-tested against deception strategies. We…

As AI agents powered by large language models (LLMs) increasingly use external tools for high-stakes decisions, a critical reliability question arises: how do errors propagate across sequential tool calls? We introduce the first theoretical…