Related papers: Counterfactual-based Agent Influence Ranker for Ag…
Agentic systems are becoming more capable: agents define strategies, take actions, and interact with different environments. This autonomy poses serious challenges for overseeing and assessing agent behavior. Most current tools are limited,…
AI-RAN consolidates AI services and Radio Access Network (RAN) functions onto a unified, GPU-accelerated infrastructure at the network edge. However, compute sharing between real-time RAN functions and highly heterogeneous AI services…
The advancement of large language model (LLM) based agents has shifted AI evaluation from single-turn response assessment to multi-step task completion in interactive environments. We present an empirical study evaluating frontier AI models…
We present an agent-driven approach to the construction of parameter inference pipelines for scientific data analysis. Our method leverages a multi-agent system, Cmbagent (the analysis system of the AI scientist Denario), in which…
Agentic AI marks an important transition from single-step generative models to systems capable of reasoning, planning, acting, and adapting over long-lasting tasks. By integrating memory, tool use, and iterative decision cycles, these…
Large language models (LLMs) deployed as agents introduce significant safety risks in clinical settings due to their potential for error and single points of failure. We introduce Tiered Agentic Oversight (TAO), a hierarchical multi-agent…
Generative artificial intelligence (AI) agents are increasingly embedded in collaborative learning environments, yet their impact on the processes of argumentative knowledge construction remains insufficiently understood. Emerging…
Large Language Models (LLMs), when paired with prompt-based tasks, have significantly reduced data annotation costs and reliance on human annotators. However, evaluating the quality of their annotations remains challenging in dynamic,…
Explainable AI (XAI) research has experienced substantial growth in recent years. Existing XAI methods, however, have been criticized for being technical and expert-oriented, motivating the development of more interpretable and accessible…
LLM-based agents have emerged as transformative tools capable of executing complex tasks through iterative planning and action, achieving significant advancements in understanding and addressing user needs. Yet, their effectiveness remains…
Action Quality Assessment (AQA) predicts fine-grained execution scores from action videos and is widely applied in sports, rehabilitation, and skill evaluation. Long-term AQA, as in figure skating or rhythmic gymnastics, is especially…
Contemporary machine learning paradigm excels in statistical data analysis, solving problems that classical AI couldn't. However, it faces key limitations, such as a lack of integration with planning, incomprehensible internal structure,…
Agentic AI shifts LLM serving from isolated prompt-generation requests to stateful, multi-turn executions that repeatedly invoke the model, call tools, and grow context over time. This paper characterizes ReAct-style agents from both the…
Autonomous multi-agent AI systems are poised to transform various industries, particularly software development and knowledge work. Understanding current perceptions among professionals is crucial for anticipating adoption challenges,…
Understanding decision-making in multi-AI-agent frameworks is crucial for analyzing strategic interactions in network-effect-driven contexts. This study investigates how AI agents navigate network-effect games, where individual payoffs…
Large-language-model (LLM)-based AI agents have recently showcased impressive versatility by employing dynamic reasoning, an adaptive, multi-step process that coordinates with external tools. This shift from static, single-turn inference to…
Continual learning enables AI models to learn new data sequentially without retraining in real-world scenarios. Most existing methods assume the training data are balanced, aiming to reduce the catastrophic forgetting problem that models…
Recent research has shown that LLM performance on reasoning tasks can be enhanced by scaling test-time compute. One promising approach, particularly with decomposable problems, involves arranging intermediate solutions as a graph on which…
Counterfactual explanations, which deal with "why not?" scenarios, can provide insightful explanations to an AI agent's behavior. In this work, we focus on generating counterfactual explanations for deep reinforcement learning (RL) agents…
Large language model-based multi-agent systems have shown great abilities across various tasks due to the collaboration of expert agents, each focusing on a specific domain. However, the impact of clumsy or even malicious agents--those who…