Related papers: Can Current Agents Close the Discovery-to-Applicat…
Multi-agent debate system (MAD) imitating the process of human discussion in pursuit of truth, aims to align the correct cognition of different agents for the optimal solution. It is challenging to make various agents perform right and…
Deep hierarchical reinforcement learning has gained a lot of attention in recent years due to its ability to produce state-of-the-art results in challenging environments where non-hierarchical frameworks fail to learn useful policies.…
With the widespread adoption of Large Language Models (LLMs) such as GitHub Copilot and ChatGPT, developers increasingly rely on AI-assisted tools to support code generation. While LLMs can generate syntactically correct solutions for…
With increasing numbers of vulnerabilities exposed on the internet, autonomous penetration testing (pentesting) has emerged as a promising research area. Reinforcement learning (RL) is a natural fit for studying this topic. However, two key…
Large language models (LLMs) have evolved into agentic systems capable of autonomous tool use and multi-step reasoning for complex problem-solving. However, post-training approaches building upon general-purpose foundation models…
While learning in an unknown Markov Decision Process (MDP), an agent should trade off exploration to discover new information about the MDP, and exploitation of the current knowledge to maximize the reward. Although the agent will…
In this study, we explored the progression trajectories of artificial intelligence (AI) systems through the lens of complexity theory. We challenged the conventional linear and exponential projections of AI advancement toward Artificial…
While large language models (LLMs) excel at factual recall, the real challenge lies in knowledge application. A gap persists between their ability to answer complex questions and their effectiveness in performing tasks that require that…
Create an idea, prototype it, evaluate if users like it, then learn. It is the circle of business. If AI can operate in all parts of the circle, it will enable rapid iteration and learning speeds for businesses. Experiment platforms that…
Large language models are increasingly expected to serve as general-purpose agents that interact with external, stateful tool environments. The Model Context Protocol (MCP) and broader agent skills offer a unified interface for connecting…
Large language models are increasingly deployed in multi-agent systems to overcome context limitations by distributing information across agents. Yet whether agents can reliably compute with distributed information, rather than merely…
With the increasing maturity and scale of quantum hardware and its integration into HPC systems, there is a need to develop robust techniques for developing, characterizing, and benchmarking quantum-HPC applications and middleware systems.…
AI agent research spans a wide spectrum: from RL agents that learn from scratch to foundation model agents that leverage pre-trained knowledge, yet no unified benchmark enables fair comparison across these approaches. We present Agentick, a…
Pre-training Reinforcement Learning agents in a task-agnostic manner has shown promising results. However, previous works still struggle in learning and discovering meaningful skills in high-dimensional state-spaces, such as pixel-spaces.…
Understanding the mechanisms behind decisions taken by large foundation models in sequential decision making tasks is critical to ensuring that such systems operate transparently and safely. In this work, we perform exploratory analysis on…
Agentic AI systems are entering software engineering workflows, yet empirical evidence on how industrial organizations actually adopt them remains sparse. We present a qualitative interview study with sixteen practitioners across twelve…
Teaching programming to K-12 students has become essential. In this context, App Inventor is a popular block-based programming environment used by a wide audience, from K-12 to higher education, including end-users to create mobile…
This chapter bridges technical analysis and organizational preparedness by tracing the path from layered failure modes to reliability awareness in generative and agentic AI systems. We first introduce an 11-layer failure stack, a structured…
Multi-agent systems powered by large language models (LLMs) are transforming enterprise automation, yet systematic evaluation methodologies for assessing tool-use reliability remain underdeveloped. We introduce a comprehensive diagnostic…
This article presents the first systematic comparative survey of how public bodies, international organisations, national regulators, and the private sector define agentic artificial intelligence, identifying the technical inaccuracies…