Related papers: Toward a Mapping of Capability and Skill Models us…

This works considers challenges of building and usage a formal knowledge base (model), which unites the ATT&CK, CAPEC, CWE, CVE security enumerations. The proposed model can be used to learn relations between attack techniques, attack…

Current AI agents can flexibly invoke tools and execute complex tasks, yet their long-term advancement is hindered by the lack of systematic accumulation and transfer of skills. Without a unified mechanism for skill consolidation, agents…

Embodied manipulation is a fundamental ability in the realm of embodied artificial intelligence. Although current embodied manipulation models show certain generalizations in specific settings, they struggle in new environments and tasks…

Multimodal agents can now tackle complex reasoning tasks with diverse tools, yet they still suffer from inefficient tool use and inflexible orchestration in open-ended settings. A central challenge is enabling such agents to continually…

Supervisory control design of cyber-physical systems has many challenges. Model-based systems engineering can address these, with solutions originating from various disciplines. We discuss several tools, each state-of-the-art in its own…

One important challenge for a set of agents to achieve more efficient collaboration is for these agents to maintain proper models of each other. An important aspect of these models of other agents is that they are often partial and…

Multi-task multi-agent reinforcement learning (MT-MARL) has recently gained attention for its potential to enhance MARL's adaptability across multiple tasks. However, it is challenging for existing multi-task learning methods to handle…

We investigate whether post-trained capabilities can be transferred across models without retraining, with a focus on transfer across different model scales. We propose the Master Key Hypothesis, which states that model capabilities…

Skill composition is the ability to combine previously learned skills to solve new tasks. As neural networks acquire increasingly complex skills during their pretraining, it is not clear how successfully they can compose them. In this…

Large language model (LLM)-based AI agents are increasingly deployed in manufacturing environments for analytics, quality management, and decision support. These agents demonstrate statistical fluency with domain terminology but lack…

Human intelligence is able to first learn some basic skills for solving basic problems and then assemble such basic skills into complex skills for solving complex or new problems. For example, the basic skills "dig hole," "put tree,"…

Simulations offer opportunities in the examination of manufacturing processes. They represent various aspects of the production process and the associated production systems. However, often a single simulation does not suffice to provide a…

Agentic AI systems - systems that can pursue goals through multi-step planning and tool-mediated action with limited direct supervision - are moving from experimental prototypes to enterprise deployments. This transition introduces tensions…

Attack Trees (AT) are a popular formalism for security analysis. They are meant to display an attacker's goal decomposed into attack steps needed to achieve it and compute certain security metrics (e.g., attack cost, probability, and…

Enterprise adoption of Large Language Models (LLMs) is constrained by hallucination, domain drift, and the inability to enforce regulatory compliance at the reasoning level. We present a neurosymbolic architecture implemented within the…

The reuse of atomistic simulation data is often limited by heterogeneous formats, incomplete metadata, and a lack of standardized representations of workflows and provenance. Here we present an ontology-based infrastructure for representing…

We distinguished between the expected and actual profit of a firm. We proposed that, beyond maximizing profit, a firm's goal also encompasses minimizing the gap between expected and actual profit. Firms strive to enhance their capability to…

Skill libraries enable large language model agents to reuse experience from past interactions, but most existing libraries store skills as isolated entries and retrieve them only by semantic similarity. This leads to two key challenges for…

Designing neural network architectures is a task that lies somewhere between science and art. For a given task, some architectures are eventually preferred over others, based on a mix of intuition, experience, experimentation and luck. For…

For improving flexibility and robustness of the engineering of automated production systems (aPS) in case of extending, reducing or modifying parts, several approaches propose an encapsulation and clustering of related functions, e.g. from…