The BEAMS initiative establishes comprehensive benchmarks and evaluates AI tools for modeling and simulation, finding that current AI tools excel at qualitative discussion tasks but struggle with comp…

The paper presents an approach to automatically generate a large number of diverse and complex cybersecurity scenarios that model enterprise IT systems for training purposes.

LOTUSim is an open-source, real-time maritime simulator supporting multi-user interaction for coordinated naval-style operations, featuring real-time interactive performance, scalability, and an Ekman…

This paper analyzes tool-calling in LLM agents, demonstrating that evaluation results are highly sensitive to implementation details and proposing new techniques to significantly improve the efficienc…

The paper introduces AbaqusAgent, a multi-AI-agent framework that uses large language models to translate natural language instructions into executable Finite Element Analysis (FEA) simulations using…

The paper introduces a new security benchmark and framework to defend LLM agents against 'cognitive poisoning,' where malicious tools build trust through benign feedback before executing a harmful fin…

This paper introduces StructureClaw, an artifact-centered workbench for evaluating structural-engineering agents, and presents StructureClaw-Bench, an executable benchmark for testing these agents.

The ACTING platform addresses the need for interoperable cyber-range training by providing a structured language (EDL-FG) for scenario description and automated evaluation mechanisms for complex, mult…

This paper synthesizes expert knowledge from a workshop to provide a comprehensive framework and best-practice guidelines for developing high-quality reinforcement learning environments for autonomous…

The paper proposes a semi-automated framework that integrates network topology and vulnerability data to generate and analyze multi-step attack graphs in Industrial Control Systems, demonstrated using…

This paper introduces a high-fidelity, integrated hardware-software simulator for LPDDR5X-PIM, enabling precise evaluation of system performance and energy efficiency.

The paper proposes a trust schema and verification framework to ensure that agent skills, which augment LLMs, are rigorously verified before deployment, thereby making human-in-the-loop oversight scal…

The paper introduces SafeAudit, a meta-audit framework that systematically enumerates test cases and uses a quantitative metric to uncover significant residual unsafe behaviors in LLM agents that exis…

This paper presents Weave, a deterministic method to convert SPICE netlists into LTspice schematics with guaranteed connectivity preservation.

The paper proposes HiSME, a lightweight hierarchical skill meta-evolving solution that jointly optimizes skills and the skill evolving strategy by learning meta-skills from task execution traces, lead…

The paper introduces TRUSTDESC, a novel framework that prevents tool poisoning attacks in LLM applications by automatically generating highly accurate and trusted tool descriptions directly from the t…

This paper proposes an automated method to generate complete PDDL planning problems directly from Asset Administration Shell (AAS) capability models, eliminating the need for specialized planning expe…

This paper presents TypoNet, a system that constructs and validates a symbolic model of a production-scale WAN from network artifacts using large language models for translation and a solver for relia…

The paper introduces LITE-SOC, a lightweight, web-based simulator designed to provide a practical, accessible alternative for teaching cybersecurity SOC workflows without requiring complex, expensive…

The paper introduces DreamForge-World 0.1 Preview, a low-compute real-time interactive world simulation system using a residual action pathway and open video backbones.