Related papers: SENTINEL: A Multi-Level Formal Framework for Safet…

Large Language Models (LLMs) are increasingly used for decision making in embodied agents, yet existing safety evaluations often rely on coarse success rates and domain-specific setups, making it difficult to diagnose why and where these…

Computer-using agents powered by Vision-Language Models (VLMs) have demonstrated human-like capabilities in operating digital environments like mobile platforms. While these agents hold great promise for advancing digital automation, their…

Large Language Models (LLMs) have been increasingly integrated into computer-use agents, which can autonomously operate tools on a user's computer to accomplish complex tasks. However, due to the inherently unstable and unpredictable nature…

Embodied agents operating in the physical world must make decisions that are not only effective but also safe, spatially coherent, and grounded in context. While recent advances in large multimodal models (LMMs) have shown promising…

We present Stratified Metric Temporal Logic (SMTL), a novel formalism for specifying and verifying properties of complex cyber-physical systems that exhibit behaviors across multiple temporal and abstraction scales. SMTL extends existing…

This paper proposes a novel architectural framework aimed at enhancing security and reliability in multi-agent systems (MAS). A central component of this framework is a network of Sentinel Agents, functioning as a distributed security layer…

Cyberattacks pose a serious threat to modern sociotechnical systems, often resulting in severe technical and societal consequences. Attackers commonly target systems and infrastructure through methods such as malware, ransomware, or other…

LLM-based agents can execute actions that are syntactically valid, user-sanctioned, and semantically appropriate, yet still violate organizational policy because the facts needed for correct policy judgment are hidden at decision time. We…

Large Language Models (LLMs) exhibit substantial promise in enhancing task-planning capabilities within embodied agents due to their advanced reasoning and comprehension. However, the systemic safety of these agents remains an underexplored…

Safety risks arise as large language model-based agents solve complex tasks with tools, multi-step plans, and inter-agent messages. However, deployer-written policies in natural language are ambiguous and context dependent, so they map…

Despite remarkable advances in Large Language Model capabilities, tool retrieval for agent-based systems remains fundamentally limited by reliance on semantic similarity, which fails to capture functional viability. Current methods often…

With the integration of large language models (LLMs), embodied agents have strong capabilities to understand and plan complicated natural language instructions. However, a foreseeable issue is that those embodied agents can also flawlessly…

Embodied agents powered by large language models (LLMs) inherit advanced planning capabilities; however, their direct interaction with the physical world exposes them to safety vulnerabilities. In this work, we identify four key reasoning…

Many simulation based Bounded Model Checking approaches to System Level Formal Verification (SLFV) have been devised. Typically such approaches exploit the capability of simulators to save computation time by saving and restoring the state…

As large language models evolve from conversational assistants to autonomous agents, ensuring trustworthiness requires a fundamental shift from post-hoc evaluation to real-time action verification. Current frameworks like AgentBench…

As LLM-based agents increasingly operate in high-stakes domains with real-world consequences, ensuring their behavioral safety becomes paramount. The dominant oversight paradigm, LLM-as-a-Judge, faces a fundamental dilemma: how can…

A formal but intuitive framework is introduced to bridge the gap between data obtained from empirical studies and that generated by agent-based models. This is based on three key tenets. Firstly, a simulation can be given multiple formal…

We identify and formalize a novel security risk: Context-Fragmented Violations (CFVs) - a class of policy breaches where individual agent actions appear locally safe and reasonable, yet collectively violate organizational policies because…

Embodied AI depends on interactive 3D environments that support meaningful activities for diverse users, yet assessing their functional affordances remains a core challenge. We introduce SceneTeract, a framework that verifies 3D scene…

With the increasing prevalence of multimodal content on social media, sentiment analysis faces significant challenges in effectively processing heterogeneous data and recognizing multi-label emotions. Existing methods often lack effective…