相关论文: Building a Foundational Guardrail for General Agen…

Unmanned Aerial Vehicles (UAVs) are increasingly used in defense, surveillance, and disaster response, yet most systems still operate at SAE Level 2 to 3 autonomy. Their dependence on rule-based control and narrow AI limits adaptability in…

Large foundation models enable powerful reasoning for autonomous systems, but mapping semantic intent to reliable real-time control remains challenging. Existing approaches either (i) let Large Language Models (LLMs) generate trajectories…

The proliferation of autonomous AI agents capable of executing real-world actions - filesystem operations, API calls, database modifications, financial transactions - introduces a class of safety risk not addressed by existing…

We present GuardReasoner-Omni, a reasoning-based guardrail model designed to moderate text, image, video, and audio data. First, we construct a comprehensive training corpus comprising 181k samples spanning these four modalities. Our…

Unmanned aerial vehicular network (UAVN) is envisioned to provide flexible connectivity, wide-area coverage, and low-latency services in dynamic environments. From an agentic artificial intelligence (Agentic AI) perspective, UAVNs naturally…

Generalizable manipulation involving cross-type object interactions is a critical yet challenging capability in robotics. To reliably accomplish such tasks, robots must address two fundamental challenges: "where to manipulate" (contact…

With the rapid proliferation of digital media, the need for efficient and transparent safeguards against unsafe content is more critical than ever. Traditional image guardrail models, constrained by predefined categories, often misclassify…

Reinforcement learning (RL) algorithms can achieve state-of-the-art performance in decision-making and continuous control tasks. However, applying RL algorithms on safety-critical systems still needs to be well justified due to the…

LLM-based agents are deployed in safety-critical applications, yet current guardrail systems fail to prevent violations of temporal safety policies, requirements that govern the ordering and sequencing of agent actions. For instance, agents…

The increasing complexity of Beyond 5G and 6G networks necessitates new paradigms for autonomy and assur- ance. Traditional O-RAN control loops rely heavily on RIC- based orchestration, which centralizes intelligence and exposes the system…

The rapid advancement of large language models (LLMs) has increased the need for guardrail models to ensure responsible use, particularly in detecting unsafe and illegal content. While substantial safety data exist in English, multilingual…

The use of reward functions to structure AI learning and decision making is core to the current reinforcement learning paradigm; however, without careful design of reward functions, agents can learn to solve problems in ways that may be…

Data scarcity and confidentiality in finance often impede model development and robust testing. This paper presents a unified multi-criteria evaluation framework for synthetic financial data and applies it to three representative generative…

We consider joint trajectory generation and tracking control for under-actuated robotic systems. A common solution is to use a layered control architecture, where the top layer uses a simplified model of system dynamics for trajectory…

We address the problem of data scarcity in harmful text classification for guardrailing applications and introduce GRAID (Geometric and Reflective AI-Driven Data Augmentation), a novel pipeline that leverages Large Language Models (LLMs)…

Retrieval-Augmented Generation (RAG) enables large language models (LLMs) to access external knowledge sources, but the effectiveness of RAG relies on the coordination between the retriever and the generator. Since these components are…

AI-based systems, currently driven largely by LLMs and tool-using agentic harnesses, are increasingly discussed as a possible threat to software engineering. Foundation models get stronger, agents can plan and act across multiple steps, and…

To cope with the large contexts that long-horizon LLM agents produce, modern frameworks increasingly rely on compaction -- invoking an LLM to rewrite the accumulated trajectory into a shorter summary that the agent resumes from. Today,…

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…

The Agentic Paradigm faces a significant Software Engineering Absence, yielding Agentic systems commonly lacking robustness, observability, and evolvability. To address these deficiencies, we propose a principled engineering framework…