Related papers: Bounded Autonomy for Enterprise AI: Typed Action C…
AI agents that build user interfaces on the fly assembling buttons, forms, and data displays from structured protocol payloads are becoming common in production systems. The trouble is that a payload can pass every schema check and still…
General Alignment has improved average-case helpfulness and safety, but current alignment practice still rewards confident, single-turn responses. The problem is not only that models fail on edge cases; it is that current evaluation makes…
Trustworthy capability evaluations are crucial for ensuring the safety of AI systems, and are becoming a key component of AI regulation. However, the developers of an AI system, or the AI system itself, may have incentives for evaluations…
AI agents increasingly act through external tools: they query databases, execute shell commands, read and write files, and send network requests. Yet in most current agent stacks, model-generated tool calls are handed to the execution layer…
Artificial intelligence (AI) copilots are increasingly integrated into enterprise cybersecurity platforms to assist analysts in threat detection, triage, and remediation. However, the effectiveness of these systems depends not only on the…
Recent evidence suggests that frontier AI systems can exhibit agentic misalignment, generating and executing harmful actions derived from internally constructed goals, even without explicit user requests. Existing mitigation methods, such…
The use of Large Language Models (LLM) by providers of cybersecurity and digital infrastructures of all kinds is an ongoing development. It is suggested and on an experimental basis used to write the code for the systems, and potentially…
AI Accelerator (AIA) are specialized hardware e.g., Tensor Processing Unit (TPU), that enable optimal and efficient execution of AI applications and on-device inference. The growing demand for AI applications has led to the widespread…
Human-centred systems require an understanding of human actions in the physical world. Temporally extended sequences of actions are intentional and structured, yet existing methods for recognising what actions are performed often do not…
As generative AI enters enterprise workflows, ensuring compliance with legal, ethical, and reputational standards becomes a pressing challenge. In beauty tech, where biometric and personal data are central, traditional reviews are often…
The increasing complexity of user demands necessitates automation frameworks that can reliably translate open-ended instructions into robust, multi-step workflows. Current monolithic agent architectures often struggle with the challenges of…
Leading language model (LM) providers like OpenAI and Anthropic allow customers to fine-tune frontier LMs for specific use cases. To prevent abuse, these providers apply filters to block fine-tuning on overtly harmful data. In this setting,…
System Instructions in Large Language Models (LLMs) are commonly used to enforce safety policies, define agent behavior, and protect sensitive operational context in agentic AI applications. These instructions may contain sensitive…
LLM agents increasingly run inside execution harnesses that dispatch tools, allocate resources, and route messages between specialized components. However, a harness can return a correct, benign answer over a trajectory that accesses…
As autonomous and agentic AI systems scale in robotic and human-machine environments, managing hallucination and persistent but unjustified action remains an open challenge. Rather than attributing these failures solely to model or…
We present an embodied AI system which receives open-ended natural language instructions from a human, and controls two arms to collaboratively accomplish potentially long-horizon tasks over a large workspace. Our system is modular: it…
Large Language Models (LLMs) have evolved into AI agents that interact with external tools and environments to perform complex tasks. The Model Context Protocol (MCP) has become the de facto standard for connecting agents with such…
Chat-based language models are designed to be helpful, yet they should not comply with every user request. While most existing work primarily focuses on refusal of "unsafe" queries, we posit that the scope of noncompliance should be…
Enterprise AI is shifting from copilots to autonomous agents capable of executing workflows, negotiating outcomes, and making decisions with limited human oversight. As these systems extend across organizational boundaries, identity alone…
The Model Context Protocol (MCP) replaces static, developer-controlled API integrations with more dynamic, user-driven agent systems, which also introduces new security risks. As MCP adoption grows across community servers and major…