相关论文: Why Does Agentic Safety Fail to Generalize Across …
Verification and validation of agentic behavior have been suggested as important research priorities in efforts to reduce risks associated with the creation of general artificial intelligence (Russell et al 2015). In this paper we question…
Credible safety plans for advanced AI development require methods to verify agent behavior and detect potential control deficiencies early. A fundamental aspect is ensuring agents adhere to safety-critical principles, especially when these…
Agentic AI systems -- Large Language Models (LLMs) augmented with planning, tool use, memory, and long-horizon interactions -- can execute complex tasks autonomously, but their multi-step trajectories introduce new failure modes that…
Contemporary benchmarks for agentic artificial intelligence (AI) frequently evaluate safety through isolated task-level accuracy thresholds, implicitly treating autonomous systems as single points of failure. This single-channel paradigm…
The leading AI companies are increasingly focused on building generalist AI agents -- systems that can autonomously plan, act, and pursue goals across almost all tasks that humans can perform. Despite how useful these systems might be,…
Computer-use agents have rapidly improved on real-world tasks such as web navigation, desktop automation, and software interaction, in some cases surpassing human performance. Yet even when the task and model are unchanged, an agent that…
Warning: This paper contains content that may be inappropriate or offensive. AI agents have gained significant recent attention due to their autonomous tool usage capabilities and their integration in various real-world applications. This…
Recent advances in AI agents capable of solving complex, everyday tasks, from scheduling to customer service, have enabled deployment in real-world settings, but their possibilities for unsafe behavior demands rigorous evaluation. While…
In recent years, agentic artificial intelligence (AI) systems are becoming increasingly widespread. These systems allow agents to use various tools, such as web browsers, compilers, and more. However, despite their popularity, agentic AI…
Autonomous agents based on large language models (LLMs) are rapidly emerging as a general-purpose technology, with recent systems such as OpenClaw extending their capabilities through broad tool use, third-party skills, and deeper…
The advancement of large language model (LLM) based agents has shifted AI evaluation from single-turn response assessment to multi-step task completion in interactive environments. We present an empirical study evaluating frontier AI models…
This article, a lightly adapted version of Perplexity's response to NIST/CAISI Request for Information 2025-0035, details our observations and recommendations concerning the security of frontier AI agents. These insights are informed by…
As AI systems gain increasing autonomy and execution capability, the number of discovered security vulnerabilities continues to rise. However, many of these vulnerabilities are not fundamentally novel, but instead reflect recurring classes…
A leading proposal for aligning artificial superintelligence (ASI) is to use AI agents to automate an increasing fraction of alignment research as capabilities improve. We argue that, even when research agents are not scheming to…
As AI systems advance in capabilities, measuring their safety and alignment to human values is becoming paramount. A fast-growing field of AI research is devoted to developing such assessments. However, most current advances therein may be…
AI agents are beginning to interact with each other directly and across internet platforms and physical environments, creating security challenges beyond traditional cybersecurity and AI safety frameworks. Free-form protocols are essential…
AI agents have been boosted by large language models. AI agents can function as intelligent assistants and complete tasks on behalf of their users with access to tools and the ability to execute commands in their environments. Through…
When AI agents don't align their actions with human values they may cause serious harm. One way to solve the value alignment problem is by including a human operator who monitors all of the agent's actions. Despite the fact, that this…
AI agents are increasingly deployed to execute important tasks. While rising accuracy scores on standard benchmarks suggest rapid progress, many agents still continue to fail in practice. This discrepancy highlights a fundamental limitation…
The implementation of agentic AI systems has the potential of providing more helpful AI systems in a variety of applications. These systems work autonomously towards a defined goal with reduced external control. Despite their potential, one…