Related papers: Contextual Agent Security: A Policy for Every Purp…
Current LLM agents typically lack instance-level context, which comprises concrete facts such as environment structure, system configurations, and local mechanics. Consequently, existing methods are forced to intertwine exploration with…
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…
Multi-agent cyber-physical systems are present in a variety of applications. Agent decision-making can be affected due to errors induced by uncertain, dynamic operating environments or due to incorrect actions taken by an agent. When an…
Understanding interpersonal communication requires, in part, understanding the social context and norms in which a message is said. However, current methods for identifying offensive content in such communication largely operate independent…
The rise of AI agents introduces a fundamental shift in Visual Analytics (VA), in which agents act as a new user group. Current agentic approaches - based on computer vision and raw DOM access - fail to perform VA tasks accurately and…
The emergence of agent-to-agent communication protocols mirrors the early internet: powerful connectivity with minimal security infrastructure. When AI agents communicate on behalf of users, every message crosses a trust boundary where the…
Getting a real cybersecurity risk assessment for a small organization is expensive -- a NIST CSF-aligned engagement runs $15,000 on the low end, takes weeks, and depends on practitioners who are genuinely scarce. Most small companies skip…
When designing multi-stakeholder privacy systems, it is important to consider how different groups of social media users have different goals and requirements for privacy. Additionally, we must acknowledge that it is important to keep in…
LLM-based Software Engineering agents face a critical bottleneck: context length limitations cause failures on complex, long-horizon tasks. One promising solution is to encode context as continuous embeddings rather than discrete tokens,…
Mobile agent technology offers a dramatically evolving computing paradigm in which a program, in the form of a software agent, can suspend its execution on a host computer, transfers itself to another agent-enabled host on the network, and…
Language model users often issue queries that lack specification, where the context under which a query was issued -- such as the user's identity, the query's intent, and the criteria for a response to be useful -- is not explicit. For…
Recent advances in large language models (LLMs) allow agents to represent actions as executable code, offering greater expressivity than traditional tool-calling. However, real-world tasks often demand both strategic planning and detailed…
The datasets most widely used for abusive language detection contain lists of messages, usually tweets, that have been manually judged as abusive or not by one or more annotators, with the annotation performed at message level. In this…
Safety evaluations of large language models (LLMs) typically focus on universal risks like dangerous capabilities or undesirable propensities. However, millions use LLMs for personal advice on high-stakes topics like finance and health,…
Cyber security incidents are increasing and humans play an important role in reducing their likelihood and impact. We identify a skewed focus towards technical aspects of cyber security in the literature, whereas factors influencing the…
The pursuit of improved accuracy in recommender systems has led to the incorporation of user context. Context-aware recommender systems typically handle large amounts of data which must be uploaded and stored on the cloud, putting the…
Long-horizon search agents must manage a rapidly growing working context as they reason, call tools, and observe information. Naively accumulating all intermediate content can overwhelm the agent, increasing costs and the risk of errors. We…
To exchange complex data structures in distributed systems, documents written in context-free languages are exchanged among communicating parties. Unparsing these documents correctly is as important as parsing them correctly because errors…
Temporal action proposal generation is an essential and challenging task that aims at localizing temporal intervals containing human actions in untrimmed videos. Most of existing approaches are unable to follow the human cognitive process…
Conversational recommender systems (CRS) have advanced with large language models, showing strong results in domains like movies. These domains typically involve fixed content and passive consumption, where user preferences can be matched…