Related papers: Auditable Agents
Sequential multi-agent systems built with large language models (LLMs) can automate complex software tasks, but they are hard to trust because errors quietly pass from one stage to the next. We study a traceable and accountable pipeline,…
We describe and implement a policy language. In our system, agents can distribute data along with usage policies in a decentralized architecture. Our language supports the specification of conditions and obligations, and also the…
Open agentic systems combine LLM-based planning with external capabilities, persistent memory, and privileged execution. They are used in coding assistants, browser copilots, and enterprise automation. OpenClaw is a visible instance of this…
AI agents are systems capable of perceiving their environment, autonomously planning and executing tasks. Recent advancements in LLM have introduced a transformative paradigm for AI agents, enabling them to interact with external resources…
Mitigating elderly loneliness requires policy interventions that achieve both adaptability and auditability. Existing methods struggle to reconcile these objectives: traditional agent-based models suffer from static rigidity, while direct…
LLM-based agents represent a paradigm shift in AI, enabling autonomous systems to plan, reason, and use tools while interacting with dynamic environments. This paper provides the first comprehensive survey of evaluation methods for these…
Agentic systems are becoming more capable: agents define strategies, take actions, and interact with different environments. This autonomy poses serious challenges for overseeing and assessing agent behavior. Most current tools are limited,…
What should a developer inspect before deploying an LLM agent: the model, the tool code, the deployment configuration, or all three? In practice, many security failures in agent systems arise not from model weights alone, but from the…
Large language model agents now act on codebases, browsers, operating systems, calendars, files, and tool ecosystems, but their evaluations often collapse behavior into final task success. AgentAtlas reframes agent evaluation as a…
Despite the growing capabilities of autonomous agents powered by large language models (LLMs), their adoption in high-stakes domains remains limited. A key barrier is security: the inherently nondeterministic behavior of LLM agents defies…
Auditability is defined as the capacity of AI systems to be independently assessed for compliance with ethical, legal, and technical standards throughout their lifecycle. The chapter explores how auditability is being formalized through…
AI systems are becoming increasingly complex, ubiquitous and autonomous, leading to increasing concerns about their impacts on individuals and society. In response, researchers have begun investigating how to ensure that the methods…
The rise of Agent AI and Large Language Model-powered Multi-Agent Systems (LLM-MAS) has underscored the need for responsible and dependable system operation. Tools like LangChain and Retrieval-Augmented Generation have expanded LLM…
LLM-powered Multi-Agent Systems (LLM-MAS) unlock new potentials in distributed reasoning, collaboration, and task generalization but also introduce additional risks due to unguaranteed agreement, cascading uncertainty, and adversarial…
Agents are LLM-driven components that can mutate environments in powerful, arbitrary ways. Extracting guarantees for the execution of agents in production environments can be challenging due to asynchrony and failures. In this paper, we…
Organisations are starting to adopt LLM-based AI agents, with their deployments naturally evolving from single agents towards interconnected, multi-agent networks. Yet a collection of safe agents does not guarantee a safe collection of…
Deploying agentic AI in regulated contexts requires principled reasoning about two design dimensions: agency (what the system can do) and autonomy (how much it acts without human involvement). Though often treated independently, they are…
Log-based insider threat detection (ITD) detects malicious user activities by auditing log entries. Recently, large language models (LLMs) with strong common sense knowledge have emerged in the domain of ITD. Nevertheless, diverse activity…
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…
LLM-based autonomous agents have demonstrated strong capabilities in reasoning, planning, and tool use, yet remain limited when tasks require sustained coordination across roles, tools, and environments. Multi-agent systems address this…