Related papers: Harms from Increasingly Agentic Algorithmic System…
The rise of artificial intelligence (A.I.) based systems is already offering substantial benefits to the society as a whole. However, these systems may also enclose potential conflicts and unintended consequences. Notably, people will tend…
The ethical imperative for technology should be first, do no harm. But digital innovations like AI and social media increasingly enable societal harms, from bias to misinformation. As these technologies grow ubiquitous, we need solutions to…
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…
Autonomous multi-agent AI systems are poised to transform various industries, particularly software development and knowledge work. Understanding current perceptions among professionals is crucial for anticipating adoption challenges,…
As frontier language models are increasingly deployed as autonomous agents pursuing complex, long-term objectives, there is increased risk of scheming: agents covertly pursuing misaligned goals. Prior work has focused on showing agents are…
The emergence of Agentic AI systems has outpaced the architectural thinking required to operate them effectively. These agents differ fundamentally from traditional software: their behavior is not fixed at deployment but continuously shaped…
The rapid deployment of generative language models (LMs) has raised concerns about social biases affecting the well-being of diverse consumers. The extant literature on generative LMs has primarily examined bias via explicit identity…
Ensuring fairness in decentralized multi-agent systems presents significant challenges due to emergent biases, systemic inefficiencies, and conflicting agent incentives. This paper provides a comprehensive survey of fairness in multi-agent…
Agentic AI systems increasingly act through tool-augmented, multi-step workflows whose failures (unsafe tool use, unauthorised actions, social harm) carry deployment-level consequences. Evaluation practice remains fragmented across isolated…
Advances in AI offer the prospect of manipulating beliefs and behaviors on a population-wide level. Large language models and autonomous agents now let influence campaigns reach unprecedented scale and precision. Generative tools can expand…
AI agents are autonomous systems that combine LLMs with external tools to solve complex tasks. While such tools extend capability, improper tool permissions introduce security risks such as indirect prompt injection and tool misuse. We…
In societies increasingly entangled with algorithms, our choices are constantly influenced and shaped by automated systems. This convergence highlights significant concerns for individual autonomy in the age of data-driven AI. It leads to…
While harms of allocation have been increasingly studied as part of the subfield of algorithmic fairness, harms of representation have received considerably less attention. In this paper, we formalize two notions of stereotyping and show…
Agentic AI systems combine LLM-based reasoning, orchestration, tool invocation, and interaction with external environments. These systems introduce faults that are difficult to characterize using existing taxonomies. To address this gap, we…
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…
Large Language Model (LLM) agents, acting on their users' behalf to manipulate and analyze data, are likely to become the dominant workload for data systems in the future. When working with data, agents employ a high-throughput process of…
As artificial intelligence (AI) systems become more prevalent, ensuring fairness in their design becomes increasingly important. This survey focuses on the subdomains of social media and healthcare, examining the concepts of fairness,…
As a widely-used and practical tool, feature engineering transforms raw data into discriminative features to advance AI model performance. However, existing methods usually apply feature selection and generation separately, failing to…
Smart recommendation algorithms have revolutionized content delivery and improved efficiency across various domains. However, concerns about user agency arise from the algorithms' inherent opacity (information asymmetry) and one-way output…
The use of machine learning to guide clinical decision making has the potential to worsen existing health disparities. Several recent works frame the problem as that of algorithmic fairness, a framework that has attracted considerable…