Related papers: Resource Rational Contractualism Should Guide AI A…
We focus on the problem of designing an artificial agent (AI), capable of assisting a human user to complete a task. Our goal is to guide human users towards optimal task performance while keeping their cognitive load as low as possible.…
Existing alignment research is dominated by concerns about safety and preventing harm: safeguards, controllability, and compliance. This paradigm of alignment parallels early psychology's focus on mental illness: necessary but incomplete.…
With increased power and prevalence of AI systems, it is ever more critical that AI systems are designed to serve all, i.e., people with diverse values and perspectives. However, aligning models to serve pluralistic human values remains an…
LLM alignment has progressed in single-agent settings through paradigms such as RL with human feedback (RLHF), while recent work explores scalable alternatives such as RL with AI feedback (RLAIF) and dynamic alignment objectives. However,…
Agentic AI represents a major shift in how autonomous systems reason, plan, and execute multi-step tasks through the coordination of Large Language Models (LLMs), Vision Language Models (VLMs), tools, and external services. While these…
One strategy in response to pluralistic values in a user population is to personalize an AI system: if the AI can adapt to the specific values of each individual, then we can potentially avoid many of the challenges of pluralism.…
The AI-alignment problem arises when there is a discrepancy between the goals that a human designer specifies to an AI learner and a potential catastrophic outcome that does not reflect what the human designer really wants. We argue that a…
As AI systems become increasingly capable and influential, ensuring their alignment with human values, preferences, and goals has become a critical research focus. Current alignment methods primarily focus on designing algorithms and loss…
The Abstraction and Reasoning Corpus (ARC) provides a compact laboratory for studying abstract reasoning, an ability central to human intelligence. Modern AI systems, including LLMs and ViTs, largely operate as sequence-of-behavior…
Humans rapidly learn abstract knowledge when encountering novel environments and flexibly deploy this knowledge to guide efficient and intelligent action. Can modern AI systems learn and plan in a similar way? We study this question using a…
As debates on potential societal harm from artificial intelligence (AI) culminate in legislation and international norms, a global divide is emerging in both AI regulatory frameworks and international governance structures. In terms of…
Discussion of AI alignment (alignment between humans and AI systems) has focused on value alignment, broadly referring to creating AI systems that share human values. We argue that before we can even attempt to align values, it is…
Contract theory studies how a principal can incentivize agents to exert costly, unobservable effort through performance-based payments. While classical economic models provide elegant characterizations of optimal solutions, modern…
Recent advances in AI research make it increasingly plausible that artificial agents with consequential real-world impact will soon operate beyond tightly controlled environments. Ensuring that these agents are not only safe but that they…
The increasing deployment of AI is shaping the future landscape of the internet, which is set to become an integrated ecosystem of AI agents. Orchestrating the interaction among AI agents necessitates decentralized, self-sustaining…
Artificial intelligence radio access networks (AI-RANs) are a promising architecture for bolstering the prosperity of the edge AI ecosystem. A well-designed incentive mechanism can further ensure the sustainable development of this…
AI has proven highly successful at urban planning analysis -- learning patterns from data to predict future conditions. The next frontier is AI-assisted decision-making: agents that recommend sites, allocate resources, and evaluate…
When organisations adopt commercial AI systems for decision support, they inherit value judgements embedded by vendors that are neither transparent nor renegotiable. The governance puzzle is not whether AI can support decisions but which…
When should we delegate decisions to AI systems? While the value alignment literature has developed techniques for shaping AI values, less attention has been paid to how to determine, under uncertainty, when imperfect alignment is good…
When we consult with a doctor, lawyer, or financial advisor, we generally assume that they are acting in our best interests. But what should we assume when it is an artificial intelligence (AI) system that is acting on our behalf? Early…