Related papers: Personal Universes: A Solution to the Multi-Agent …

The AI safety literature is full of examples of powerful AI agents that, in blindly pursuing a specific and usually narrow objective, ends up with unacceptable and even catastrophic collateral damage to others. In this paper, we consider…

This work develops a fully decentralized multi-agent algorithm for policy evaluation. The proposed scheme can be applied to two distinct scenarios. In the first scenario, a collection of agents have distinct datasets gathered following…

For artificial intelligence to be beneficial to humans the behaviour of AI agents needs to be aligned with what humans want. In this paper we discuss some behavioural issues for language agents, arising from accidental misspecification by…

We consider that existing approaches to AI "safety" and "alignment" may not be using the most effective tools, teams, or approaches. We suggest that an alternative and better approach to the problem may be to treat alignment as a social…

AI systems have the potential to improve decision-making, but decision makers face the risk that the AI may be misaligned with their objectives. We study this problem in the context of a treatment decision, where a designer decides which…

Machine Learning algorithms are technological key enablers for artificial intelligence (AI). Due to the inherent complexity, these learning algorithms represent black boxes and are difficult to comprehend, therefore influencing compliance…

As artificial intelligence (AI) systems become increasingly integrated into various domains, ensuring that they align with human values becomes critical. This paper introduces a novel formalism to quantify the alignment between AI systems…

Agreement Technologies refer to open computer systems in which autonomous software agents interact with one another, typically on behalf of humans, in order to come to mutually acceptable agreements. With the advance of AI systems in recent…

Aligning Large Language Models (LLMs) to cater to different human preferences, learning new skills, and unlearning harmful behavior is an important problem. Search-based methods, such as Best-of-N or Monte-Carlo Tree Search, are performant,…

Human decision makers increasingly delegate choices to AI agents, raising a natural question: does the AI implement the human principal's preferences or pursue its own? To study this question using revealed preference techniques, I…

While there is a widespread belief that artificial general intelligence (AGI) -- or even superhuman AI -- is imminent, complex problems in expert domains are far from being solved. We argue that such problems require human-AI cooperation…

Large Language Models (LLMs) are typically aligned with human values using preference data or predefined principles such as helpfulness, honesty, and harmlessness. However, as AI systems progress toward Artificial General Intelligence (AGI)…

Despite the growing interest in collaborative AI, designing systems that seamlessly integrate human input remains a major challenge. In this study, we developed a task to systematically examine human preferences for collaborative agents. We…

Effective collaboration between humans and AI-based systems requires effective modeling of the human in the loop, both in terms of the mental state as well as the physical capabilities of the latter. However, these models can also open up…

Balancing game difficulty in video games is a key task to create interesting gaming experiences for players. Mismatching the game difficulty and a player's skill or commitment results in frustration or boredom on the player's side, and…

Motivated by mitigating potentially harmful impacts of technologies, the AI community has formulated and accepted mathematical definitions for certain pillars of accountability: e.g. privacy, fairness, and model transparency. Yet, we argue…

Autonomous agents (AA) will increasingly be interacting with us in our daily lives. While we want the benefits attached to AAs, it is essential that their behavior is aligned with our values and norms. Hence, an AA will need to estimate the…

We model a competitive market where AI agents buy answers from upstream generative models and resell them to users who differ in how much they value accuracy and in how much they fear hallucinations. Agents can privately exert effort for…

The issues of AI risk and AI safety are becoming critical as the prospect of artificial general intelligence (AGI) looms larger. The emergence of extremely large and capable generative models has led to alarming predictions and created a…

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.…