相关论文: Normative Common Ground Replication (NormCoRe): Re…

The international community must collaborate to mitigate climate change and sustain economic growth. However, collaboration is hard to achieve, partly because no global authority can ensure compliance with international climate agreements.…

AI agents have become increasingly adept at complex tasks such as coding, reasoning, and multimodal understanding. However, building generalist systems requires moving beyond individual agents to collective inference -- a paradigm where…

AI alignment is often framed as the task of ensuring that an AI system follows a set of stated principles or human preferences, but general principles rarely determine their own application in concrete cases. When principles conflict, when…

As artificial intelligence (AI) advances toward superhuman capabilities, aligning these systems with human values becomes increasingly critical. Current alignment strategies rely largely on externally specified constraints that may prove…

Securing coordination between AI agent and teammates (human players or AI agents) in contexts involving unfamiliar humans continues to pose a significant challenge in Zero-Shot Coordination. The issue of cooperative incompatibility becomes…

Norms are known to be a major factor determining humans behavior. It's also shown that norms can be quite effective tool for building agent-based societies. Various normative architectures have been proposed for designing normative…

With recent advancements in multi-agent generative AI (Gen AI), technology organizations like Microsoft are adopting these complex tools, redefining AI agents as active collaborators in complex workflows rather than as passive tools. In…

We are currently unable to specify human goals and societal values in a way that reliably directs AI behavior. Law-making and legal interpretation form a computational engine that converts opaque human values into legible directives. "Law…

Human intelligence naturally intertwines omni-modal perception -- spanning vision, audio, and language -- with complex reasoning and tool usage to interact with the world. However, current multi-modal LLMs are primarily confined to bi-modal…

Human computer interaction is shifting from screen-based systems to multimodal interfaces where artificial intelligence powered systems increasingly interpret user intent through speech, gesture, and gaze. Yet users rarely understand how…

Cooperative multi-agent reinforcement learning (MARL) aims to develop agents that can collaborate effectively. However, most cooperative MARL methods overfit training agents, making learned policies not generalize well to unseen…

As AI agents become increasingly autonomous, widely deployed in consequential contexts, and efficacious in bringing about real-world impacts, ensuring that their decisions are not only instrumentally effective but also normatively aligned…

Collaborative learning works when groups regulate together by setting shared goals, coordinating participation, monitoring progress, and responding to breakdowns through co-regulation (CoRL) and socially shared regulation (SSRL). As…

Human-AI policy specification is a novel procedure we define in which humans can collaboratively warm-start a robot's reinforcement learning policy. This procedure is comprised of two steps; (1) Policy Specification, i.e. humans specifying…

Effective human-AI coordination requires artificial agents capable of exhibiting and responding to human-like behaviors while adapting to changing contexts. Imitation learning has emerged as one of the prominent approaches to build such…

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…

Beneficial societal outcomes cannot be guaranteed by aligning individual AI systems with the intentions of their operators or users. Even an AI system that is perfectly aligned to the intentions of its operating organization can lead to bad…

Over the past decade, artificial intelligence has demonstrated its efficiency in many different applications and a huge number of algorithms have become central and ubiquitous in our life. Their growing interest is essentially based on…

AI alignment is about ensuring AI systems only pursue goals and activities that are beneficial to humans. Most of the current approach to AI alignment is to learn what humans value from their behavioural data. This paper proposes a…

Agent-based modelling is a powerful tool when simulating human systems, yet when human behaviour cannot be described by simple rules or maximising one's own profit, we quickly reach the limits of this methodology. Machine learning has the…