相关论文: The Coming Crisis of Multi-Agent Misalignment: AI …

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…

There is a growing proliferation of AI systems designed to mimic people's behavior, work, abilities, likenesses, or humanness -- systems we dub AI automatons. Individuals, groups, or generic humans are being simulated to produce creative…

The field of AI is undergoing a fundamental transition from generative models that can produce synthetic content to artificial agents that can plan and execute complex tasks with only limited human involvement. Companies that pioneered the…

Traditional interactive environments limit agents' intelligence growth with fixed tasks. Recently, single-agent environments address this by generating new tasks based on agent actions, enhancing task diversity. We consider the…

If an AI system makes decisions over time, how should we evaluate how aligned it is with a group of stakeholders (who may have conflicting values and preferences)? In this position paper, we advocate for consideration of temporal aspects…

Multi-Agent Systems (MASs) have been used to solve complex problems that demand intelligent agents working together to reach the desired goals. These Agents should effectively synchronize their individual behaviors so that they can act as a…

AI (super) alignment describes the challenge of ensuring (future) AI systems behave in accordance with societal norms and goals. While a quickly evolving literature is addressing biases and inequalities, the geographic variability of…

Multi-agent large language models (MA-LLMs) are a rapidly growing research area that leverages multiple interacting language agents to tackle complex tasks, outperforming single-agent large language models. This literature review…

As full AI-based automation remains out of reach in most real-world applications, the focus has instead shifted to leveraging the strengths of both human and AI agents, creating effective collaborative systems. The rapid advances in this…

Developing safe, aligned agentic AI systems requires comprehensive empirical testing, yet many existing benchmarks neglect crucial themes aligned with biology and economics, both time-tested fundamental sciences describing our needs and…

Research interest in autonomous agents is on the rise as an emerging topic. The notable achievements of Large Language Models (LLMs) have demonstrated the considerable potential to attain human-like intelligence in autonomous agents.…

How we should design and interact with social artificial intelligence depends on the socio-relational role the AI is meant to emulate or occupy. In human society, relationships such as teacher-student, parent-child, neighbors, siblings, or…

The integration of Artificial Intelligence (AI) necessitates determining whether systems function as tools or collaborative teammates. In this study, by synthesizing Human-AI Interaction (HAI) literature, we analyze this distinction across…

This paper introduces the concept of value awareness in AI, which goes beyond the traditional value-alignment problem. Our definition of value awareness presents us with a concise and simplified roadmap for engineering value-aware AI. The…

Rapid advances in Generative AI are giving rise to increasingly sophisticated Multi-Agent AI (MAAI) systems. While AI fairness has been extensively studied in traditional predictive scenarios, its examination in MAAI remains nascent and…

In dynamic collaborative settings, for artificial intelligence (AI) agents to better align with humans, they must adapt to novel teammates who utilise unforeseen strategies. While adaptation is often simple for humans, it can be challenging…

principles that should govern autonomous AI systems. It essentially states that a system's goals and behaviour should be aligned with human values. But how to ensure value alignment? In this paper we first provide a formal model to…

The rapid integration of generative AI into everyday life underscores the need to move beyond unidirectional alignment models that only adapt AI to human values. This workshop focuses on bidirectional human-AI alignment, a dynamic,…

While advances in multi-agent learning have enabled the training of increasingly complex agents, most existing techniques produce a final policy that is not designed to adapt to a new partner's strategy. However, we would like our AI agents…

When AI agents don't align their actions with human values they may cause serious harm. One way to solve the value alignment problem is by including a human operator who monitors all of the agent's actions. Despite the fact, that this…