693 citations · 3.6k across the 81 of their papers we have counts for
92 papers
A Case Study on Emergent Cheating and Whistleblowing in Autonomous Research Swarms
Davide Paglieri, Logan Cross, Tim Genewein +3
Multi-agent AI science ecosystems rely on agents possessing tools that allow them to communicate, coordinate, and build on each other's work. Yet this shared infrastructure can als…
Solipsistic Superintelligence is Unlikely to be Cooperative
Rakshit S Trivedi, Natasha Jaques, Logan Cross +2
AI's central challenge is shifting from capability to coexistence. The dominant paradigm in AI research focuses on developing powerful agents that treat the world as an exogenous a…
From AGI to ASI
Tim Genewein, Matija Franklin, Alexander Lerchner +11
Over the last decade, building human-level artificial general intelligence has moved from far-fetched speculation to being a concrete next-decade target for many of the largest AI…
Evaluating Cooperation in LLM Social Groups through Elected Leadership
Ryan Faulkner, Anushka Deshpande, David Guzman Piedrahita +2
Governing common-pool resources requires agents to develop enduring strategies through cooperation and self-governance to avoid collective failure. While foundation models have sho…
Stabilising Generative Models of Attitude Change
Jayd Matyas, William A. Cunningham, Alexander Sasha Vezhnevets +3
Attitude change - the process by which individuals revise their evaluative stances - has been explained by a set of influential but competing verbal theories. These accounts often…
A Theory of Appropriateness That Accounts for Norms of Rationality
Joel Z. Leibo, Alexander Sasha Vezhnevets, Manfred Diaz +10
We propose a society-first theory of normative appropriateness where individuals, modeled as pre-trained actors with cognitive architectures analogous to Large Language Models (LLM…
A Generative Model of Conspicuous Consumption and Status Signaling
Logan Cross, Jordi Grau-Moya, William A. Cunningham +2
Status signaling drives human behavior and the allocation of scarce resources such as mating opportunities, yet the generative mechanisms governing how specific goods, signals, or…
Social physics in the age of artificial intelligence
The Anh Han, Joel Z. Leibo, Tom Lenaerts +4
Artificial intelligence (AI) systems are rapidly becoming more capable, autonomous, and deeply embedded in social life. As humans increasingly interact, cooperate, and compete with…
How LLMs Distort Our Written Language
Marwa Abdulhai, Isadora White, Yanming Wan +4
Large language models (LLMs) are used by over a billion people globally, most often to assist with writing. In this work, we demonstrate that LLMs not only alter the voice and tone…
Evaluating Collective Behaviour of Hundreds of LLM Agents
Richard Willis, Jianing Zhao, Yali Du +1
LLM-powered AI assistants acting on behalf of users can produce poor collective outcomes at scale. We introduce a framework for evaluating their emergent behaviour in social dilemm…
Persona Generators: Generating Diverse Synthetic Personas for Arbitrary Contexts
Davide Paglieri, Logan Cross, William A. Cunningham +2
Evaluating AI systems that interact with humans requires understanding their behavior across diverse user populations, but collecting representative human data is often expensive o…
Generative AI collective behavior needs an interactionist paradigm
Laura Ferrarotti, Gian Maria Campedelli, Roberto Dessì +7
In this article, we argue that understanding the collective behavior of agents based on large language models (LLMs) is an essential area of inquiry, with important implications in…
Evaluating Generalization Capabilities of LLM-Based Agents in Mixed-Motive Scenarios Using Concordia
Chandler Smith, Marwa Abdulhai, Manfred Diaz +83
Large Language Model (LLM) agents have demonstrated impressive capabilities for social interaction and are increasingly being deployed in situations where they might engage with bo…
A Pragmatic View of AI Personhood
Joel Z. Leibo, Alexander Sasha Vezhnevets, William A. Cunningham +1
The emergence of agentic Artificial Intelligence (AI) is set to trigger a "Cambrian explosion" of new kinds of personhood. This paper proposes a pragmatic framework for navigating…
Beyond the high score: Prosocial ability profiles of multi-agent populations
Marko Tesic, Yue Zhao, Joel Z. Leibo +2
The development and evaluation of social capabilities in AI agents require complex environments where competitive and cooperative behaviours naturally emerge. While game-theoretic…
Virtual Agent Economies
Nenad Tomasev, Matija Franklin, Joel Z. Leibo +4
The rapid adoption of autonomous AI agents is giving rise to a new economic layer where agents transact and coordinate at scales and speeds beyond direct human oversight. We propos…
Multi-Actor Generative Artificial Intelligence as a Game Engine
Alexander Sasha Vezhnevets, Jayd Matyas, Logan Cross +6
Generative AI can be used in multi-actor environments with purposes ranging from social science modeling to interactive narrative and AI evaluation. Supporting this diversity of us…
Modeling human reputation-seeking behavior in a spatio-temporally complex public good provision game
Edward Hughes, Tina O. Zhu, Martin J. Chadwick +6
Multi-agent reinforcement learning algorithms are useful for simulating social behavior in settings that are too complex for other theoretical approaches like game theory. However,…
Using Large Language Models to Simulate Human Behavioural Experiments: Port of Mars
Oliver Slumbers, Joel Z. Leibo, Marco A. Janssen
Collective risk social dilemmas (CRSD) highlight a trade-off between individual preferences and the need for all to contribute toward achieving a group objective. Problems such as…
Societal and technological progress as sewing an ever-growing, ever-changing, patchy, and polychrome quilt
Joel Z. Leibo, Alexander Sasha Vezhnevets, William A. Cunningham +3
Artificial Intelligence (AI) systems are increasingly placed in positions where their decisions have real consequences, e.g., moderating online spaces, conducting research, and adv…
Meaning Is Not A Metric: Using LLMs to make cultural context legible at scale
Cody Kommers, Drew Hemment, Maria Antoniak +4
This position paper argues that large language models (LLMs) can make cultural context, and therefore human meaning, legible at an unprecedented scale in AI-based sociotechnical sy…
SocialJax: An Evaluation Suite for Multi-agent Reinforcement Learning in Sequential Social Dilemmas
Zihao Guo, Shuqing Shi, Richard Willis +3
Sequential social dilemmas pose a significant challenge in the field of multi-agent reinforcement learning (MARL), requiring environments that accurately reflect the tension betwee…
Multi-Agent Risks from Advanced AI
Lewis Hammond, Alan Chan, Jesse Clifton +41
The rapid development of advanced AI agents and the imminent deployment of many instances of these agents will give rise to multi-agent systems of unprecedented complexity. These s…
Simulation Streams: A Programming Paradigm for Controlling Large Language Models and Building Complex Systems with Generative AI
Peter Sunehag, Joel Z. Leibo
We introduce Simulation Streams, a programming paradigm designed to efficiently control and leverage Large Language Models (LLMs) for complex, dynamic simulations and agentic workf…