English
Related papers

Related papers: Emergent Alignment via Competition

200 papers

The behaviour of multi-agent learning in competitive settings is often considered under the restrictive assumption of a zero-sum game. Only under this strict requirement is the behaviour of learning well understood; beyond this, learning…

Computer Science and Game Theory · Computer Science 2023-07-27 Aamal Hussain , Francesco Belardinelli , Georgios Piliouras

It is widely agreed that when AI models assist decision-makers in high-stakes domains by predicting an outcome of interest, they should communicate the confidence of their predictions. However, empirical evidence suggests that…

Machine Learning · Computer Science 2026-05-14 Nina Corvelo Benz , Eleni Straitouri , Manuel Gomez-Rodriguez

Achieving human-AI alignment in complex multi-agent games is crucial for creating trustworthy AI agents that enhance gameplay. We propose a method to evaluate this alignment using an interpretable task-sets framework, focusing on high-level…

Artificial Intelligence · Computer Science 2024-06-21 Sugandha Sharma , Guy Davidson , Khimya Khetarpal , Anssi Kanervisto , Udit Arora , Katja Hofmann , Ida Momennejad

Strategic interaction in congested systems is commonly modelled using Stackelberg games, where competing leaders anticipate the behaviour of self-interested followers. A key limitation of existing models is that they typically ignore agents…

Multiagent Systems · Computer Science 2026-03-06 Niloofar Aminikalibar , Farzaneh Farhadi , Maria Chli

Artificial and biological systems may evolve similar computational solutions despite fundamental differences in architecture and learning mechanisms -- a form of convergent evolution. We demonstrate this phenomenon through large-scale…

Neurons and Cognition · Quantitative Biology 2025-07-04 Guobin Shen , Dongcheng Zhao , Yiting Dong , Qian Zhang , Yi Zeng

Given that Artificial Intelligence (AI) increasingly permeates our lives, it is critical that we systematically align AI objectives with the goals and values of humans. The human-AI alignment problem stems from the impracticality of…

Computers and Society · Computer Science 2022-07-05 John Nay , James Daily

Whenever an AI model is used to predict a relevant (binary) outcome in AI-assisted decision making, it is widely agreed that, together with each prediction, the model should provide an AI confidence value. However, it has been unclear why…

Artificial Intelligence · Computer Science 2025-01-27 Nina L. Corvelo Benz , Manuel Gomez Rodriguez

In this work, we study the system of interacting non-cooperative two Q-learning agents, where one agent has the privilege of observing the other's actions. We show that this information asymmetry can lead to a stable outcome of population…

Machine Learning · Computer Science 2021-01-26 Ezra Tampubolon , Haris Ceribasic , Holger Boche

We introduce robust learning equilibrium. The idea of learning equilibrium is that learning algorithms in multi-agent systems should themselves be in equilibrium rather than only lead to equilibrium. That is, learning equilibrium is immune…

Computer Science and Game Theory · Computer Science 2012-07-02 Itai Ashlagi , Dov Monderer , Moshe Tennenholtz

As autonomous AI agents increasingly mediate online platform markets, a fundamental question emerges: do these markets generate stable strategic outcomes? In repeated strategic environments, the Nash equilibrium provides a natural benchmark…

Artificial Intelligence · Computer Science 2026-04-28 Enoch Hyunwook Kang

With AI systems becoming more powerful and pervasive, there is increasing debate about keeping their actions aligned with the broader goals and needs of humanity. This multi-disciplinary and multi-stakeholder debate must resolve many…

Artificial Intelligence · Computer Science 2021-12-21 Koen Holtman

The rise of artificial intelligence (A.I.) based systems is already offering substantial benefits to the society as a whole. However, these systems may also enclose potential conflicts and unintended consequences. Notably, people will tend…

Computers and Society · Computer Science 2020-12-23 Pedro Fernandes , Francisco C. Santos , Manuel Lopes

While we would like agents that can coordinate with humans, current algorithms such as self-play and population-based training create agents that can coordinate with themselves. Agents that assume their partner to be optimal or similar to…

Machine Learning · Computer Science 2020-01-10 Micah Carroll , Rohin Shah , Mark K. Ho , Thomas L. Griffiths , Sanjit A. Seshia , Pieter Abbeel , Anca Dragan

When learning in strategic environments, a key question is whether agents can overcome uncertainty about their preferences to achieve outcomes they could have achieved absent any uncertainty. Can they do this solely through interactions…

Computer Science and Game Theory · Computer Science 2024-11-21 Nivasini Ananthakrishnan , Nika Haghtalab , Chara Podimata , Kunhe Yang

Covering and packing problems can be modeled as games to encapsulate interesting social and engineering settings. These games have a high Price of Anarchy in their natural formulation. However, existing research applicable to specific…

Computer Science and Game Theory · Computer Science 2011-09-19 Maria-Florina Balcan , Sara Krehbiel , Georgios Piliouras , Jinwoo Shin

This paper explores the capacity of artificial intelligence (AI) algorithms to autonomously design incentive-compatible contracts in dual-principal-agent settings, a relatively unexplored aspect of algorithmic mechanism design. We develop a…

Artificial Intelligence · Computer Science 2024-06-14 Qian Qi

We suggest that the analysis of incomplete contracting developed by law and economics researchers can provide a useful framework for understanding the AI alignment problem and help to generate a systematic approach to finding solutions. We…

Artificial Intelligence · Computer Science 2018-04-13 Dylan Hadfield-Menell , Gillian Hadfield

As machine learning algorithms increasingly influence critical decision making in different application areas, understanding human strategic behavior in response to these systems becomes vital. We explore individuals' choice between…

Machine Learning · Computer Science 2026-03-17 Sura Alhanouti , Parinaz Naghizadeh

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.…

AI is increasingly deployed in multi-agent systems; however, most research considers only the behavior of individual models. We experimentally show that multi-agent "AI organizations" are simultaneously more effective at achieving business…