Vincent Conitzer — accepted AI-conference papers

2026

Convergence of Regret Matching in Potential Games and Constrained Optimization

Ioannis Anagnostides, Emanuel Tewolde, Brian Hu Zhang, Ioannis Panageas, Vincent Conitzer, Tuomas Sandholm

ICLR 2026poster

Regret matching (RM)---and its modern variants---is a foundational online algorithm that has been at the heart of many AI breakthrough results in solving benchmark zero-sum games, such as poker. Yet, surprisingly little is known so far in theory about its convergence beyond two-player zero-sum games…

Cited by 0 Source ↗Scholar ↗

2026

CoopEval: Benchmarking Cooperation-Sustaining Mechanisms and LLM Agents in Social Dilemmas

Emanuel Tewolde, Xiao Zhang, David Guzman Piedrahita, Vincent Conitzer, Zhijing Jin

ICML 2026poster

It is increasingly important that LLM agents interact effectively and safely with other goal-pursuing agents, yet, according to recent works, the opposite trend appears to be the case: LLMs with stronger reasoning capabilities behave _less_ cooperatively in mixed-motive games such as the prisoner's …

Cited by 0 Source ↗Scholar ↗

2026

Designing Rules to Pick a Rule: Aggregation by Consistency

Ratip Emin Berker, Ben Armstrong, Vincent Conitzer, Nihar B Shah

ICLR 2026poster

Rank aggregation has critical applications for developing AI agents, as well as for evaluating them. However, different methods can give rise to significantly different aggregate rankings, impacting these applications. Indeed, work in social choice and statistics has produced many rank aggregation m…

Cited by 0 Source ↗Scholar ↗

2026

Moral Change or Noise? On Problems of Aligning AI with Temporally Unstable Human Feedback

Vijay Keswani, Cyrus Cousins, Breanna Nguyen, Vincent Conitzer, Hoda Heidari, Jana Schaich Borg +1

AAAI 2026technical

Alignment methods in moral domains seek to elicit moral preferences of human stakeholders and incorporate them into AI. This presupposes moral preferences as static targets, but such preferences often evolve over time. Proper alignment of AI to dynamic human preferences should ideally account for "l

Cited by 0 Source ↗PDF ↗Scholar ↗

2026

On the Edge of Core (Non-)Emptiness: An Automated Reasoning Approach to Approval-Based Multi-Winner Voting

Ratip Emin Berker, Emanuel Tewolde, Vincent Conitzer, Mingyu Guo, Marijn Heule, Lirong Xia

AAAI 2026technical

Core stability is a natural and well-studied notion for group fairness in multi-winner voting, where the task is to select a committee from a pool of candidates. We study the setting where voters either approve or disapprove of each candidate; here, it remains a major open problem whether a core-sta

Cited by 0 Source ↗PDF ↗Scholar ↗

2026

Position: We Need Practical AI Alignment Methods that Mirror Human Reasoning

Vijay Keswani, Breanna Nguyen, Cyrus Cousins, Vincent Conitzer, Walter Sinnott-Armstrong, Jana Schaich Borg

ICML 2026poster

AI systems are increasingly employed as decision aids, decision delegates, or autonomous decision-makers. This position paper argues that in many settings, particularly high-stakes decision-making, we need accurate cognitively-aligned AI systems that reason similarly to their users, and faithfully c…

Cited by 0 Source ↗Scholar ↗

2026

Towards Cognitively-Faithful Decision-Making Models to Improve AI Alignment

Cyrus Cousins, Vijay Keswani, Vincent Conitzer, Hoda Heidari, Jana Schaich Borg, Walter Sinnott-Armstrong

ICLR 2026poster

Recent AI trends seek to align AI models to learned human-centric objectives, such as personal preferences, utility, or societal values. Using standard preference elicitation methods, researchers and practitioners build models of human decisions and judgments, to which AI models are aligned. However…

Cited by 0 Source ↗Scholar ↗

2025

AI Testing Should Account for Sophisticated Strategic Behaviour

Vojtech Kovarik, Eric Olav Chen, Sami Petersen, Alexis Ghersengorin, Vincent Conitzer

NeurIPS 2025poster

This position paper argues for two claims regarding AI testing and evaluation. First, to remain informative about deployment behaviour, evaluations need account for the possibility that AI systems understand their circumstances and reason strategically. Second, game-theoretic analysis can inform eva…

Cited by 0 Source ↗Scholar ↗

2025

Characterising Simulation-Based Program Equilibria

Emery Cooper, Caspar Oesterheld, Vincent Conitzer

AAAI 2025technical

In Tennenholtz’s program equilibrium, players of a game submit programs to play on their behalf. Each program receives the other programs’ source code and outputs an action. This can model interactions involving AI agents, mutually transparent institutions, or commitments. Tennenholtz 2004 (https://…

Cited by 2 Source ↗PDF ↗Scholar ↗

2025

Computing Game Symmetries and Equilibria That Respect Them

Emanuel Tewolde, Brian Hu Zhang, Caspar Oesterheld, Tuomas Sandholm, Vincent Conitzer

AAAI 2025technical

Strategic interactions can be represented more concisely, and analyzed and solved more efficiently, if we are aware of the symmetries within the multiagent system. Symmetries also have conceptual implications, for example for equilibrium selection. We study the computational complexity of identifyin…

Cited by 1 Source ↗PDF ↗Scholar ↗

2025

Expected Variational Inequalities

Brian Hu Zhang, Ioannis Anagnostides, Emanuel Tewolde, Ratip Emin Berker, Gabriele Farina, Vincent Conitzer +1

ICML 2025oral

*Variational inequalities (VIs)* encompass many fundamental problems in diverse areas ranging from engineering to economics and machine learning. However, their considerable expressivity comes at the cost of computational intractability. In this paper, we introduce and analyze a natural relaxation—w…

Cited by 1 Source ↗PDF ↗Scholar ↗

2025

Observation Interference in Partially Observable Assistance Games

Scott Emmons, Caspar Oesterheld, Vincent Conitzer, Stuart Russell

ICML 2025poster

We study partially observable assistance games (POAGs), a model of the human-AI value alignment problem which allows the human and the AI assistant to have partial observations. Motivated by concerns of AI deception, we study a qualitatively new phenomenon made possible by partial observability: wou…

Cited by 2 Source ↗PDF ↗Scholar ↗

2025

The Value of Recall in Extensive-Form Games

Ratip Emin Berker, Emanuel Tewolde, Ioannis Anagnostides, Tuomas Sandholm, Vincent Conitzer

AAAI 2025technical

Imperfect-recall games—in which players may forget previously acquired information—have found many practical applications, ranging from game abstractions to team games and testing AI agents. In this paper, we quantify the utility gain by endowing a player with perfect recall, which we call the value…

Cited by 0 Source ↗PDF ↗Scholar ↗

2024

Aggregating Quantitative Relative Judgments: From Social Choice to Ranking Prediction

Yixuan Even Xu, Hanrui Zhang, Yu Cheng, Vincent Conitzer

NeurIPS 2024poster

Quantitative Relative Judgment Aggregation (QRJA) is a new research topic in (computational) social choice. In the QRJA model, agents provide judgments on the relative quality of different candidates, and the goal is to aggregate these judgments across all agents. In this work, our main conceptual c…

Cited by 1 Source ↗PDF ↗code ↗Scholar ↗

2024

Computing Optimal Equilibria in Repeated Games with Restarts

Ratip Emin Berker, Vincent Conitzer

IJCAI 2024poster

Infinitely repeated games can support cooperative outcomes that are not equilibria in the one-shot game. The idea is to make sure that any gains from deviating will be offset by retaliation in future rounds. However, this model of cooperation fails in anonymous settings with many strategic agents t…

Cited by 0 Source ↗PDF ↗Scholar ↗

2024

Game Transformations That Preserve Nash Equilibria or Best-Response Sets

Emanuel Tewolde, Vincent Conitzer

IJCAI 2024poster

In this paper, we investigate under which conditions normal-form games are (guaranteed to be) strategically equivalent. First, we show for N -player games (N >= 3) that (A) it is NP-hard to decide whether a given strategy is a best response to some strategy profile of the opponents, and that (B) i…

Cited by 7 Source ↗PDF ↗Scholar ↗

2024

Imperfect-Recall Games: Equilibrium Concepts and Their Complexity

Emanuel Tewolde, Brian Hu Zhang, Caspar Oesterheld, Manolis Zampetakis, Tuomas Sandholm, Paul Goldberg +1

IJCAI 2024poster

We investigate optimal decision making under imperfect recall, that is, when an agent forgets information it once held before. An example is the absentminded driver game, as well as team games in which the members have limited communication capabilities. In the framework of extensive-form games with…

Cited by 6 Source ↗PDF ↗Scholar ↗

2024

Melting Pot Contest: Charting the Future of Generalized Cooperative Intelligence

Rakshit Trivedi, Akbir Khan, Jesse Clifton, Lewis Hammond, Edgar A. Duéñez-Guzmán, Dipam Chakraborty +20

NeurIPS 2024poster

Multi-agent AI research promises a path to develop human-like and human-compatible intelligent technologies that complement the solipsistic view of other approaches, which mostly do not consider interactions between agents. Aiming to make progress in this direction, the Melting Pot contest 2023 focu…

Cited by 0 Source ↗PDF ↗Scholar ↗

2024

Non-excludable Bilateral Trade between Groups

Yixuan Even Xu, Hanrui Zhang, Vincent Conitzer

AAAI 2024technical

Bilateral trade is one of the most natural and important forms of economic interaction: A seller has a single, indivisible item for sale, and a buyer is potentially interested. The two parties typically have different, privately known valuations for the item, and ideally, they would like to trade if…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2024

Position: Social Choice Should Guide AI Alignment in Dealing with Diverse Human Feedback

Vincent Conitzer, Rachel Freedman, Jobst Heitzig, Wesley H. Holliday, Bob M. Jacobs, Nathan Lambert +6

ICML 2024poster

Foundation models such as GPT-4 are fine-tuned to avoid unsafe or otherwise problematic behavior, such as helping to commit crimes or producing racist text. One approach to fine-tuning, called reinforcement learning from human feedback, learns from humans’ expressed preferences over multiple outputs…

Cited by 29 Source ↗PDF ↗Scholar ↗

2024

The Complexity of Computing Robust Mediated Equilibria in Ordinal Games

Vincent Conitzer

AAAI 2024technical

Usually, to apply game-theoretic methods, we must specify utilities precisely, and we run the risk that the solutions we compute are not robust to errors in this specification. Ordinal games provide an attractive alternative: they require specifying only which outcomes are preferred to which other…

Cited by 1 Source ↗PDF ↗Scholar ↗

2023

Computing Optimal Equilibria and Mechanisms via Learning in Zero-Sum Extensive-Form Games

Brian Hu Zhang, Gabriele Farina, Ioannis Anagnostides, Federico Cacciamani, Stephen Marcus McAleer, Andreas Alexander Haupt +4

NeurIPS 2023poster

We introduce a new approach for computing optimal equilibria via learning in games. It applies to extensive-form settings with any number of players, including mechanism design, information design, and solution concepts such as correlated, communication, and certification equilibria. We observe that…

Cited by 24 Source ↗PDF ↗Scholar ↗

2023

Foundations of Cooperative AI

Vincent Conitzer, Caspar Oesterheld

AAAI 2023technical

AI systems can interact in unexpected ways, sometimes with disastrous consequences. As AI gets to control more of our world, these interactions will become more common and have higher stakes. As AI becomes more advanced, these interactions will become more sophisticated, and game theory will provide…

Cited by 41 Source ↗PDF ↗Scholar ↗

2023

Game Theory with Simulation of Other Players

Vojtěch Kovařík, Caspar Oesterheld, Vincent Conitzer

IJCAI 2023poster

Game-theoretic interactions with AI agents could differ from traditional human-human interactions in various ways. One such difference is that it may be possible to simulate an AI agent (for example because its source code is known), which allows others to accurately predict the agent's actions. Thi…

Cited by 17 Source ↗PDF ↗Scholar ↗

2023

Similarity-based cooperative equilibrium

Caspar Oesterheld, Johannes Treutlein, Roger Baker Grosse, Vincent Conitzer, Jakob Nicolaus Foerster

NeurIPS 2023poster

As machine learning agents act more autonomously in the world, they will increasingly interact with each other. Unfortunately, in many social dilemmas like the one-shot Prisoner’s Dilemma, standard game theory predicts that ML agents will fail to cooperate with each other. Prior work has shown that…

Cited by 7 Source ↗PDF ↗Scholar ↗

2023

The Computational Complexity of Single-Player Imperfect-Recall Games

Emanuel Tewolde, Caspar Oesterheld, Vincent Conitzer, Paul W. Goldberg

IJCAI 2023poster

We study single-player extensive-form games with imperfect recall, such as the Sleeping Beauty problem or the Absentminded Driver game. For such games, two natural equilibrium concepts have been proposed as alternative solution concepts to ex-ante optimality. One equilibrium concept uses generalized…

Cited by 14 Source ↗PDF ↗Scholar ↗

2022

For Learning in Symmetric Teams, Local Optima are Global Nash Equilibria

Scott Emmons, Caspar Oesterheld, Andrew Critch, Vincent Conitzer, Stuart Russell

ICML 2022spotlight

Although it has been known since the 1970s that a

Cited by 13 Source ↗PDF ↗code ↗Scholar ↗

2022

Learning Influence Adoption in Heterogeneous Networks

Vincent Conitzer, Debmalya Panigrahi, Hanrui Zhang

AAAI 2022technical

We study the problem of learning influence adoption in networks. In this problem, a communicable entity (such as an infectious disease, a computer virus, or a social media meme) propagates through a network, and the goal is to learn the state of each individual node by sampling only a small number o…

Cited by 4 Source ↗PDF ↗Scholar ↗

2022

Planning with Participation Constraints

Hanrui Zhang, Yu Cheng, Vincent Conitzer

AAAI 2022technical

We pose and study the problem of planning in Markov decision processes (MDPs), subject to participation constraints as studied in mechanism design. In this problem, a planner must work with a self-interested agent on a given MDP. Each action in the MDP provides an immediate reward to the planner and…

Cited by 8 Source ↗PDF ↗Scholar ↗

2021

Automated Dynamic Mechanism Design

Hanrui Zhang, Vincent Conitzer

NeurIPS 2021poster

We study Bayesian automated mechanism design in unstructured dynamic environments, where a principal repeatedly interacts with an agent, and takes actions based on the strategic agent's report of the current state of the world. Both the principal and the agent can have arbitrary and potentially dif…

Cited by 18 Source ↗PDF ↗Scholar ↗

2021

Automated Mechanism Design for Classification with Partial Verification

Hanrui Zhang, Yu Cheng, Vincent Conitzer

AAAI 2021technical

We study the problem of automated mechanism design with partial verification, where each type can (mis)report only a restricted set of types (rather than any other type), induced by the principal's limited verification power. We prove hardness results when the revelation principle does not necessari…

Cited by 14 Source ↗PDF ↗Scholar ↗

2021

Classification with Few Tests through Self-Selection

Hanrui Zhang, Yu Cheng, Vincent Conitzer

AAAI 2021technical

We study test-based binary classification, where a principal either accepts or rejects agents based on the outcomes they get in a set of tests. The principal commits to a policy, which consists of all sets of outcomes that lead to acceptance. Each agent is modeled by a distribution over the space…

Cited by 9 Source ↗PDF ↗Scholar ↗

2021

Classification with Strategically Withheld Data

Anilesh K. Krishnaswamy, Haoming Li, David Rein, Hanrui Zhang, Vincent Conitzer

AAAI 2021technical

Machine learning techniques can be useful in applications such as credit approval and college admission. However, to be classified more favorably in such contexts, an agent may decide to strategically withhold some of her features, such as bad test scores. This is a missing data problem with a twis…

Cited by 17 Source ↗PDF ↗code ↗Scholar ↗

2021

Incentive-Aware PAC Learning

Hanrui Zhang, Vincent Conitzer

AAAI 2021technical

We study PAC learning in the presence of strategic manipulation, where data points may modify their features in certain predefined ways in order to receive a better outcome. We show that the vanilla ERM principle fails to achieve any nontrivial guarantee in this context. Instead, we propose an incen…

Cited by 51 Source ↗PDF ↗Scholar ↗

2021

Indecision Modeling

Duncan C. McElfresh, Lok Chan, Kenzie Doyle, Walter Sinnott-Armstrong, Vincent Conitzer, Jana Schaich Borg +1

AAAI 2021technical

AI systems are often used to make or contribute to important decisions in a growing range of applications, including criminal justice, hiring, and medicine. Since these decisions impact human lives, it is important that the AI systems act in ways which align with human values. Techniques for prefere…

Cited by 13 Source ↗PDF ↗code ↗Scholar ↗

2020

Learning Opinions in Social Networks

Vincent Conitzer, Debmalya Panigrahi, Hanrui Zhang

ICML 2020poster

We study the problem of learning opinions in social networks. The learner observes the states of some sample nodes from a social network, and tries to infer the states of other nodes, based on the structure of the network. We show that sample-efficient learning is impossible when the network exhibit…

Cited by 11 Source ↗PDF ↗Scholar ↗

2020

Learning the Valuations of a $k$-demand Agent

Hanrui Zhang, Vincent Conitzer

ICML 2020poster

We study problems where a learner aims to learn the valuations of an agent by observing which goods he buys under varying price vectors. More specifically, we consider the case of a $k$-demand agent, whose valuation over the goods is additive when receiving up to $k$ goods, but who has no interest i…

Cited by 10 Source ↗PDF ↗Scholar ↗

2020

Mitigating Manipulation in Peer Review via Randomized Reviewer Assignments

Steven Jecmen, Hanrui Zhang, Ryan Liu, Nihar Shah, Vincent Conitzer, Fei Fang

NeurIPS 2020poster

We consider three important challenges in conference peer review: (i) reviewers maliciously attempting to get assigned to certain papers to provide positive reviews, possibly as part of quid-pro-quo arrangements with the authors; (ii) "torpedo reviewing," where reviewers deliberately attempt to get…

Cited by 88 Source ↗PDF ↗code ↗Scholar ↗

2019

Distinguishing Distributions When Samples Are Strategically Transformed

Hanrui Zhang, Yu Cheng, Vincent Conitzer

NeurIPS 2019poster

Often, a principal must make a decision based on data provided by an agent. Moreover, typically, that agent has an interest in the decision that is not perfectly aligned with that of the principal. Thus, the agent may have an incentive to select from or modify the samples he obtains before sending…

Cited by 10 Source ↗PDF ↗Scholar ↗

2019

When Samples Are Strategically Selected

Hanrui Zhang, Yu Cheng, Vincent Conitzer

ICML 2019oral

In standard classification problems, the assumption is that the entity making the decision (the

Cited by 17 Source ↗PDF ↗Scholar ↗