2.9k citations · 2.9k across the 22 of their papers we have counts for
24 papers
Test-Time Strategies for More Efficient and Accurate Agentic RAG
Brian Zhang, Deepti Guntur, Zhiyang Zuo +7
Retrieval-Augmented Generation (RAG) systems face challenges with complex, multihop questions, and agentic frameworks such as Search-R1 (Jin et al., 2025), which operates iterative…
Decision Making under Imperfect Recall: Algorithms and Benchmarks
Emanuel Tewolde, Brian Hu Zhang, Ioannis Anagnostides +2
In game theory, imperfect-recall decision problems model situations in which an agent forgets information it held before. They encompass games such as the ``absentminded driver'' a…
The Complexity of Proper Equilibrium in Extensive-Form and Polytope Games
Brian Hu Zhang, Ioannis Anagnostides, Kiriaki Fragkia +2
The proper equilibrium, introduced by Myerson (1978), is a classic refinement of the Nash equilibrium that has been referred to as the "mother of all refinements." For normal-form…
OpenAI GPT-5 System Card
Aaditya Singh, Adam Fry, Adam Perelman +483
This is the system card published alongside the OpenAI GPT-5 launch, August 2025. GPT-5 is a unified system with a smart and fast model that answers most questions, a deeper reason…
Convergence of Regret Matching in Potential Games and Constrained Optimization
Ioannis Anagnostides, Emanuel Tewolde, Brian Hu Zhang +3
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…
The Complexity of Equilibrium Refinements in Potential Games
Ioannis Anagnostides, Maria-Florina Balcan, Kiriaki Fragkia +3
The complexity of computing equilibrium refinements has been at the forefront of algorithmic game theory research, but it has remained open in the seminal class of potential games;…
Scale-Invariant Regret Matching and Online Learning with Optimal Convergence: Bridging Theory and Practice in Zero-Sum Games
Brian Hu Zhang, Ioannis Anagnostides, Tuomas Sandholm
A considerable chasm has been looming for decades between theory and practice in zero-sum game solving through first-order methods. Although a convergence rate of has long…
gpt-oss-120b & gpt-oss-20b Model Card
OpenAI, :, Sandhini Agarwal +124
We present gpt-oss-120b and gpt-oss-20b, two open-weight reasoning models that push the frontier of accuracy and inference cost. The models use an efficient mixture-of-expert trans…
TrajFlow: Multi-modal Motion Prediction via Flow Matching
Qi Yan, Brian Zhang, Yutong Zhang +8
Efficient and accurate motion prediction is crucial for ensuring safety and informed decision-making in autonomous driving, particularly under dynamic real-world conditions that ne…
General search techniques without common knowledge for imperfect-information games, and application to superhuman Fog of War chess
Brian Hu Zhang, Tuomas Sandholm
Since the advent of AI, games have served as progress benchmarks. Meanwhile, imperfect-information variants of chess have existed for over a century, present extreme challenges, an…
LithOS: An Operating System for Efficient Machine Learning on GPUs
Patrick H. Coppock, Brian Zhang, Eliot H. Solomon +6
The surging demand for GPUs in datacenters for machine learning (ML) has made efficient GPU utilization crucial. However, meeting the diverse needs of ML models while optimizing re…
A Polynomial-Time Algorithm for Variational Inequalities under the Minty Condition
Ioannis Anagnostides, Gabriele Farina, Tuomas Sandholm +1
Solving (Stampacchia) variational inequalities (SVIs) is a foundational problem at the heart of optimization. However, this expressivity comes at the cost of computational hardness…
Learning a Game by Paying the Agents
Brian Hu Zhang, Tao Lin, Yiling Chen +1
We study the problem of learning the utility functions of no-regret learning agents in a repeated normal-form game. Differing from most prior literature, we introduce a principal w…
Expected Variational Inequalities
Brian Hu Zhang, Ioannis Anagnostides, Emanuel Tewolde +4
Variational inequalities (VIs) encompass many fundamental problems in diverse areas ranging from engineering to economics and machine learning. However, their considerable expressi…
Computing Game Symmetries and Equilibria That Respect Them
Emanuel Tewolde, Brian Hu Zhang, Caspar Oesterheld +2
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…
Learning and Computation of -Equilibria at the Frontier of Tractability
Brian Hu Zhang, Ioannis Anagnostides, Emanuel Tewolde +4
-equilibria -- and the associated notion of -regret -- are a powerful and flexible framework at the heart of online learning and game theory, whereby enriching the set of dev…
Iteratively Regularized Gradient Tracking Methods for Optimal Equilibrium Seeking
Yuyang Qiu, Farzad Yousefian, Brian Zhang
In noncooperative Nash games, equilibria are often inefficient. This is exemplified by the Prisoner's Dilemma and was first provably shown in the 1980s. Since then, understanding t…
Polynomial-Time Optimal Equilibria with a Mediator in Extensive-Form Games
Brian Hu Zhang, Tuomas Sandholm
For common notions of correlated equilibrium in extensive-form games, computing an optimal (e.g., welfare-maximizing) equilibrium is NP-hard. Other equilibrium notions -- communica…
Optimal Correlated Equilibria in General-Sum Extensive-Form Games: Fixed-Parameter Algorithms, Hardness, and Two-Sided Column-Generation
Brian Zhang, Gabriele Farina, Andrea Celli +1
We study the problem of finding optimal correlated equilibria of various sorts in extensive-form games: normal-form coarse correlated equilibrium (NFCCE), extensive-form coarse cor…
Polynomial-Time Sum-of-Squares Can Robustly Estimate Mean and Covariance of Gaussians Optimally
Pravesh K. Kothari, Peter Manohar, Brian Hu Zhang
In this work, we revisit the problem of estimating the mean and covariance of an unknown -dimensional Gaussian distribution in the presence of an -fraction of adver…
Team Correlated Equilibria in Zero-Sum Extensive-Form Games via Tree Decompositions
Brian Hu Zhang, Tuomas Sandholm
Despite the many recent practical and theoretical breakthroughs in computational game theory, equilibrium finding in extensive-form team games remains a significant challenge. Whil…
Coconuts and Islanders: A Statistics-First Guide to the Boltzmann Distribution
Brian Zhang
The Boltzmann distribution is one of the key equations of thermal physics and is widely used in machine learning as well. Here I derive a Boltzmann distribution in a simple pedagog…
Zap: Making Predictions Based on Online User Behavior
Yuri Chervonyi, Dragos Harabor, Brian Zhang +1
This paper introduces Zap, a generic machine learning pipeline for making predictions based on online user behavior. Zap combines well known techniques for processing sequential da…
The Kinetics Human Action Video Dataset
Will Kay, Joao Carreira, Karen Simonyan +9
We describe the DeepMind Kinetics human action video dataset. The dataset contains 400 human action classes, with at least 400 video clips for each action. Each clip lasts around 1…