arXiv Machine Learning June 11, 2026 By Wongyu Lee, Francesco Lelli, Omran Ayoub, Massimo Tornatore

Phi-Actor-Critic: Steering General-Sum Games to Pareto-Efficient Correlated Equilibria

Read the original on arXiv Machine Learning →

arXiv:2606. 11284v1 Announce Type: cross Abstract: Real-world multi-agent systems, from traffic coordination to resource allocation, are often modeled as general-sum games where individual incentives conflict with collective welfare.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv AI

Jul 14

World Models as Adversaries: Multi-Agent Self-Play Fine-Tuning for Robust Motion Planning

arXiv:2607. 10630v1 Announce Type: cross Abstract: Robust motion planning in dense traffic requires autonomous vehicles to interact in rare and safety-critical scenarios that are underrepresented in naturalistic driving data.

By Tong Nie, Yuewen Mei, Junlin He, Yihong Tang, Jian Sun, Wei Ma

agents reinforcement-learning fine-tuning benchmarks safety

arXiv Machine Learning

Aug 11

Regret, equilibrium, and learning in games: A guided tour

arXiv:2608. 09389v1 Announce Type: cross Abstract: This note aims to serve as an entry point to the literature on learning in games, a topic with significant theoretical appeal and a wide range of applications -- from machine learning and data science to economics and beyond.

By Panayotis Mertikopoulos

agents reinforcement-learning safety

arXiv Machine Learning

Aug 11

Multi-Agent Reinforcement Learning via Agent-Specific Preference

arXiv:2608. 08604v1 Announce Type: new Abstract: Multi-agent reinforcement learning (MARL) is a powerful framework for solving complex collaborative tasks, but it relies heavily on well-defined global reward functions.

By Ni Mu, Yao Luan, Yiqin Yang, Qing-Shan Jia

agents reinforcement-learning benchmarks

arXiv Machine Learning

Jun 5

DNQ: Deep Nash Q-Network for Partially Observable n-Player Games

arXiv:2606. 06480v1 Announce Type: cross Abstract: Many real-world competitive systems require multiple decision-makers to act simultaneously under shared constraints, limited information, and repeated interaction, as in auctions, resource allocation, and security competition.

By Qintong Xie, Edward Koh, Xavier Cadet, Peter Chin

agents

arXiv Machine Learning

Jun 9

DICE: Entropy-Regularized Equilibrium Selection for Stable Multi-Agent LLM Coordination

arXiv:2606. 08068v1 Announce Type: new Abstract: Multi-agent large language model (LLM) systems often fail to reliably outperform a single strong model equipped with best-of-N sampling.

By Yi Xie, Zhanke Zhou, Chentao Cao, Bo Liu, Bo Han

llms agents fine-tuning benchmarks

arXiv AI

Jul 28

Training with (Swap) Regret Loss in a Single-Layer Self-Attention Model: A Case Study on the Probability Simplex

arXiv:2607. 23333v1 Announce Type: cross Abstract: We revisit the regret loss framework introduced in Park et al.

By Chanwoo Park, Asuman Ozdaglar

Related stories

World Models as Adversaries: Multi-Agent Self-Play Fine-Tuning for Robust Motion Planning

Regret, equilibrium, and learning in games: A guided tour

Multi-Agent Reinforcement Learning via Agent-Specific Preference

DNQ: Deep Nash Q-Network for Partially Observable n-Player Games

DICE: Entropy-Regularized Equilibrium Selection for Stable Multi-Agent LLM Coordination

Training with (Swap) Regret Loss in a Single-Layer Self-Attention Model: A Case Study on the Probability Simplex