[ICLR'26] MARSHAL: Incentivizing Multi-Agent Reasoning via Self-Play with Strategic LLMs

RLinf: Reinforcement Learning Infrastructure for Embodied and Agentic AI

An Open-Source Large-Scale Reinforcement Learning Project for Search Agents

Code release for "A Testbed for Multi-Drone Volleyball Game Combining Motion Control and Strategic Play" (NeurIPS 2025), https://arxiv.org/abs/2502.01932

VS-Bench: Evaluating VLMs for Strategic Reasoning and Decision-Making in Multi-Agent Environments

A Simple, Distributed and Asynchronous Multi-Agent Reinforcement Learning Framework for Google Research Football AI.