arXiv AI September 7, 2026 By Kai Wang, Ge Fan, Chaoyun Zhang, Yuyang Jiang, Yuze Liu

CHAMP: Cross-domain Hybrid Architecture for Matchmaking and Prediction in Online Multi-Player Games

CHAMP is a cross‑domain matchmaking framework for Multiplayer Online Battle Arena games that tackles cold‑start, distribution shift, and data‑scarcity issues by using hybrid player profiles and a Domain‑Aware Win‑rate Network (DAWN). DAWN learns mode‑conditioned representations through a shared network, achieving 67.73% win‑rate prediction accuracy and improving match balance in large‑scale A/B tests. The system reduces imbalanced matches, notably cutting 5‑minute kill crushing rates by up to 20.73% for lower‑tier players.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

efficiency

arXiv Computer Vision

3d ago

MOBA-VL: Event-Localized Multi-Turn Reinforcement Learning for Real-Time MOBA Commentary

arXiv:2609.38428v1 Announce Type: new Abstract: Real-time commentary for Multiplayer Online Battle Arena (MOBA) esports requires a vision-language model (VLM) to narrate a live match second by second...

By Shengyun Zhong, Xinkang Zhao, Ziyuan Chu, Linchao Zhu

llms reinforcement-learning fine-tuning multimodal benchmarks

arXiv AI

Jul 2

Play Like Champions: Counterfactual Feedback Generation in Latent Space

arXiv:2607. 00190v1 Announce Type: cross Abstract: Recent advances in reinforcement learning have produced superhuman agents across a wide range of competitive games.

By Andrzej Bia{\l}ecki, Adam Mastalerz, Han Zhou

agents diffusion reinforcement-learning

arXiv Machine Learning

1d ago

Faynt: Scaling and Optimizing Policies for Competitive Melee

Faynt is a family of Transformer policies (10M and 75M parameters) that control all 26 characters in Super Smash Bros. Melee from a single checkpoint. After reinforcement learning, the 10M model wins 98.4% of same‑character games against fourteen specialist and multi‑character releases, and defeats a zero‑delay Slippi‑AI model in all 68 evaluated games. The work details architecture, scaling, hyperparameter transfer, supervised pretraining on 840,000 human replays, post‑training curricula, distillation, and efficient inference, and it releases the weights, benchmark suites, and a platform for automated model tournaments.

By Ali Janati, Nikita Kuzmin, Rohit Swamy, Charles Niu

llms reinforcement-learning efficiency benchmarks

arXiv AI

3d ago

STRATA: Self-Learning Through Role-Aligned Tiered Agents for Real-Time Strategy Games

arXiv:2609.38881v1 Announce Type: new Abstract: Real-time strategy (RTS) games require agents to coordinate economic development, production and construction, base defense, unit organization, and att...

By Xinhe Tian, Xiaoyue Zhang, Ziyou Zhang, Jiacheng Li, Xiaoqiang Jin, Qianchuan Zhao, Gaochen Cui

llms agents efficiency

arXiv Machine Learning

Jul 15

A Replicate-and-Quantize Strategy for Plug-and-Play Load Balancing of Sparse Mixture-of-Experts LLMs

arXiv:2602. 19938v2 Announce Type: replace Abstract: Sparse Mixture-of-Experts (SMoE) architectures are increasingly used to scale large language models efficiently, delivering strong accuracy under fixed compute budgets.

By Zijie Liu, Jie Peng, Jinhao Duan, Zirui Liu, Kaixiong Zhou, Mingfu Liang, Luke Simon, Xi Liu, Zhaozhuo Xu, Tianlong Chen

llms efficiency benchmarks

arXiv Machine Learning

Jul 21

PLayer-FL: A Principled Approach to Personalized Layer-wise Cross-Silo Federated Learning

arXiv:2502. 08829v2 Announce Type: replace Abstract: Federated learning (FL) with non-IID data often degrades client performance below local training baselines.

By Ahmed Elhussein, Florent Pollet, Gamze G\"ursoy

efficiency

One email a morning, machine-written

Related stories

MOBA-VL: Event-Localized Multi-Turn Reinforcement Learning for Real-Time MOBA Commentary

Play Like Champions: Counterfactual Feedback Generation in Latent Space

Faynt: Scaling and Optimizing Policies for Competitive Melee

STRATA: Self-Learning Through Role-Aligned Tiered Agents for Real-Time Strategy Games

A Replicate-and-Quantize Strategy for Plug-and-Play Load Balancing of Sparse Mixture-of-Experts LLMs

PLayer-FL: A Principled Approach to Personalized Layer-wise Cross-Silo Federated Learning