| title | Game Arena: Strategic LLM Evaluation in Competitive Environments |
|---|---|
| authors | Bovard Doerschuk-Tiberi, Yao Yan, Justin Chiu, Hann Wang, Timothy Chung, Martyna Plomecka, John Schultz, Jon Lipovetz, Clayton Drazner, Yuchen Zhuang, Jaimie Hwang, Nate Keating, Riley Jones, Andrew Lee, Oran Kelly, Ian Gemp, Michael Aaron, Laurel Prince, Kate Larson, Jeff Moser, Harrison Jobe, Chad Woodford, Siqi Liu, Andrew Wang, Bo Chang, Christopher D'Mello, Diane Chaleff, Addison Howard, Johnny Yip, Chuck Sugnet, Antonio Gulli, Meghan O'Connell, Will Cukierski, Nenad Tomasev, Dima Yeroshenko, Kinjal Parekh, Roxanne Daniel, Marc Lanctot, Domino Weir, Elsa Dong, Daniel Hennes, Melissa Nalubwama, Robert Fraser, Ryan Trostle, Jun Peng, Tom Mason, Lloyd Hightower, Chiamaka Chukwuka, Yuexiang Zhai, Phoebe Kirk, Yi Su, Yuting Han, Jie Ren, Chris Prichard, Sahand Sharifzadeh, Karim Hakimzadeh, DJ Sterling, Meg Risdal, Kate Olszewska, Ya Xu, Orhan Firat, Minmin Chen |
| date | 2026-09-25 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2609.31473 |
| affiliation | Kaggle |
| upvotes | 11 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf |
| abstract | We introduce Kaggle Game Arena, an open and ever-expanding platform to evaluate large language models (LLMs) through competitive games. Different from static benchmarks, game arena enables models to play head-to-head matchups in structured environments where the gameplay strength naturally increases as models evolve, preventing performance saturation. This technical report details the infrastructure behind Game Arena and describes the three pilot game environments: Chess, Poker, and Werewolf. These environments span perfect information, imperfect information, and multiplayer game settings, enabling a systematic study of models' strategic planning, adaptation, and robustness under uncertainty. For each game, we provide a detailed description of the environment, evaluation metrics, and results from running full competitions across models. Through robust infrastructure and large-scale ground-truth based evaluation, Game Arena ensures reproducibility, transparency and generalizability to new games and variants over time. |
cite
@misc{doerschuktiberi2026game,
title={Game Arena: Strategic LLM Evaluation in Competitive Environments},
author={Bovard Doerschuk-Tiberi and Yao Yan and Justin Chiu and Hann Wang and Timothy Chung and Martyna Plomecka and John Schultz and Jon Lipovetz and Clayton Drazner and Yuchen Zhuang and Jaimie Hwang and Nate Keating and Riley Jones and Andrew Lee and Oran Kelly and Ian Gemp and Michael Aaron and Laurel Prince and Kate Larson and Jeff Moser and Harrison Jobe and Chad Woodford and Siqi Liu and Andrew Wang and Bo Chang and Christopher D'Mello and Diane Chaleff and Addison Howard and Johnny Yip and Chuck Sugnet and Antonio Gulli and Meghan O'Connell and Will Cukierski and Nenad Tomasev and Dima Yeroshenko and Kinjal Parekh and Roxanne Daniel and Marc Lanctot and Domino Weir and Elsa Dong and Daniel Hennes and Melissa Nalubwama and Robert Fraser and Ryan Trostle and Jun Peng and Tom Mason and Lloyd Hightower and Chiamaka Chukwuka and Yuexiang Zhai and Phoebe Kirk and Yi Su and Yuting Han and Jie Ren and Chris Prichard and Sahand Sharifzadeh and Karim Hakimzadeh and DJ Sterling and Meg Risdal and Kate Olszewska and Ya Xu and Orhan Firat and Minmin Chen},
year={2026},
eprint={2609.31473},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2609.31473}
}