Metraipolis › archive › dc_71fb31fa44e1

Game Arena: Strategic LLM Evaluation in Competitive Environments — arXiv:2609.31473

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.31473
License (as archived)
CC0-1.0
Archived
2026-10-08T01:38:44.117Z
SHA-256 of the archived text
c183967bc85a3fb22744610758d5801ffb00862d8b99800c3a63e25a450ed74e
Stable URL of this page
https://metraipolis.com/documento/dc_71fb31fa44e1

How to cite

Game Arena: Strategic LLM Evaluation in Competitive Environments — arXiv:2609.31473 — arXiv (en), https://arxiv.org/abs/2609.31473 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_71fb31fa44e1 (Metraipolis archive dc_71fb31fa44e1, sha256 c183967bc85a3fb22744610758d5801ffb00862d8b99800c3a63e25a450ed74e)
BibTeX
@misc{dc71fb31fa44e1,
  title = {Game Arena: Strategic LLM Evaluation in Competitive Environments — arXiv:2609.31473},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.31473},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_71fb31fa44e1; sha256 c183967bc85a3fb22744610758d5801ffb00862d8b99800c3a63e25a450ed74e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.31473. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-28 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.31473 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-08T01:12:14.383Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).