Metraipolis › archive › dc_0bf8f12ae442

Modular Discovery of General Game-Playing Algorithms with Large Language Models — arXiv:2609.33115

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.33115
License (as archived)
CC0-1.0
Archived
2026-10-07T20:54:09.598Z
SHA-256 of the archived text
6854e8e771ed71378e8b396b6b53e4979f4a69d01c2f8c00f8a1d0e32cf1ee53
Stable URL of this page
https://metraipolis.com/documento/dc_0bf8f12ae442

How to cite

Modular Discovery of General Game-Playing Algorithms with Large Language Models — arXiv:2609.33115 — arXiv (en), https://arxiv.org/abs/2609.33115 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0bf8f12ae442 (Metraipolis archive dc_0bf8f12ae442, sha256 6854e8e771ed71378e8b396b6b53e4979f4a69d01c2f8c00f8a1d0e32cf1ee53)
BibTeX
@misc{dc0bf8f12ae442,
  title = {Modular Discovery of General Game-Playing Algorithms with Large Language Models — arXiv:2609.33115},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.33115},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0bf8f12ae442; sha256 6854e8e771ed71378e8b396b6b53e4979f4a69d01c2f8c00f8a1d0e32cf1ee53},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.33115. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

General Game Playing across arbitrary games from rules alone remains challenging due to differing algorithmic requirements across game classes and strict decision-time constraints. Rather than hand-designing search heuristics for specific domains, can we leverage Large Language Models (LLMs) to discover general game-playing algorithms? Because language models can propose and refactor structured code, they provide an expressive proposal engine for exploring the space of algorithmic designs. We introduce a multi-agent LLM meta-learning system to co-evolve game-agnostic procedural search mechanisms in C++ alongside domain heuristics synthesized directly from game rules. Controlling the compute budget, we benchmark the discovered mechanisms across more than 400 diverse environments, including OpenSpiel training and held-out games, procedural simulation engines, and games with deep neural policy-value representations trained via PPO. Evaluated via AlphaRank stationary distributions and Soft Condorcet Optimization (SCO) against 15 established MCTS baselines, the discovered search mechanisms consistently achieve top-tier ratings and pairwise ballot majorities over most baselines across independent evolutionary runs, generalizing to unseen human-designed and procedurally synthesized games and remaining competitive with baselines on frozen neural network representations.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.MA).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computer Science and Game Theory (cs.GT); Multiagent Systems (cs.MA).
Pagina del lavoro: https://arxiv.org/abs/2609.33115 — 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 2026-10-07T20:24:41.688Z dalla pagina https://arxiv.org/catchup/cs.MA/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).