EUVIMEDEUVIMED entdecken
Crossref

Evaluating the Architectural Reasoning Capabilities of LLM Provers via the Obfuscated Natural Number Game

Lixing Li

Proceedings of the AAAI Symposium Series · 18.05.2026 · 8 (1) · 588-591

DOI: 10.1609/aaaiss.v8i1.42591 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Symposium Series, online erschienen am 18.05.2026. Verfasst von Lixing Li.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

While Large Language Models have achieved notable success on formal mathematics benchmarks such as MiniF2F, it remains unclear whether these results stem from genuine logical reasoning or semantic pattern matching against pre-training data. This paper identifies Architectural Reasoning—the ability to synthesize formal proofs using exclusively local axioms and definitions within an alien math domain—as the necessary ability for future automated theorem discovery AI. We use the Obfuscated Natural Number Game, a benchmark to evaluate Architectural Reasoning. By renaming identifiers in the Natural Number Game in Lean 4, we created a zero-knowledge, closed environment. We evaluate state-of-the-art models, finding a universal latency tax where obfuscation increases inference time. The results also reveal a divergence in robustness: while general models (Claude-Sonnet-4.5, GPT-4o) suffer performance degradation, reasoning models (DeepSeek-R1, GPT-5, DeepSeek-Prover-V2) maintain the same accuracy despite the absence of semantic cues. These findings provide a quantitative metric for assessing the true capacity for mathematical reasoning.

Zitieren

APA

Li, L. (2026). Evaluating the Architectural Reasoning Capabilities of LLM Provers via the Obfuscated Natural Number Game. Proceedings of the AAAI Symposium Series, 8(1), 588-591. https://doi.org/10.1609/aaaiss.v8i1.42591

Vancouver

Li L. Evaluating the Architectural Reasoning Capabilities of LLM Provers via the Obfuscated Natural Number Game. Proceedings of the AAAI Symposium Series. 2026;8(1):588-591. doi:10.1609/aaaiss.v8i1.42591

BibTeX
@article{Li2026,
  author = {Li, Lixing},
  title = {Evaluating the Architectural Reasoning Capabilities of LLM Provers via the Obfuscated Natural Number Game},
  journal = {Proceedings of the AAAI Symposium Series},
  year = {2026},
  volume = {8},
  number = {1},
  pages = {588--591},
  doi = {10.1609/aaaiss.v8i1.42591}
}
Kostenlos starten →