arXiv:2607. 28632v1 Announce Type: new Abstract: Major mathematical conjectures still depend heavily on expert intuition, so a unified method for the systematic generation and validation of conjectures with substantial mathematical potential remains unavailable.
arXiv:2607. 17388v1 Announce Type: cross Abstract: We investigate the capacity of current language models to contribute to mathematical research.
The paper introduces OpenConjecture, a dataset of mathematical conjectures from arXiv papers since February 2026, and evaluates frontier GPT models on 200 randomly sampled conjectures. The models generate candidate solutions for about 60% of the conjectures, with counterexamples occurring roughly 1.3 times more often than proofs. The study examines solution novelty, citation practices, and fidelity to the original statements, finding that some solutions deviate from authors’ intent and that many proofs closely follow existing results, though some exhibit moderate novelty.
MathAdv is a diagnostic benchmark for formal theorem proving that covers 13 undergraduate- and graduate-level mathematics domains. It includes Lean 4 proofs and up to three auxiliary tasks—multiple-choice questions, fill-in-the-blank problems, and expert-crafted transformations—to probe knowledge, informal reasoning, and robustness to problem presentation. Evaluation of current theorem provers shows formalization is a major bottleneck, performance varies by domain, natural-language guidance can help or hinder models, and equivalent reformulations reveal significant robustness gaps.
arXiv:2606. 10799v1 Announce Type: new Abstract: Large Language Models (LLMs) struggle to rigorously verify complex mathematical proofs.
arXiv:2606. 14838v1 Announce Type: new Abstract: How to define a good explanation is a long-standing philosophical debate which has found recent renewed interest in the context of AI outputs.
arXiv:2609.36663v1 Announce Type: new Abstract: We present GenLimitLib, a source-aligned Lean 4 library for language generation in the limit. Introduced by Kleinberg and Mullainathan at NeurIPS 2024,...
arXiv:2606. 28615v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed in high-stakes domains, where free-text explanations such as chain-of-thought and post-hoc rationales are used to justify model outputs.
arXiv:2608. 15979v1 Announce Type: new Abstract: Large language models produce outputs presented as discoveries - new proofs, conjectures, or molecules.
Large language models produce outputs presented as discoveries - new proofs, conjectures, or molecules. Whether such an output that appears creative is truly original and effective is hard to establis...
arXiv:2611.06962v1 Announce Type: new Abstract: Proof assistants such as Lean check mathematical proofs down to the axioms, and AI agents have recently made writing such proofs cheap. We describe Aut...
The study investigates whether large language models (LLMs) can generalize arithmetic reasoning across different input formats, such as numeric and verbal expressions in English, Spanish, and Italian. By using attribution patching, the researchers identified the specific internal circuits each model employs for numeric versus verbal arithmetic tasks. They found that the degree of overlap between a model’s numeric circuit and its verbal circuit predicts how well the model generalizes to verbal formats, explaining variations in performance across languages and formats without requiring labeled data.