| A counterexample to Han's conjecture | Algebra, Algebraic Geometry, LLM | arXiv 2026 | |
| A dual linear programming bound for sphere packing in dimension 36 | Discrete Geometry, Number Theory, LLM | arXiv 2026 | Code |
| A Machine Learning Approach That Beats Large Rubik's Cubes | Graph Theory, Group Theory, RL | NeurIPS 2025 | Code arXiv |
| A Machine Learning Approach to the Nirenberg Problem | Differential Geometry, PINN | arXiv 2026 | Code |
| A Separable Banach Space with a Schauder Basis Which Is Not a Lipschitz Retract of Its Bidual | Analysis, LLM | arXiv 2026 | |
| A Systematization of the Wagner Framework: Graph Theory Conjectures and Reinforcement Learning | Graph Theory, RL | Discovery Science 2025 | Code arXiv |
| ABC implies that Ramanujan's tau function misses almost all primes | Number Theory, ATP | Indagationes Mathematicae 2026 | Code arXiv |
| Accelerating mathematical research with language models: A case study of an interaction with GPT-5-Pro on a convex analysis problem | Analysis, LLM | arXiv 2025 | Chat Logs |
| Advancing mathematics by guiding human intuition with AI | Knot Theory, Representation Theory | Nature 2021 | Code |
| Advancing Mathematics Research with AI-Driven Formal Proof Search | ATP, LLM | arXiv 2026 | Code |
| Agentic Neurosymbolic Collaboration for Mathematical Discovery: A Case Study in Combinatorial Design | Combinatorics, LLM, ATP | arXiv 2026 | |
| AI Co-Mathematician: Accelerating Mathematicians with Agentic AI | Group Theory, Representation Theory, LLM | arXiv 2026 | |
| AI Finds A Way | Survey, RL, LLM | arXiv 2026 | Anecdotes |
| AI for Mathematics: Progress, Challenges, and Prospects | Survey | arXiv 2026 | |
| AI Mathematician as a Partner in Advancing Mathematical Discovery -- A Case Study in Homogenization Theory | Analysis, LLM | arXiv 2025 | Chat Logs |
| AI Mathematician: Towards Fully Automated Frontier Mathematical Research | Analysis, LLM | arXiv 2025 | Chat Logs |
| AI-driven research in pure mathematics and theoretical physics | Survey | Nature Reviews Physics 2025 | |
| Aletheia tackles FirstProof autonomously | LLM, Benchmark | arXiv 2026 | Chat Logs |
| Algebraic geometric framework of Rogers--Ramanujan identities | Number Theory, Combinatorics, Representation Theory, Algebraic Geometry, ATP | arXiv 2026 | Code |
| Algorithm Discovery With LLMs: Evolutionary Search Meets Reinforcement Learning | Combinatorics, LLM, RL | arXiv 2025 | Code |
| Algorithm-assisted discovery of an intrinsic order among mathematical constants | Number Theory | PNAS 2024 | Code |
| Almost all primes are partially regular | Number Theory, ATP | Archiv der Mathematik 2026 | Code arXiv |
| AlphaEvolve: A coding agent for scientific and algorithmic discovery | Matrix Multiplication, Analysis, Combinatorics, Discrete Geometry, LLM | arXiv 2025 | Unofficial Code |
| AlphaTensor: Discovering faster matrix multiplication algorithms | Matrix Multiplication, RL | Nature 2022 | Code Blog |
| An algorithm for Aubert-Zelevinsky duality à la Mœglin-Waldspurger | Representation Theory, Neural Network | arXiv 2025 | Code |
| An automated proof that R(B_8,B_10)=37 | Combinatorics, LLM, ATP | arXiv 2026 | Code |
| An equidistribution conjecture for quotient-closed and submodule-closed subcategories | Representation Theory, Algebra, Combinatorics, LLM, ATP | arXiv 2026 | Code |
| An example of a very non-movable effective divisor | Algebraic Geometry, LLM | arXiv 2026 | |
| An explicit refined Gan--Gross--Prasad identity for Fourier--Jacobi periods of degree 2 Siegel cusp forms | Number Theory, LLM | arXiv 2026 | |
| An ML approach to resolution of singularities | Algebraic Geometry, RL | TAG-ML 2023 | Code |
| Aristotle: IMO-level Automated Theorem Proving | ATP, LLM | arXiv 2025 | |
| Arithmetic volumes of moduli stacks of Shtukas | Number Theory, Algebraic Geometry, LLM | arXiv 2026 | Chat Logs |
| Artificial intelligence and machine learning generated conjectures with TxGraffiti | Graph Theory, Combinatorics | arXiv 2024 | Code |
| Artificial Intelligence and the Structure of Mathematics | Survey | arXiv 2026 | |
| Artificial Intelligence for Mathematical Reasoning: An Integrated Survey of Language Models, Neuro-symbolic Systems, and Verified Discovery | Survey | arXiv 2026 | Code |
| Automated Conjecture Resolution with Formal Verification | LLM, ATP | arXiv 2026 | Code (Rethlas), Code (Archon), Code (Lean) |
| Automated Search for Conjectures on Mathematical Constants using Analysis of Integer Sequences | Number Theory | ICML 2023 | Code |
| Autonomous disproofs of the sum-product conjecture over $\mathbb R$ with GPT-5.5 Pro | Combinatorics, Number Theory, LLM | arXiv 2026 | Code |
| Benchmarks in Leipzig | Benchmark, LLM | arXiv 2026 | |
| Beyond Mock Modularity: Elliptic Corrections for Higher Dyson Ranks | Combinatorics, Number Theory, ATP | arXiv 2026 | Code |
| Can Transformers Do Enumerative Geometry? | Algebraic Geometry, Interpretability, Transformer | ICLR 2025 | Code |
| CayleyPy RL: Pathfinding and Reinforcement Learning on Cayley Graphs | Graph Theory, Group Theory, RL | Advances in Theoretical and Mathematical Physics 2026 | Code arXiv |
| Certifying Arithmeticity for Two Degree-Six Symplectic Hypergeometric Monodromy Groups | Number Theory, LLM | arXiv 2026 | Code |
| ComBench: A Benchmark for Rigorous Proof Reasoning and Constructive Realization in Olympiad-Level Combinatorics | Benchmark, Combinatorics, LLM | arXiv 2026 | |
| Constructions in combinatorics via neural networks | Graph Theory, RL | arXiv 2021 | Code |
| Counterexample to majority optimality in NICD with erasures | Analysis, LLM | arXiv 2025 | |
| Counting partial Hadamard matrices in the cubic regime | Combinatorics, LLM | arXiv 2026 | |
| Data-scientific study of Kronecker coefficients | Representation Theory, PCA | Experimental Mathematics 2023 | |
| Dead ends in square-free digit walks | Number Theory, ATP | arXiv 2026 | Code |
| Decision trees, Frobenius traces, and Weierstrass coefficients of elliptic curves | Number Theory, Decision Tree, Transformer, Interpretability, LLM | arXiv 2026 | Code |
| Deep Learning for Symbolic Mathematics | Differential Equations, Symbolic Computation, Transformer | ICLR 2020 | Code |
| Deep Reinforcement Learning for Fano Hypersurfaces | Algebraic Geometry, RL | arXiv 2026 | Code |
| Digesting the proof of the sharp thin-shell inequality | Geometry, Analysis, Probability, LLM | arXiv 2026 | Chat Logs |
| Discovery of Unstable Singularities | Differential Equations, PINN | arXiv 2025 | |
| Does My Embedding Reflect That A = B? Evaluating Mathematical Equivalence in Embedding Models | Benchmark, ATP, LLM | arXiv 2026 | |
| Doubly Saturated Ramsey Graphs: A Case Study in Computer-Assisted Mathematical Discovery | Combinatorics, LLM, ATP | arXiv 2026 | |
| E6-local systems from cubic threefolds | Algebraic Geometry, LLM | arXiv 2026 | |
| Early science acceleration experiments with GPT-5 | Combinatorics, Optimization Theory, LLM | arXiv 2025 | Chat Logs |
| Eigenweights for arithmetic Hirzebruch Proportionality | Number Theory, Representation Theory, LLM | PNAS Nexus 2026 | Chat Logs arXiv |
| Equality in Fill's spectral gap problem | Combinatorics, LLM | arXiv 2026 | |
| EternalMath: A Living Benchmark of Frontier Mathematics that Evolves with Human Discovery | Benchmark, LLM | arXiv 2026 | |
| Even with AI, Bijection Discovery is Still Hard: The Opportunities and Challenges of OpenEvolve for Novel Bijection Construction | Combinatorics, LLM | arXiv 2025 | |
| Every finite group admits a just finite presentation | Group Theory, LLM | arXiv 2026 | |
| Every string has probabilistic automatic complexity at most three | Automata Theory, LLM, ATP | arXiv 2026 | Code |
| Evolving Local Corrections for Global Constructions in Combinatorics | Combinatorics, LLM | arXiv 2026 | |
| Evolving Ranking Functions for Canonical Blow-Ups in Positive Characteristic | Algebraic Geometry, LLM | arXiv 2026 | |
| Extremal Chowla sets and their linear analogues: A human-AI mathematical investigation using Co-Scientist | Number Theory, Group Theory, LLM | arXiv 2026 | |
| Extremal descendant integrals on moduli spaces of curves: An inequality discovered and proved in collaboration with AI | Algebraic Geometry, ATP, LLM | arXiv 2025 | Code Chat Logs |
| Fel's Conjecture on Syzygies of Numerical Semigroups | Combinatorics, Algebra, Number Theory, ATP | Journal of Combinatorial Theory, Series A 2026 | Code arXiv |
| FIMO: A Challenge Formal Dataset for Automated Theorem Proving | Benchmark, ATP | arXiv 2023 | |
| Finding Kissing Numbers with Game-theoretic Reinforcement Learning | Discrete Geometry, RL | arXiv 2025 | Code |
| First Proof | Benchmark, LLM | arXiv 2026 | Website |
| First Proof Second Batch | Benchmark, LLM | arXiv 2026 | |
| Flow-based Extremal Mathematical Structure Discovery | Combinatorics, Transformer, Discrete Geometry, RL | arXiv 2026 | Code |
| FlowBoost Reveals Phase Transitions and Spectral Structure in Finite Free Information Inequalities | Analysis | arXiv 2026 | |
| Forbidden Sidon subsets of perfect difference sets, featuring a human-assisted proof | Combinatorics, Number Theory, LLM, ATP | Proceedings of the National Academy of Sciences 2026 | Code arXiv |
| Formal Conjectures: An Open and Evolving Benchmark for Verified Discovery in Mathematics | Benchmark, ATP | arXiv 2026 | Code |
| Formalized $q$-series: The Rogers-Ramanujan Identities and Beyond | Number Theory, Combinatorics, ATP | arXiv 2026 | Code |
| Formalizing Mathematics at Scale | ATP, LLM | arXiv 2026 | Code (AutoformBot) Code (Atlas) |
| FormalMATH: Benchmarking Formal Mathematical Reasoning of Large Language Models | Benchmark, ATP, LLM | arXiv 2025 | Website |
| Four-digit Kaprekar dynamics in odd bases | Number Theory, Combinatorics, ATP | arXiv 2026 | |
| From Black Box to Bijection: Interpreting Machine Learning to Build a Zeta Map Algorithm | Combinatorics, Transformer | arXiv 2025 | |
| From Euler to AI: Unifying Formulas for Mathematical Constants | Number Theory, LLM | NeurIPS 2025 | Code arXiv |
| FrontierMath: A Benchmark for Evaluating Advanced Mathematical Reasoning in AI | Benchmark, LLM | arXiv 2024 | Website |
| GAUSS: Benchmarking Structured Mathematical Skills for Large Language Models | Benchmark, LLM | arXiv 2025 | Website |
| Generating conjectures on fundamental constants with the Ramanujan Machine | Number Theory | Nature 2021 | Code |
| Generating Special Triangulations with Transformers | Mathematical Physics, Algebraic Geometry, Transformer | arXiv 2026 | |
| Generative AI for brane configurations and coamoeba | Mathematical Physics, VAE | Physical Review D 2025 | |
| Generative Modeling for Mathematical Discovery | Combinatorics, Number Theory, LLM | Advances in Theoretical and Mathematical Physics 2026 | Code arXiv |
| Geometric Generality of Transformer-Based Gröbner Basis Computation | Algebraic Geometry, Transformer | Artificial Intelligence and Mathematics Research 2026 | arXiv |
| Global Lyapunov functions: a long-standing open problem in mathematics, with symbolic transformers | Differential Equations, Transformer | NeurIPS 2024 | Code |
| Gödel Test: Can Large Language Models Solve Easy Conjectures? | Discrete Mathematics, LLM | arXiv 2025 | |
| HARDMath: A Benchmark Dataset for Challenging Problems in Applied Mathematics | Benchmark, LLM | arXiv 2024 | Code |
| Hierarchical Reinforcement Learning for Sparse-Reward Search in Commutative Algebra | Commutative Algebra, Combinatorics, RL, Neural Network | ICML 2026 | Code |
| Hilbert series, machine learning, and applications to physics | Algebraic Geometry, Mathematical Physics, Neural Network | Physics Letters B 2024 | Code |
| How Twist Class Redundancy Drives the Prediction of Traces of Frobenius of Elliptic Curves | Number Theory, Benchmark, Transformer | arXiv 2026 | Dataset |
| Humanity's Last Exam | Benchmark, LLM | Nature 2026 | Website arXiv |
| Illuminating new and known relations between knot invariants | Knot Theory, Neural Network | Machine Learning: Science and Technology 2024 | Code arXiv |
| IMProofBench: Benchmarking AI on Research-Level Mathematical Proof Generation | Benchmark, LLM | arXiv 2025 | Website |
| Improving the matrix multiplication exponent with modern optimization and AlphaEvolve | Matrix Multiplication, Computational Complexity, Optimization Theory, LLM | arXiv 2026 | |
| In between myth and reality: AI for math -- a case study in category theory | Survey, LLM | arXiv 2025 | |
| Inclusions between p-bounded crystalline loci in dimension two | Algebraic Geometry, Number Theory, LLM, ATP | arXiv 2026 | Artifacts Code |
| Int2Int: a framework for mathematics with transformers | Number Theory, Transformer | Advances in Theoretical and Mathematical Physics 2026 | Code arXiv |
| Interpretable Machine Learning for Kronecker Coefficients | Representation Theory, Neural Network, Symbolic Computation, PCA, Transformer | Advances in Theoretical and Mathematical Physics 2026 | arXiv |
| Irrationality of rapidly converging series: a problem of Erdős and Graham | Number Theory, LLM | Bulletin of the London Mathematical Society 2026 | Chat Logs arXiv |
| Iteris: Agentic Research Loops for Computational Mathematics | Numerical Analysis, LLM | arXiv 2026 | Code |
| k-Coloring is Faster than Computing the Chromatic Number | Graph Theory, Computational Complexity, LLM | arXiv 2026 | Chat Logs |
| Lattice-Valued Bottleneck Duality | Combinatorics | arXiv 2024 | |
| LeanMarathon: Toward Reliable AI Co-Mathematicians through Long-Horizon Lean Autoformalization | ATP, LLM | arXiv 2026 | Code |
| LEAP: Supercharging LLMs for Formal Mathematics with Agentic Frameworks | ATP, LLM | arXiv 2026 | |
| Learning Euler factors of elliptic curves | Number Theory, Transformer | Advances in Theoretical and Mathematical Physics 2026 | arXiv |
| Learning Fast Monomial Orders for Gröbner Basis Computations | Algebraic Geometry, Symbolic Computation, RL | arXiv 2026 | Code |
| Learning Formal Mathematics From Intrinsic Motivation | ATP, LLM | NeurIPS 2024 | Code arXiv |
| Learning Fricke signs from Maass form Coefficients | Number Theory, LDA | Advances in Theoretical and Mathematical Physics 2026 | arXiv |
| Learning knot invariants across dimensions | Knot Theory, Neural Network | SciPost Physics 2023 | Code arXiv |
| Learning the Inverse Ryu--Takayanagi Formula with Transformers | Mathematical Physics, Transformer | JHEP 2026 | Code arXiv |
| Learning to compute Gröbner Basis | Algebraic Geometry, Transformer | NeurIPS 2024 | Code |
| Learning Topological Invariance | Knot Theory, Neural Network, Transformer | arXiv 2025 | |
| LemmaBench: A Live, Research-Level Benchmark to Evaluate LLM Capabilities in Mathematics | Benchmark, LLM | arXiv 2026 | |
| Lift-independence problem in the $P$-adic Simpson correspondence for curves | Algebraic Geometry, Number Theory | arXiv 2026 | Code (Rethlas) |
| Linear algebra with transformers | Linear Algebra, Symbolic Computation, Transformer | TMLR 2022 | Code |
| Linear dependence of time-frequency shifts of a Schwartz function | Analysis, LLM | arXiv 2026 | Code |
| Local cohomology modules with nonclosed support | Commutative Algebra, Algebraic Geometry, LLM | arXiv 2026 | |
| Lower bounds for multivariate independence polynomials and their generalisations | Combinatorics, LLM | arXiv 2026 | Chat Logs |
| MA-ProofBench: A Two-Tiered Evaluation of LLMs for Theorem Proving in Mathematical Analysis | Benchmark, ATP, LLM | arXiv 2026 | |
| Machine Learning Approaches to the Shafarevich-Tate Group of Elliptic Curves | Number Theory, Neural Network, Decision Tree | IJDSMS 2024 | Code |
| Machine learning assisted exploration for affine Deligne-Lusztig varieties | Number Theory, Representation Theory | Peking Math J 2024 | Code |
| Machine learning BPS spectra and the gap conjecture | Mathematical Physics, PCA | Physical Review D 2024 | |
| Machine learning Calabi-Yau hypersurfaces | Mathematical Physics | Physical Review D 2022 | |
| Machine learning class numbers of real quadratic fields | Number Theory, Interpretability | IJDSMS 2023 | |
| Machine learning detects terminal singularities | Algebraic Geometry | NeurIPS 2023 | Code Talk |
| Machine learning for complete intersection Calabi-Yau manifolds: a methodological study | Mathematical Physics | Physical Review D 2021 | |
| Machine learning for modular multiplication | Number Theory, Transformer | Research Directions in Number Theory 2026 | Code arXiv |
| Machine Learning in the String Landscape | Mathematical Physics | JHEP 2017 | |
| Machine learning invariants of arithmetic curves | Number Theory, Logistic Regression, Random Forest | Journal of Symbolic Computation 2023 | |
| Machine Learning Kreuzer–Skarke Calabi–Yau Threefolds | Mathematical Physics, Algebraic Geometry, Neural Network | International Journal of Modern Physics A 2025 | arXiv |
| Machine learning Kronecker coefficients | Representation Theory, CNN, Decision Tree | IJDSMS 2023 | |
| Machine learning line bundle cohomologies of hypersurfaces in toric varieties | Algebraic Geometry | Physics Letters B 2019 | |
| Machine Learning Number Fields | Number Theory, Neural Network, Random Forest | MCGD 2022 | |
| Machine learning of Calabi-Yau volumes | Mathematical Physics, CNN, Linear Regression | Physical Review D 2017 | |
| Machine learning Sasakian G2 topology on contact Calabi-Yau 7-manifolds | Mathematical Physics, Neural Network | Physics Letters B 2024 | Code |
| Machine learning the dimension of a Fano variety | Algebraic Geometry | Nature Communications 2023 | Code |
| Machine Learning the vanishing order of rational L-functions | Number Theory, LDA, Neural Network | Advances in Theoretical and Mathematical Physics 2026 | arXiv |
| Machine-learning dessins d'enfants: explorations via modular and Seiberg–Witten curves | Algebraic Geometry, Mathematical Physics | Journal of Physics A 2021 | |
| Machine-learning Sato-Tate conjecture | Number Theory | Journal of Symbolic Computation 2022 | |
| Machines Learn Number Fields, But How? The Case of Galois Groups | Number Theory, Logistic Regression, Decision Tree, Interpretability | Research in the Mathematical Sciences 2026 | Code arXiv |
| Mapping Uncharted Symmetries: Machine Discovery in Combinatorics | Combinatorics, Representation Theory, Neural Network, ATP | arXiv 2026 | Code |
| Mathematical Capabilities of ChatGPT | Benchmark, LLM | NeurIPS 2023 | Code arXiv |
| Mathematical discoveries from program search with large language models | Combinatorics, LLM | Nature 2024 | Code |
| Mathematical discovery in the age of artificial intelligence | Survey | Nature Physics 2025 | |
| Mathematical exploration and discovery at scale | Combinatorics, Analysis, Number Theory, Discrete Geometry, LLM | arXiv 2025 | Code |
| Mathematical methods and human thought in the age of AI | Survey | arXiv 2026 | |
| MiniF2F: a cross-system benchmark for formal Olympiad-level mathematics | Benchmark, ATP | ICLR 2022 | |
| Modularity of Point Counts for the Curves $X^a=Y^b$: New Rogers--Ramanujan Identities | Number Theory, Combinatorics, Representation Theory, ATP | arXiv 2026 | Code |
| Murmurations of Elliptic Curves | Number Theory, PCA | Experimental Mathematics 2024 | Quanta |
| Neural network approximations for Calabi-Yau metrics | Mathematical Physics, Neural Network | JHEP 2022 | |
| New Calabi–Yau manifolds from genetic algorithms | Algebraic Geometry, Mathematical Physics, Genetic Algorithm | Physics Letters B 2024 | |
| New Lower and Upper Bounds for the Grothendieck Constant | Computational Complexity, Optimization Theory, LLM | arXiv 2026 | Code |
| New Records for the Hadamard Maximal Determinant Problem in Dimensions 51, 107, and 115 | Combinatorics, RL | arXiv 2026 | Code |
| No compromise in the liquid drop model | Differential Geometry, Mathematical Physics, Analysis, LLM | arXiv 2026 | |
| Non-uniqueness for a differential equation and a proof by ChatGPT | Analysis, LLM | arXiv 2026 | Chat Logs |
| Off-diagonal Ramsey numbers | Combinatorics, LLM | arXiv 2026 | |
| Olympiad-level formal mathematical reasoning with reinforcement learning | RL, ATP | Nature 2025 | |
| On (not) learning the Möbius function | Number Theory | arXiv 2026 | |
| On the paucity of lattice triangles | Geometry, Number Theory, Combinatorics, ATP | arXiv 2026 | Code |
| On the Quartic Invariant of Odd Degree Binary Forms | Algebraic Geometry, Number Theory, LLM, ATP | arXiv 2026 | Code |
| On two counterexamples in the geometry of numbers | Discrete Geometry, Number Theory, LLM | arXiv 2026 | |
| Optimal bounds for an Erdős problem on matching integers to distinct multiples | Number Theory, Combinatorics, ATP | arXiv 2026 | Code |
| Parity of k-differentials in genus zero and one | Algebraic Geometry, Number Theory, ATP | arXiv 2026 | Code |
| PatternBoost: Constructions in Mathematics with a Little Help from AI | Discrete Geometry, Combinatorics, Transformer, RL | arXiv 2024 | Code |
| Point Convergence of Nesterov's Accelerated Gradient Method: An AI-Assisted Proof | Optimization Theory, LLM | arXiv 2025 | |
| Positive quasimodular forms and the sign uncertainty principle | Number Theory, Analysis, LLM, ATP | arXiv 2026 | Code |
| Positivity in classical enumerative geometry: a case study in synchronized AI-assisted mathematics | Algebraic Geometry, LLM | arXiv 2026 | |
| Power-saving bounds for Thue--Mahler and Mordell equations | Number Theory, LLM | arXiv 2026 | |
| Predicting root numbers with neural networks | Number Theory, RNN, CNN | IJDSMS 2024 | |
| Primitive sets and von Mangoldt chains: Erdős Problem #1196 and beyond | Number Theory, LLM, ATP | arXiv 2026 | |
| Process-Verified Reinforcement Learning for Theorem Proving via Lean | ATP, LLM, RL | arXiv 2026 | |
| Proof or Bluff? Evaluating LLMs on 2025 USA Math Olympiad | Benchmark, LLM | arXiv 2025 | |
| ProofNet: Autoformalizing and Formally Proving Undergraduate-Level Mathematics | Benchmark, ATP | arXiv 2023 | |
| Putnam-AXIOM: A Functional and Static Benchmark for Measuring Higher Level Mathematical Reasoning in LLMs | Benchmark, LLM | arXiv 2025 | |
| PutnamBench: Evaluating Neural Theorem-Provers on the Putnam Mathematical Competition | Benchmark, ATP | NeurIPS 2024 | Code Website arXiv |
| QED: An Open-Source Multi-Agent System for Generating Mathematical Proofs on Open Problems | LLM | arXiv 2026 | Code |
| R-equivalence on Cubic Surfaces I: Existing Cases with Non-Trivial Universal Equivalence | Algebraic Geometry, LLM | arXiv 2026 | |
| Ranks of elliptic curves and deep neural networks | Number Theory, CNN | Research in Number Theory 2023 | Code |
| RealMath: A Continuous Benchmark for Evaluating Language Models on Research-Level Mathematics | Benchmark, LLM | NeurIPS 2025 | arXiv |
| Recursions for Mock Theta Functions | Number Theory, LLM | arXiv 2026 | Skills and Chat Logs Chat Logs (DeepSeek) |
| Recursive-algebraic solution of the closed string tachyon vacuum equation | Mathematical Physics, LLM | arXiv 2026 | Code Chat Logs |
| Reinforced Generation of Combinatorial Structures: Hardness of Approximation | Computational Complexity, Combinatorics, LLM | arXiv 2025 | |
| Reinforced Generation of Combinatorial Structures: Ramsey Numbers | Combinatorics, LLM | arXiv 2026 | |
| Reinforcement Learning the Chromatic Symmetric Function | Graph Theory, RL | Advances in Theoretical and Mathematical Physics 2026 | Code arXiv |
| Remarks on the disproof of the unit distance conjecture | Discrete Geometry, Number Theory, LLM | arXiv 2026 | Original Paper CoT |
| Removing the Torsion-free Hypothesis in a Positivity Theorem on Deligne-Mumford Stacks | Algebraic Geometry, LLM | arXiv 2026 | Code (Danus) |
| Resolution of Erdős Problem #728: a writeup of Aristotle's Lean proof | Number Theory, LLM, ATP | arXiv 2026 | |
| Rigor with Machine Learning from Field Theory to the Poincaré Conjecture | Geometry, Mathematical Physics | Nature Reviews Physics 2024 | |
| Searching for ribbons with machine learning | Geometry, Bayesian Optimization, RL, Neural Network | Machine Learning Science and Technology 2025 | Code |
| Semi-Autonomous Mathematics Discovery with Gemini: A Case Study on the Erdős Problems | Combinatorics, Number Theory, LLM | arXiv 2026 | Chat Logs |
| Settling the Optimal Exponent Relating Sumsets and Difference Sets | Combinatorics, LLM, ATP | arXiv 2026 | Code |
| Sharp First-Order Lower Bounds for Higher-Order Smooth Nonconvex Optimization | Optimization Theory, LLM | arXiv 2026 | |
| Sharp small-deviation inequalities for sums of independent nonnegative random variables | Probability, Combinatorics, LLM, ATP | arXiv 2026 | Code |
| Short proofs in combinatorics and number theory | Combinatorics, Number Theory, LLM | arXiv 2026 | |
| Short proofs in combinatorics, probability and number theory II | Combinatorics, Probability, Number Theory, LLM | arXiv 2026 | |
| Solving a Research Problem in Mathematical Statistics with AI Assistance | Statistics, LLM | arXiv 2025 | Chat Log (Upper Bound) Chat Log (Lower Bound) |
| Soohak: A Mathematician-Curated Benchmark for Evaluating Research-level Math Capabilities of LLMs | Benchmark, LLM | arXiv 2026 | |
| Stochastically evolving ellipsoids with symmetries | Discrete Geometry, Number Theory, Probability, LLM | arXiv 2026 | Chat Logs |
| Strongly Polynomial Time Complexity of Policy Iteration for L-inf Robust MDPs | Computational Complexity, LLM | arXiv 2026 | Chat Logs |
| Studying number theory with deep learning: a case study with the Möbius and squarefree indicator functions | Number Theory, Transformer | Advances in Theoretical and Mathematical Physics 2026 | Code arXiv |
| Ten Digits on a Train: AI-Assisted Verification of Two Eigenvalue Problems | Analysis, Numerical Analysis, LLM | arXiv 2026 | |
| The Agentic Researcher: A Practical Guide to AI-Assisted Research in Mathematics and Machine Learning | LLM | arXiv 2026 | |
| The Equational Theories Project: Advancing Collaborative Mathematical Research at Scale | Algebra, LLM, CNN, ATP | arXiv 2025 | Code |
| The Hayman--Wu constant is $\pi^2$ | Analysis, LLM | arXiv 2026 | |
| The Mathieu group $M_{23}$ is a Galois group over $\mathbb{Q}$ | Number Theory, Group Theory, Algebraic Geometry, LLM | arXiv 2026 | Code |
| The Maxwell Conjecture is False | Mathematical Physics, LLM | arXiv 2026 | |
| The motivic class of the space of genus 0 maps to the flag variety | Algebraic Geometry, LLM | arXiv 2026 | |
| The Optimist: Towards Fully Automated Graph Theory Research | Graph Theory, Optimization Theory | arXiv 2024 | Code |
| The period-index conjecture is false | Algebraic Geometry, LLM | arXiv 2026 | |
| The Problem Is the Problem: Towards Scalable Mathematical Discovery | Combinatorics, LLM | arXiv 2026 | Code |
| The Simplicity of Hodge Bundle | Algebraic Geometry, LLM | Proceedings of the National Academy of Sciences 2026 | Chat Logs arXiv |
| Towards Autonomous Mathematics Research | Survey, LLM | arXiv 2026 | |
| Trees and Graphs with Non Log-concave Dominating Set Sequence via AI Tools | Graph Theory, Transformer | arXiv 2026 | Code |
| Twelve common flex lines in a general pencil of cubics | Algebraic Geometry, LLM | arXiv 2026 | Code (Danus) |
| Undecidability problems for semifree DG algebras | Algebra, Geometric Topology, Logic, Symplectic Geometry, LLM | arXiv 2026 | Chat Logs |
| Unsupervised Discovery of Formulas for Mathematical Constants | Number Theory | NeurIPS 2024 | Code |
| Verifiable Auto-Formalization of Mathematics Using a Relaxed Natural Formal Language | ATP, LLM | arXiv 2026 | |
| What makes math problems hard for reinforcement learning: a case study | Group Theory, RL, Transformer | NeurIPS 2025 | Code arXiv |
