Advancing mathematics research with AI-driven formal proof search
Open accessThe DOI matches its Crossref record; 80 of the 80 references it cites were found in a registry or an index; none of the 41 sources its claims cite is checked for support yet.
Abstract
Large language models (LLMs) increasingly excel at mathematics tasks, but their unreliability limits their utility in mathematics research. A mitigation is to use LLMs to generate formal proofs in languages such as Lean, in which the compiler verifies every proof step. We present the first demonstration of this method’s value in solving open problems at scale. We built an artificial intelligence agent for formal proof search that autonomously resolved nine of 353 open Erdős problems, proved 44/492 On-Line Encyclopedia of Integer Sequences conjectures, and is being deployed in combinatorics, optimization, graph theory, algebraic geometry, and quantum optics research. Even a basic agent alternating LLM-based generation with Lean-based verification replicated the Erdős successes. These findings demonstrate the power of formal proof search as an enabler of autonomous mathematical discovery.
Overview
CoChat Summary
TL;DR
The paper reports a large-scale evaluation of AI-driven formal proof search in Lean, using the AlphaProof Nexus framework to attack open research problems. Its full-featured agent autonomously solved 9 of 353 open Erdős problems, proved 44 of 492 OEIS conjectures, and was deployed in several research areas.
Key findings
- The full-featured agent solved 9/353 open Erdős problems, including two questions open for 56 years, at a per-problem inference cost of a few hundred dollars.
- It proved 44/492 OEIS conjectures that manual review found correctly formalized and previously unproven.
- A basic agent alternating LLM generation with Lean verification replicated the Erdős successes but was costlier on the hardest problems.
- AlphaProof in standalone tree-search mode and basic agents using smaller models (Gemini 3.0 Flash, Gemini 3.1 Flash-Lite) solved none of the Erdős problems.
Methods
- The authors built AlphaProof Nexus, an LLM-aided proof-generation framework using Lean compiler feedback, with a basic agent of independent subagents and a full-featured agent adding evolutionary search, Elo-based sketch rating, P-UCB sampling, and AlphaProof as a tool.
- Evaluation used all 353 Lean formalizations of Erdős problems available in Formal Conjectures, terminating search after 3000 episodes if no proof was found; OEIS evaluation used 492 autoformalized open questions with test lemmas guarding against misformalization.
- The full-featured agent used Gemini 3.1 Pro for provers and Gemini 3.0 Flash for rater subagents; comparisons across agents used solve rate versus mean inference cost in USD.
Limitations
- The paper states that successes are concentrated in areas such as combinatorics, convex optimization, and number theory where Lean’s library is mature and tasks decompose into tractable subgoals; most Erdős problems remain out of reach, as do problems requiring extensive new theory.
- The paper states that agents inherit biases of their underlying LLMs and exhibit high search variance, and that reported costs do not capture the full cost of discovery, including identifying tractable problems.
- The paper’s failure analysis found that agents often offloaded core difficulty into a single `sorry` in a helper lemma, and that some top sketches relied on hallucinated literature lemmas; the text also notes misformalization risks, including density-interpretation ambiguities that required correction.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures



![Figure 2 Rater agent prompt (condensed). Elided text is represented by [...] . Text in braces denotes template variables populated at runtime. For example, { player blocks } is replaced by the sketches to be Figure 8 | Full prompt for the basic agent (A). Text in braces denotes template variables populated at runtime. For example, {code} is replaced by the current Lean file.](https://figures.cochat.ai/paper-figures/99176cf508264aaeaf6d185108bab6df/advancing-mathematics-research-with-ai-driven-formal-proof-search-figure-2.png)



Verification
Claims the paper makes
0 Valid · 3 Not valid · 29 Not checked · 127 Own results and interpretations
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Several proofs require sophisticated constructions and the synthesis of distinct mathematical arguments.”
§ Advancing Mathematics Research with AI-Driven Formal Proof Search > 3. Systematic Evaluation on Open Problems
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Upon manual inspection, these lemmas proved to be hallucinations.”
§ Advancing Mathematics Research with AI-Driven Formal Proof Search > Failure Analysis.
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The agent also served as a tool for detecting and fixing misformalizations.”
- Also stated in: § 6. Discussion · boosted
“the agents were powerful tools for detecting misformalizations.”
§ Advancing Mathematics Research with AI-Driven Formal Proof Search > AlphaProof Nexus
boostedstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Also stated in: § 6. Discussion · boosted
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“in Erdős problems #125 and #741(i), the interpretation of”
§ Advancing Mathematics Research with AI-Driven Formal Proof Search > AlphaProof Nexus
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Following the correction of the ambiguity, the agent was still able to resolve the questions.”
§ Advancing Mathematics Research with AI-Driven Formal Proof Search > AlphaProof Nexus
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
98 more claims
Create a free account to see all 159 claims and every source verdict.
- Probably not a substantial claim. 30
- It may state two separate claims as one. 31
- The quote only partly states this claim. 4
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated major: it would touch a result — a value a result rests on, reported and recomputed p-values on opposite sides of the significance level, two passages that conflict with no sign which is right, or a cited work retracted before this paper was published.
In the paper
§ Advancing Mathematics Research with AI-Driven Formal Proof Search > Conjecture Summary Proof Technique
“741 (ii) (1994) Existence of a basis 𝐴 of order 2 with 𝐴 1 + 𝐴 1 , 𝐴 2 + 𝐴 2 having bounded gaps for all 𝐴 1 , 𝐴 2 such that 𝐴 = 𝐴 1 ⊔ 𝐴 2”
§ 1. Role and Goal You are a world-class mathematician and Lean 4 expert.Your goal is to solve hard mathematical problems by devising a proof strategy and translating it into a Lean 4 proof.# 2. Your Task You will be given Lean code containing theorem statement with a partial proof.You goal is to modify the file to continue proving the statement until there are no sorries left.You will be getting feedback from Lean Compiler after every time you modify code.Compilation errors will be highlighted and you need to keep iterating until the code compiles.CRITICAL: Don't end a session with the code which doesn't compile.You session will be discarded if the final proof doesn't compile.If you can't finish the proof in the current session at least make sure it compiles before you wrap up the session.Put any findings, plans or solutions as comments in the file.Only file content will be passed to the next session.Think like a mathematician: focus on the key insights, proof structure, and creative steps (e.g., constructing an object via 'let').If you get stuck on the main proof, try to gain insights by exploring diverse ideas: study specific cases, or define and attempt to prove interesting generalizations, specializations, or variants of the problem statement as new helper lemmas.Prefer clever mathematical arguments over brute-force casework where possible.Some of these problems are very hard, possibly even open problems in mathematics.But don't be discouraged|approach them with curiosity and persistence.Like George Dantzig, who solved two famous unsolved problems in statistics thinking they were homework, you might solve a problem you think is difficult simply by not knowing it was considered impossible!Believe in your ability to find creative solutions where others might not.CRITICAL: You MUST use tools available to you exhaustively to refine your proof until you either find a proof or are certain the current direction is flawed.Do NOT give up easily, and NEVER put off formalization work to the next session if you have more tool calls available.Your effort in each turn must be maximal: try to solve the problem in full, as if there is no next session.**No Imports:** The execution environment imports 'Mathlib' by default.Do **not** add any 'import' statements in your proof.# Current proof This is the proof to be modified in your session.{code} Make sure that you only propose changes inside sections enclosed by '--EVOLVE-BLOCK-START' and '--EVOLVE-BLOCK-END', or '--EVOLVE-VALUE-START' and '--EVOLVE-VALUE-END' comments. .Text in braces denotes template variables populated at runtime.For example, {player blocks} is replaced by the sketches to be compared. > Erdős #741-(ii)
“Question.Is there a basis 𝐴 of order 2 such that if 𝐴 = 𝐴 1 ⊔ 𝐴 2 then 𝐴 1 + 𝐴 1 and 𝐴 2 + 𝐴 2 cannot both have bounded gaps?”
Citations
Cites
Towards Deep Learning Models Resistant to Adversarial Attacks
Madry, A., Makelov, A., Schmidt, L., Tsipras, D., & Vladu, A. (2017) · arXiv · doi:10.48550/arxiv.1706.06083 · Cited by 6,602
A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play
Silver, D., Hubert, T., Schrittwieser, J., Antonoglou, I., Lai, M., Guez, A., Lanctot, M., Sifre, L., Kumaran, D., Graepel, T., et al. (2018) · Science · doi:10.1126/science.aar6404 · Cited by 3,562
Self-citationThe On-Line Encyclopedia of Integer Sequences
Sloane, N. J. A. (2007) · Lecture Notes in Computer Science · doi:10.1007/978-3-540-73086-6_12 · Cited by 3,225
The extragradient method for finding saddle points and other problems
Korpelevich, G. M. (1976) · Medical Entomology and Zoology · Cited by 2,779
A collection of mathematical problems
Ulam, S. M. (1960) · Medical Entomology and Zoology · Cited by 2,262
Individual choice behavior; a theoretical analysis.
Luce, R. D. (n.d.) · University of Michigan Library Repository · Cited by 1,870
Genetic programming as a means for programming computers by natural selection
Koza, J. (1994) · Statistics and Computing · doi:10.1007/bf00175355 · Cited by 1,685
(2002) · Lecture Notes in Computer Science · doi:10.1007/3-540-45949-9 · Cited by 1,629
Fixed points of nonexpanding maps
Halpern, B. R. (1967) · Bulletin of the American Mathematical Society · doi:10.1090/s0002-9904-1967-11864-0 · Cited by 1,415
A Reductions Approach to Fair Classification
Agarwal, A., Beygelzimer, A., Dudík, M., Langford, J., & Wallach, H. (2018) · arXiv · doi:10.48550/arxiv.1803.02453 · Cited by 1,288
Hilbert functions of graded algebras
Stanley, R. P. (1978) · Advances in Mathematics · doi:10.1016/0001-8708(78)90045-2 · Cited by 938
Plackett, R. L. (1975) · Applied Statistics · doi:10.2307/2346567 · Cited by 731
Mathematical discoveries from program search with large language models
Romera-Paredes, B., Barekatain, M., Novikov, A., Balog, M., Kumar, M. P., Dupont, E., Ruiz, F. J. R., Ellenberg, J. S., Wang, P., Fawzi, O., et al. (2024) · Nature · doi:10.1038/s41586-023-06924-6 · Cited by 544
Self-citationA modification of the Arrow-Hurwicz method for search of saddle points
Popov, L. D. (1980) · Mathematical Notes · doi:10.1007/bf01141092 · Cited by 477
A congruence theorem for trees
Kelly, P. S. (1957) · Pacific Journal of Mathematics · doi:10.2140/pjm.1957.7.961 · Cited by 410
Certified Programming with Dependent Types: A Pragmatic Introduction to the Coq Proof Assistant
Chlipala, A. J. (2013) · The MIT Press eBooks · doi:10.7551/mitpress/9153.001.0001 · Cited by 385
Daskalakis, C., Ilyas, A., Syrgkanis, V., & Zeng, H. (2017) · International Conference on Learning Representations · Cited by 326
Bondy, J. A., & Hemminger, R. L. (1977) · Journal of Graph Theory · doi:10.1002/jgt.3190010306 · Cited by 303
Fajtlowicz, S. (1988) · Discrete Mathematics · doi:10.1016/0012-365x(88)90199-9 · Cited by 289
The Lean 4 Theorem Prover and Programming Language
Moura, L. D., & Ullrich, S. (2021) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-79876-5_37 · Cited by 258
Draft, Sketch, and Prove: Guiding Formal Theorem Provers with Informal ProofsPreprint
Jiang, A. Q., Welleck, S., Zhou, J., Li, W., Liu, J., Jamnik, M., Lacroix, T., Wu, Y., & Lample, G. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2210.12283 · Cited by 227
Goedel-Prover-V2: Scaling Formal Theorem Proving with Scaffolded Data Synthesis and Self-Correction
Lin, Y., Tang, S., Lyu, B., Yang, Z., Chung, J.-H., Zhao, H., Jiang, L., Geng, Y., Ge, J., Sun, J., et al. (2026) · International Conference on Learning Representations · doi:10.48550/arxiv.2508.03613 · Cited by 184
Efficient Bayesian Inference for Generalized Bradley–Terry Models
Caron, F., & Doucet, A. (2012) · Journal of Computational and Graphical Statistics · doi:10.1080/10618600.2012.638220 · Cited by 183
Yoon, T., & Ryu, E. K. (2021) · International Conference on Machine Learning · Cited by 177
Mathematical discovery and exploration can be done at scale
Georgiev, B., Gómez-Serrano, J., Tao, T., & Wagner, A. Z. (2026) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2536158123 · Cited by 166
Self-citationStochastic Variance Reduction Methods for Policy EvaluationPreprint
Du, S. S., Chen, J., Li, L., Xiao, L., & Zhou, D. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1702.07944 · Cited by 166
Community, T. M. (2020) · Proceedings of the 9th ACM SIGPLAN International Conference on Certified Programs and Proofs · doi:10.1145/3372885.3373824 · Cited by 161
Aristotle: IMO-level Automated Theorem Proving
Achim, T., Best, A. J., Bietti, A., Der, K., Fédérico, M., Gukov, S., Halpern-Leistner, D., Henningsgard, K., Kudryashov, Y., Meiburg, A., et al. (2026) · SuperIntelligence - Robotics - Safety & Alignment · doi:10.70777/si.v3i3.18745 · Cited by 159
On the convergence of single-call stochastic extra-gradient methodsPreprint
Hsieh, Y.-G., Iutzeler, F., Malick, J., & Mertikopoulos, P. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1908.08465 · Cited by 155
Fajtlowicz, S. (1988) · Annals of discrete mathematics · doi:10.1016/s0167-5060(08)70776-3 · Cited by 135
Formal Mathematical Reasoning: A New Frontier in AIPreprint
Yang, K., Poesia, G., He, J., Li, W., Lauter, K., Chaudhuri, S., & Song, D. X. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2412.16075 · Cited by 129
Self-citationQuantum Experiments and Graphs: Multiparty States as Coherent Superpositions of Perfect Matchings
Krenn, M., Gu, X., & Zeilinger, A. (2017) · Physical Review Letters · doi:10.1103/physrevlett.119.240403 · Cited by 123
Thor: Wielding Hammers to Integrate Language Models and Automated Theorem Provers
Jiang, A. Q., Li, W., Tworkowski, S., Czechowski, K., Odrzygóźdź, T., Miłoś, P., Wu, Y., & Jamnik, M. (2022) · neural information processing systems · doi:10.52202/068431-0608 · Cited by 120
Learning and Planning in Complex Action SpacesPreprint
Hubert, T., Schrittwieser, J., Antonoglou, I., Barekatain, M., Schmitt, S., & Silver, D. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.06303 · Cited by 118
Self-citationDeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
DeepSeek-AI, Liu, A., Feng, B., Wang, B., Wang, B., Liu, B., Zhao, C., Dengr, C., Ruan, C., Dai, D., et al. (2024) · arXiv · doi:10.48550/arxiv.2405.04434 · Cited by 109
LeanDojo: Theorem Proving with Retrieval-Augmented Language Models
Yang, K., Swope, A., Gu, A., Chalamala, R., Song, P., Yu, S., Godil, S., Prenger, R. J., & Anandkumar, A. (2023) · Advances in Neural Information Processing Systems 36 · doi:10.52202/075280-0944 · Cited by 97
Generative Language Modeling for Automated Theorem Proving
Polu, S., & Sutskever, I. (2020) · arXiv · doi:10.48550/arxiv.2009.03393 · Cited by 82
Diakonikolas, J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2002.08872 · Cited by 82
Seed-Prover 1.5: Mastering Undergraduate-Level Theorem Proving via Learning from ExperiencePreprint
Chen, J., Chen, W., Du, J., Hu, J., Jiang, Z., Jie, A., Jin, X., Jin, X., Li, C., Shi, W., et al. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2512.17260 · Cited by 70
Hilbert: Recursively Building Formal Proofs with Informal Reasoning
Varambally, S., Voice, T., Sun, Y., Chen, Z., Yu, R., & Ye, K. (2025) · International Conference on Learning Representations · doi:10.48550/arxiv.2509.22819 · Cited by 68
Last-Iterate Convergence of Optimistic Gradient Method for Monotone Variational Inequalities
Gorbunov, E., Taylor, A., & Gidel, G. (2022) · neural information processing systems · doi:10.52202/068431-1589 · Cited by 65
Cai, Y., Oikonomou, A., & Zheng, W. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2204.09228 · Cited by 58
ODE Analysis of Stochastic Gradient Methods with Optimism and Anchoring for Minimax ProblemsPreprint
Ryu, E. K., Yuan, K., & Yin, W. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.10899 · Cited by 52
On the shape of a pure 𝑂-sequence
Boij, M., Migliore, J. C., Miró‐Roig, R. M., Nagel, U., & Zanello, F. (2011) · Memoirs of the American Mathematical Society · doi:10.1090/s0065-9266-2011-00647-7 · Cited by 51
Accelerating Scientific Research with Gemini: Case Studies and Common TechniquesPreprint
Woodruff, D. P., Cohen-Addad, V., Jain, L., Mao, J., Zuo, S., Bateni, M., Brânzei, S., Brenner, M. P., Chen, L., Feng, Y., et al. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2602.03837 · Cited by 47
AI co-mathematician: Accelerating mathematicians with agentic AIPreprint
Zheng, D., von Glehn, I., Zwólš, Y., Beloshapka, I., Buesing, L., Roy, D. M., Wattenberg, M., Georgiev, B., Schmidt, T., Cowie, A., et al. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2605.06651 · Cited by 37
Self-citationAniva, L., Sun, C., Miranda, B., Barrett, C., & Koyejo, S. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-90643-5_6 · Cited by 32
On the Divisibility Properties of Sequences of Integers
Erdős, P., & Sárközi, A. (1970) · Proceedings of the London Mathematical Society · doi:10.1112/plms/s3-21.1.97 · Cited by 32
Reinforced Generation of Combinatorial Structures: Hardness of ApproximationPreprint
Nagda, A., Raghavan, P., & Thakurta, A. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2509.18057 · Cited by 25
Tight last-iterate convergence rates for no-regret learning in multi-player gamesPreprint
Golowich, N., Pattathil, S., & Daskalakis, C. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.13724 · Cited by 24
Progress in Formalizing Sphere Packing in Dimension 8Preprint
Hariharan, S., Birkbeck, C., Lee, S., Ma, H. K. G., Mehta, B., Poiroux, A., & Viazovska, M. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2604.23468 · Cited by 22
Negative Stepsizes Make Gradient-Descent-Ascent ConvergePreprint
Shugart, H., & Altschuler, J. M. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2505.01423 · Cited by 21
LEAP: Supercharging LLMs for Formal Mathematics with Agentic FrameworksPreprint
Kung, P.-N., Song, L., Hwang, D., Yoon, J., Li, C.-L., Severini, S., Olšák, M., Lockhart, E., Le, Q. V., Gokturk, S. B., et al. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2606.03303 · Cited by 20
Self-citationFormal Conjectures: An Open and Evolving Benchmark for Verified Discovery in MathematicsPreprint
Firsching, M., Lezeau, P., Mercuri, S., Horváth, M. Z., Dillies, Y., Sönne, C., Wieser, E., Zhang, F., Hubert, T., y Arcas, B. A., et al. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2605.13171 · Cited by 17
Self-citationPrimitive sets and von Mangoldt chains: Erdős Problem #1196 and beyondPreprint
Alexeev, B., Barreto, K., Li, Y., Lichtman, J. D., Price, L., Shah, J. I., Tang, Q., & Tao, T. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2605.00301 · Cited by 16
AlphaEvolve: A coding agent for scientific and algorithmic discovery
Novikov, A., Vũ, N., Eisenberger, M., Dupont, E., Huang, P.-S., Wagner, A. Z., Shirobokov, S., Kozlovskii, B., Ruiz, F. J. R., Mehrabian, A., et al. (2025) · arXiv · doi:10.48550/arxiv.2506.13131 · Cited by 15
Self-citationReinforced Generation of Combinatorial Structures: Ramsey NumbersPreprint
Nagda, A., Raghavan, P., & Thakurta, A. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2603.09172 · Cited by 13
Complete sequences of sets of integer powers
Burr, S. A., Erdös, P., Graham, R. L., & Li, W. (1996) · Acta Arithmetica · doi:10.4064/aa-77-2-133-138 · Cited by 11
An Improved Last-Iterate Convergence Rate for Anchored Gradient Descent AscentPreprint
Surina, A., Suggala, A. S., Tsoukalas, G., Kovsharov, A., Shirobokov, S., Ruiz, F. J. R., Kohli, P., & Chaudhuri, S. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2604.03782 · Cited by 9
Self-citationShort proofs in combinatorics and number theoryPreprint
Alexeev, B., Putterman, M., Sawhney, M. S., Sellke, M., & Valiant, G. J. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2603.29961 · Cited by 9
Colouring versus density in integers and Hales–Jewett cubes
Reiher, C., Rödl, V., & Sales, M. T. (2024) · Journal of the London Mathematical Society · doi:10.1112/jlms.12987 · Cited by 8
Short proofs in combinatorics, probability and number theory IIPreprint
Alexeev, B., Putterman, M., Sawhney, M. S., Sellke, M., & Valiant, G. J. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2604.06609 · Cited by 8
On a Problem of Erdős and Sárközy
Schoen, T. (2001) · Journal of Combinatorial Theory Series A · doi:10.1006/jcta.2000.3142 · Cited by 6
Last-Iterate Convergence of Anchored Gradient DescentPreprint
Cai, Y., & Zheng, W. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2604.12235 · Cited by 6
LOG-CONCAVITY OF LEVEL HILBERT FUNCTIONS AND PURE O-SEQUENCES
Zanello, F. (2024) · Journal of Commutative Algebra · doi:10.1216/jca.2024.16.245 · Cited by 5
On Erdős and Sárközy’s sequences with Property P
Elsholtz, C., & Planitzer, S. (2016) · Monatshefte für Mathematik · doi:10.1007/s00605-016-0995-9 · Cited by 4
Baier, S. (2004) · UEA Digital Repository (University of East Anglia) · Cited by 4
Towards Autonomous Mathematics Research
Feng, T., Trinh, T. H., Bingham, G., Hwang, D., Chervonyi, Y., Jung, J., Lee, J., Pagano, C., Kim, S.-H., Pasqualotto, F., et al. (2026) · arXiv · doi:10.48550/arxiv.2602.10177 · Cited by 3
Mathematical exploration and discovery at scale
Georgiev, B., Gómez-Serrano, J., Tao, T., & Wagner, A. Z. (2025) · arXiv · doi:10.48550/arxiv.2511.02864 · Cited by 3
Self-citationKimina-Prover Preview: Towards Large Formal Reasoning Models with Reinforcement Learning
Wang, H., Unsal, M., Lin, X., Baksys, M., Liu, J., Santos, M. D., Sung, F., Vinyes, M., Ying, Z., Zhu, Z., et al. (2025) · arXiv · doi:10.48550/arxiv.2504.11354 · Cited by 2
Self-citationOn infinite sets with no $3$ on a linePreprint
Putterman, M., Sawhney, M. S., & Valiant, G. J. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2602.21275 · Cited by 2
Equality in Fill's spectral gap problemPreprint
Jain, V., & Mizgerd, C. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2604.03937 · Cited by 1
google-deepmind/alphaproof-nexus-results: v1.0.0-science-submission
Ferraiuolo, A., & Wieser, E. (2026) · Zenodo (CERN European Organization for Nuclear Research) · doi:10.5281/zenodo.21477348 · Cited by 1
Self-citationThe motivic class of the space of genus $0$ maps to the flag variety
Bryan, J., Elek, B., Manners, F., Salafatinos, G., & Vakil, R. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2601.07222
Aletheia tackles FirstProof autonomously
Feng, T., Jung, J., Kim, S.-H., Pagano, C., Gukov, S., Tsai, C.-C., Woodruff, D. P., Javanmard, A., Mokhtari, A., Hwang, D., et al. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2602.21201
Point Convergence of Nesterov's Accelerated Gradient Method: An AI-Assisted Proof
Jang, U., & Ryu, E. K. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2510.23513
Schmitt, J. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2512.14575
Applications to psychophysics.
Luce, R. D. (n.d.) · Individual choice behavior: A theoretical analysis. · doi:10.1037/14396-002
Aristotle: IMO-level Automated Theorem Proving
Achim, T., Best, A., Bietti, A., Der, K., Fédérico, M., Gukov, S., Halpern-Leistner, D., Henningsgard, K., Kudryashov, Y., Meiburg, A., et al. (2025) · arXiv · doi:10.48550/arxiv.2510.01346
On Erdős and Sárközy's sequences with Property P
Elsholtz, C., & Planitzer, S. (2016) · arXiv · doi:10.48550/arxiv.1609.07935
Research works printed but not linked: 10
- 10.1006/jcta.2000.3142 · DOI
- N. J. Sloane The On-Line Encyclopedia of Integer Sequences in Proceedings of the 14th Symposium on Towards Mechanized Mathematical Assistants: 6th International Conference Calculemus ’07 / MKM ’07 (Springer Berlin Heidelberg) (2007) p. 130.10.1007/978-3-540-73086-6_12 · DOI · Paper page
- A. Thakur, G. Tsoukalas, Y. Wen, J. X. Xin, S. Chaudhuri, An in-context learning agent for formal theorem-proving, in Conference on Language Models (2024).
- A. Nagda P. Raghavan A. Thakurta Reinforced generation of combinatorial structures: Ramsey numbers. arXiv.2603.09172 [math.CO] (2026). · arXiv
- D. Alvarez-Melis, T. Jaakkola, S. Jegelka, Structured Optimal Transport, in Proceedings of the Twenty-First International Conference on Artificial Intelligence and Statistics (2018).
- H. Shugart J. M. Altschuler Negative stepsizes make gradient-descent-ascent converge. arXiv preprint arXiv:2505.01423 (2025). · arXiv
- Y. Cai, W. Zheng, Accelerated Single-Call Methods for Constrained Min-Max Optimization, in International Conference on Learning Representations (2023).
- S. Lee, D. Kim, Fast extragradient methods for smooth structured nonconvex-nonconcave minimax problems. Adv. Neural Inf. Process. Syst. (2021).
- S. Lee D. Kim Semi-Anchored Gradient Methods for Nonconvex-Nonconcave Minimax Problems (2024) https://openreview.net/forum?id=rmLTwKGiSP.
- L. Chen, L. Luo, Near-Optimal Algorithms for Makinghe Gradient Small in Stochastic Minimax Optimization. J. Mach. Learn. Res. 25, 1–44 (2024).
Cited by
LeanMarathon: Toward Reliable AI Co-Mathematicians through Long-Horizon Lean AutoformalizationPreprint
Zhang, Y., Sun, Y., Suzuki, T., Lee, J. D., & Liu, F. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2606.05400 · Cited by 26
LEAP: Supercharging LLMs for Formal Mathematics with Agentic FrameworksPreprint
Kung, P.-N., Song, L., Hwang, D., Yoon, J., Li, C.-L., Severini, S., Olšák, M., Lockhart, E., Le, Q. V., Gokturk, S. B., et al. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2606.03303 · Cited by 20
Self-citationSimple Baselines are Competitive with Code EvolutionPreprint
Gideoni, Y., Risi, S., & Gal, Y. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2602.16805 · Cited by 15
A Domain-Specific Harness for End-to-End Automation of Optimization ResearchPreprint
Kim, H.-T., Ryu, E. K., & Gupta, S. D. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2608.07407 · Cited by 13
Lin, H., Woodruff, D. P., Deng, Y., Mao, J., Zuo, S., & Mirrokni, V. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2609.15983 · Cited by 9
Metadata
- Authors
- Tsoukalas, G., Kovsharov, A., Shirobokov, S., Surina, A., Firsching, M., Bérczi, G., Ruiz, F. J. R., Suggala, A., Wagner, A. Z., Wieser, E., Yu, L., Huang, A., Horváth, M. Z., Ferraiuolo, A., Michalewski, H., Grosu, C., Lockhart, E., Hubert, T., Balog, M., Kohli, P., & Chaudhuri, S.
- Affiliations
- Google DeepMind (United Kingdom) (GB)
- Aarhus University (DK)
- Google DeepMind, London, UK.
- Google, Mountain View, CA.
- Corresponding author
- Tsoukalas, George
- Kovsharov, Anton
- Shirobokov, Sergey
- Kohli, Pushmeet
- Chaudhuri, Swarat
- ORCID
- Tsoukalas, George
- Kovsharov, Anton
- Shirobokov, Sergey
- Surina, Anja
- Bérczi, Gergely
- Ruiz, Francisco J. R.
- Suggala, Arun
- Wagner, Adam Zsolt
- Wieser, Eric
- Yu, Lei
- Huang, Aja
- Horváth, Miklós Z.
- Ferraiuolo, Andrew
- Michalewski, Henryk
- Grosu, Codrut
- Lockhart, Edward
- Hubert, Thomas
- Balog, Matej
- Kohli, Pushmeet
- Chaudhuri, Swarat
- Venue
- Science
- Published
- 2026-10-08
- Volume
- 394
- Issue
- 6820
- Pages
- 234-239
- ISSN
- 0036-8075 (ISSN-L)
- 1095-9203
- OpenAlex
- W7162098200
- Cited by
- 62
- References
- 76
- Citations by year
- 2026: 61
- FWCI
- 97.09
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- cc-by-nc-nd
- Locations
- Science (publishedVersion)
- PubMed (publishedVersion)
- arXiv (Cornell University) (submittedVersion, cc-by-nc-nd)
- arXiv (Cornell University) (cc-by-nc-nd)
- Topics
- Physical Sciences › Computer Science › Computational Theory and Mathematics › Mathematics, Computing, and Information Processing
- Physical Sciences › Computer Science › Software › Logic, programming, and type systems
- Physical Sciences › Computer Science › Artificial Intelligence › Artificial Intelligence Applications
- Keywords
- large language models, Lean theorem prover, AI agents, open problems in mathematics, Erdős problem, proof verification, autonomous reasoning
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
A language model drew the claims from the paper on 2026-11-21, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-11-21 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.