Fetching the paper…
Reading the bibliography…
We introduce Kimina-Prover Preview, a large language model that pioneers a novel reasoning-driven exploration paradigm for formal theorem proving, as showcased in this preview release.
“Isabelle/HOL: a proof assistant for higher-order logic”
Tobias Nipkow, Lawrence Paulson and Markus Wenzel · 2002
Earlier work this paper cites.
“The Lean 4 Theorem Prover and Programming Language”
Leonardo Moura and Sebastian Ullrich · 2021
Earlier work this paper cites.
“HyperTree Proof Search for Neural Theorem Proving”
Guillaume Lample et al · 2022
Earlier work this paper cites.
“Formal Mathematics Statement Curriculum Learning”, 2022
Stanislas Polu et al · 2022
Earlier work this paper cites.
“MiniF2F: a cross-system benchmark for formal Olympiad-level mathematics”, 2022
Kunhao Zheng, Jesse Han and Stanislas Polu · 2022
Earlier work this paper cites.
“ProofNet: Autoformalizing and Formally Proving Undergraduate-Level Mathematics”, 2023
Zhangir Azerbayev et al · 2023
Earlier work this paper cites.
“Baldur: Whole-Proof Generation and Repair with Large Language Models”, 2023
Emily First et al · 2023
Earlier work this paper cites.
“Draft, Sketch, and Prove: Guiding Formal Theorem Provers with Informal Proofs”, 2023
Albert. Jiang · 2023
Earlier work this paper cites.
“Multilingual Mathematical Autoformalization”, 2023
Albert. Jiang, Wenda Li and Mateja Jamnik · 2023
Earlier work this paper cites.
“A read-eval-print-loop for Lean 4”
Lean FRO · 2023
Earlier work this paper cites.
“Dt-solver: Automated theorem proving with dynamic-tree sampling guided by proof-level value function”
Haiming Wang · 2023
Earlier work this paper cites.
“LEGO-Prover: Neural Theorem Proving with Growing Libraries”, 2023
Haiming Wang et al · 2023
Cited alongside, same era.
“AI achieves silver-medal standard solving International Mathematical Olympiad problems”, 2024
Deepmind · 2024
Cited alongside, same era.
“MUSTARD: Mastering Uniform Synthesis of Theorem and Proof Data”, 2024
Yinya Huang et al · 2024
Cited alongside, same era.
“NuminaMath” GitHub repository
Jia Li et al · 2024
Cited alongside, same era.
OpenAI et al · 2024
Cited alongside, same era.
“Claude 3.7 Sonnet System Card”, https://anthropic.com/claude-3-7-sonnet-system-card , 2025
Anthropic · 2025
Closest in time.
“DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning”, 2025
DeepSeek-AI · 2025
Closest in time.
“Kimi k1.5: Scaling reinforcement learning with llms”
Kimi-Team · 2025
Closest in time.
Yang Li et al · 2025
Closest in time.
“Lean-STaR: Learning to Interleave Thinking and Proving”
Haohan Lin et al · 2025
Closest in time.
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Qwen-Team · 2024
Cited alongside, same era.
“Compfiles: Catalog Of Math Problems Formalized In Lean” GitHub repository, https://github.com/dwrensha/compfiles , 2024
David Renshaw · 2024
Cited alongside, same era.
“PutnamBench: Evaluating Neural Theorem-Provers on the Putnam Mathematical Competition”, 2024
George Tsoukalas et al · 2024
Cited alongside, same era.
“Proving Theorems Recursively”, 2024
Haiming Wang et al · 2024
Cited alongside, same era.
Zijian Wu et al · 2024
Cited alongside, same era.
Huajian Xin et al · 2024
Cited alongside, same era.
Yong Lin et al · 2025
Closest in time.
“Numina Lean Server: Technical Report” arXiv preprint forthcoming
Numina · 2025
Closest in time.
Ruida Wang et al · 2025
Closest in time.
“BFS-Prover: Scalable Best-First Tree Search for LLM-based Automatic Theorem Proving”, 2025
Ran Xin et al · 2025
Closest in time.
“Leanabell-Prover: Posttraining Scaling in Formal Reasoning”, 2025
Jingyuan Zhang et al · 2025
Closest in time.