theorem-proving

Tag

Cards List
#theorem-proving

@rohanpaul_ai: $2K of tokens costs less than sending 2 people to a conference, and that gap is what changes the calculation for open p…

X AI KOLs Following · 2026-08-03 Cached

OpenAI reports that an internal version of its next major model (Astra) solved 10 long-standing open problems in math and theoretical computer science for roughly $2,000 in tokens, with formal Lean certificates.

0 favorites 0 likes
#theorem-proving

Ten advances in mathematics and theoretical computer science

OpenAI Blog · 2026-08-01 Cached

OpenAI announces ten results on long-standing open problems in mathematics and theoretical computer science, achieved by an internal version of its next model Astra, with proofs formalized in Lean.

0 favorites 0 likes
#theorem-proving

Why Rocq is better than Lean for program verification

Lobsters Hottest · 2026-07-28 Cached

A technical blog post argues that Rocq (Coq) is better than Lean for program verification due to Rocq's native support for coinductive types and cofixpoints, contrasting with Lean's less mature, library-based approach.

0 favorites 0 likes
#theorem-proving

Learned Interventions in Lean 4 grind

arXiv cs.LG · 2026-07-28 Cached

A research paper introducing a failure-triggered cascade approach to safely integrate machine learning into Lean 4's grind tactic, achieving improved efficiency and solving previously unsolvable proofs without regressions.

0 favorites 0 likes
#theorem-proving

LeanFlow: A Case Study in Workflow-Driven Lean Autoformalization

arXiv cs.AI · 2026-07-24 Cached

LeanFlow is an LLM agent system for translating mathematical papers into formalized Lean projects, evaluated through case studies and benchmarks with Kimi-K2.6 and GPT-5.5, achieving high completion rates within budget constraints.

0 favorites 0 likes
#theorem-proving

PriorProof: A Point-in-Time Measure of Technique Novelty for Formal Proofs

arXiv cs.AI · 2026-07-21 Cached

PriorProof introduces a method to measure the novelty of proof techniques in formal mathematics by analyzing the dependency footprint of Lean proof terms against a prior built from an earlier snapshot of Mathlib. The method agrees with human raters on 69.7% of pairs and provides interpretable score gaps.

0 favorites 0 likes
#theorem-proving

Theory-Level Autoformalization: From Isolated Statements to Unified Formal Knowledge Bases

arXiv cs.AI · 2026-07-16 Cached

This position paper argues for theory-level autoformalization, which formalizes entire theories including axioms, definitions, and lemmas as coherent libraries, rather than isolated statements. It discusses the significance, alternative views, open challenges, and proposes paths forward for this shift in formalization research.

0 favorites 0 likes
#theorem-proving

OpenProver: Agentic and Interactive Theorem Proving with Lean 4

arXiv cs.AI · 2026-07-13 Cached

OpenProver is an open-source system for LLM-driven automated theorem proving using Lean 4, featuring a Planner-Worker-Verifier architecture and both autonomous and interactive modes. It enables reproducible evaluation and human-AI synergy in mathematical proof search.

0 favorites 0 likes
#theorem-proving

From Solvers to Research: Large Language Model-Driven Formal Mathematics at the Research Frontier

arXiv cs.CL · 2026-07-10 Cached

This position paper reviews the current state of LLM-driven formal mathematics, identifies key limitations in applying these systems to open-ended research mathematics, and proposes a strategic roadmap for developing AI agents capable of advancing mathematical frontiers.

0 favorites 0 likes
#theorem-proving

@AnimaAnandkumar: Excited to share four Lean-related papers from our group at @icmlconf workshops in Math and Physics! Together, these wo…

X AI KOLs Timeline · 2026-07-09 Cached

Anima Anandkumar announces four Lean-related papers from their group at ICML workshops, covering verified ML systems, functional program synthesis, proof assistant interoperability, and scientific reasoning, positioning Lean as infrastructure for AI.

0 favorites 0 likes
#theorem-proving

Beyond Compilation: Evaluating Faithful Natural-Language-to-Lean Statement Formalization

arXiv cs.AI · 2026-07-01 Cached

This paper presents a benchmark and evaluation protocol for faithful natural-language-to-Lean statement formalization, revealing a 29-point gap between compile-pass and consensus-faithfulness, and decomposing the effects of expert drafting, context search, and elaboration feedback.

0 favorites 0 likes
#theorem-proving

Leanstral 1.5

Hacker News Top · 2026-06-30 Cached

Mistral AI releases Leanstral 1.5, an updated Lean 4 formal proof engineering model optimized for automated theorem proving and autoformalization, with 119B total parameters and 6.5B active parameters.

0 favorites 0 likes
#theorem-proving

Proving the Fundamental Theorem of Arithmetic in Agda

Lobsters Hottest · 2026-06-30 Cached

A detailed blog post presenting a fully commented proof of the Fundamental Theorem of Arithmetic in Agda, intended for intermediate learners of the proof assistant.

0 favorites 0 likes
#theorem-proving

Faults in Our Formal Benchmarking: Dataset Defects and Evaluation Failures in Lean Theorem Proving

arXiv cs.AI · 2026-06-30 Cached

This paper audits five widely used Lean theorem-proving benchmarks, uncovering 398 mechanically certified issues such as counterexamples, vacuous theorems, and unsound axioms. It proposes a fault taxonomy, automated checkers, and release standards to improve evaluation reliability and trustworthiness.

0 favorites 0 likes
#theorem-proving

Theory-Scale Auto-Formalization of Logics for Computer Science

arXiv cs.LG · 2026-06-26 Cached

Introduces LCS-Bench, a theory-scale benchmark for auto-formalization of logics for computer science, covering 327 textbook items over 4,076 Lean declarations. Evaluation on 14 models shows the benchmark is challenging, with SOTA models achieving only 20.1% on auto-formalization tasks.

0 favorites 0 likes
#theorem-proving

Process-Verified Reinforcement Learning for Theorem Proving via Lean

arXiv cs.AI · 2026-06-20 Cached

This paper presents Process-Verified Reinforcement Learning, using the Lean proof assistant as a process oracle to provide fine-grained tactic-level feedback during training, improving theorem proving performance.

0 favorites 0 likes
#theorem-proving

IsabeLLM: Automated Theorem Proving Applied to Formally Verifying Consensus

arXiv cs.AI · 2026-06-17 Cached

This paper presents improvements to IsabeLLM, an automated theorem proving tool built on Isabelle, by integrating a retrieval-augmented generation framework, error tracing, and counterexample generation. The improved tool is evaluated on the formal verification of Bitcoin's Proof of Work consensus protocol.

0 favorites 0 likes
#theorem-proving

Formalizing Numerical Analysis: An Agent Pipeline and Quality Audit Beyond Kernel Acceptance

arXiv cs.AI · 2026-06-15 Cached

This paper presents an agent pipeline for formalizing a numerical analysis textbook in Lean 4 and introduces a quality audit framework that evaluates semantic correctness and library reuse beyond kernel acceptance, revealing common unfaithful formalization patterns.

0 favorites 0 likes
#theorem-proving

Sorries Are Not the Hard Part: An Expert-Review Case Study of a Semi-Autonomous Formalization

arXiv cs.AI · 2026-06-15 Cached

This paper presents a case study of using a large language model (Claude Code) to formalize Grothendieck's vanishing theorem in the Lean theorem prover. It finds that while agents can produce verified code, they struggle with definitions and API design, emphasizing the need for expert review beyond mere compilation.

0 favorites 0 likes
#theorem-proving

MA-ProofBench: A Two-Tiered Evaluation of LLMs for Theorem Proving in Mathematical Analysis

arXiv cs.AI · 2026-06-15 Cached

MA-ProofBench is a new formal benchmark for evaluating LLMs on theorem proving in mathematical analysis, containing 200 problems across two difficulty levels. The best model, GPT-5.5, achieves only 16% on Level I and 5% on Level II, highlighting a significant gap between informal and formal reasoning.

0 favorites 0 likes
Next →
← Back to home

Submit Feedback