lean-dojo / LeanAgentLinks
LeanAgent is a novel lifelong learning framework for formal theorem proving that continuously generalizes to and improves on ever-expanding mathematical knowledge without forgetting previously learned knowledge.
☆43Updated 6 months ago
Alternatives and similar repositories for LeanAgent
Users that are interested in LeanAgent are comparing it to the libraries listed below
Sorting:
- LLMs + Lean, on your laptop or in the cloud☆195Updated 2 months ago
- LeanUniverse: A Library for Consistent and Scalable Lean4 Dataset Management☆75Updated 11 months ago
- ☆45Updated last year
- Benchmark for undergraduate-level formal mathematics☆113Updated last year
- Neural theorem proving tutorial, version II☆40Updated last year
- Formalizing stochastic doubly-efficient debate☆114Updated last year
- Harmonic Datasets☆52Updated last year
- ProofNet dataset ported into Lean 4☆27Updated 6 months ago
- ☆163Updated 3 weeks ago
- An environment for learning formal mathematical reasoning from scratch☆71Updated last year
- Tutorial on neural theorem proving☆177Updated last year
- Transformers for Mathematics Tutorial | Simons/SLMath Workshop on AI for Mathematics 2025☆42Updated 8 months ago
- ChatGPT plugin for theorem proving in Lean☆123Updated last year
- An evaluation benchmark for undergraduate competition math in Lean4, Isabelle, Coq, and natural language.☆187Updated this week
- Retrieval-Augmented Theorem Provers for Lean☆309Updated 10 months ago
- A package for defining deep learning models using categorical algebraic expressions.☆61Updated last year
- LeanEuclid is a benchmark for autoformalization in the domain of Euclidean geometry, targeting the proof assistant Lean.☆116Updated 2 weeks ago
- Official implementation of "Beyond Theorem Proving: Formulation, Framework and Benchmark for Formal Problem-Solving"☆27Updated 7 months ago
- A long-horizon, sparse-reward math environment for reinforcement learning. Official code repo for "What makes Math problems hard for rein…☆30Updated 4 months ago
- ☆52Updated 4 months ago
- COPRA: An in-COntext PRoof Agent which uses LLMs like GPTs to prove theorems in formal languages.☆67Updated 3 weeks ago
- NeqLIPS: a powerful Olympiad-level inequality prover☆39Updated 3 months ago
- A "code intepreter" for Lean☆73Updated 3 months ago
- This is the official repository for all the code of TheoremLlama☆47Updated 4 months ago
- Evaluation of neuro-symbolic engines☆40Updated last year
- The official repository for the paper Multilingual Mathematical Autoformalization☆38Updated last year
- ☆262Updated 3 months ago
- ☆82Updated 6 months ago
- Code for the paper LeanReasoner: Boosting Complex Logical Reasoning with Lean: https://arxiv.org/pdf/2403.13312.pdf☆23Updated last year
- Materials for ConceptARC paper☆109Updated last year