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.
☆36Updated 3 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☆177Updated 2 months ago
- ☆45Updated 11 months ago
- A package for defining deep learning models using categorical algebraic expressions.☆61Updated last year
- Harmonic Datasets☆46Updated last year
- Learning Universal Predictors☆79Updated last year
- Evaluation of neuro-symbolic engines☆39Updated last year
- Neural theorem proving tutorial, version II☆39Updated last year
- LeanUniverse: A Library for Consistent and Scalable Lean4 Dataset Management☆70Updated 8 months ago
- Implementing RASP transformer programming language https://arxiv.org/pdf/2106.06981.pdf.☆58Updated 4 years ago
- Tutorial on neural theorem proving☆177Updated last year
- A programming language for formal/informal computation.☆41Updated last month
- ☆164Updated last year
- Transformers for Mathematics Tutorial | Simons/SLMath Workshop on AI for Mathematics 2025☆40Updated 5 months ago
- ☆57Updated 6 months ago
- Code and data for the paper "Why think step by step? Reasoning emerges from the locality of experience"☆61Updated 5 months ago
- Benchmark for undergraduate-level formal mathematics☆108Updated 11 months ago
- Materials for ConceptARC paper☆102Updated 10 months ago
- Repo for solving arc problems with an Neural Cellular Automata☆20Updated 3 months ago
- A reading list of relevant papers and projects on foundation model annotation☆27Updated 6 months ago
- Probabilistic programming with large language models☆135Updated last month
- A domain-specific probabilistic programming language for modeling and inference with language models☆135Updated 4 months ago
- ☆63Updated 10 months ago
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆128Updated 3 years ago
- Formalizing stochastic doubly-efficient debate☆108Updated 11 months ago
- An environment for learning formal mathematical reasoning from scratch☆72Updated last year
- PyTorch Implementation of the paper "A Neuro-vector-symbolic architecture for Solving Raven's Progressive Matrices" published in Nature M…☆94Updated 2 years ago
- Understanding how features learned by neural networks evolve throughout training☆39Updated 10 months ago
- Genetic programming using LLMs☆45Updated 6 months ago
- Language-annotated Abstraction and Reasoning Corpus☆93Updated 2 years ago
- A long-horizon, sparse-reward math environment for reinforcement learning. Official code repo for "What makes Math problems hard for rein…☆30Updated last month