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.
☆29Updated last month
Alternatives and similar repositories for LeanAgent
Users that are interested in LeanAgent are comparing it to the libraries listed below
Sorting:
- ☆45Updated 10 months ago
- A package for defining deep learning models using categorical algebraic expressions.☆61Updated last year
- LLMs + Lean, on your laptop or in the cloud☆173Updated 3 weeks ago
- Transformers for Mathematics Tutorial | Simons/SLMath Workshop on AI for Mathematics 2025☆37Updated 3 months ago
- Official repository for the paper "Can You Learn an Algorithm? Generalizing from Easy to Hard Problems with Recurrent Networks"☆59Updated 3 years ago
- ☆68Updated 3 years ago
- Learning Universal Predictors☆78Updated last year
- An environment for learning formal mathematical reasoning from scratch☆72Updated 11 months ago
- Harmonic Datasets☆43Updated last year
- Genetic programming using LLMs☆40Updated 5 months ago
- Implementing RASP transformer programming language https://arxiv.org/pdf/2106.06981.pdf.☆58Updated 3 years ago
- Tangle Software Library☆33Updated last year
- Materials for ConceptARC paper☆98Updated 9 months ago
- Evaluation of neuro-symbolic engines☆38Updated last year
- Neural theorem proving tutorial, version II☆38Updated last year
- A programming language for formal/informal computation.☆41Updated last week
- A domain-specific probabilistic programming language for modeling and inference with language models☆132Updated 3 months ago
- ☆55Updated 5 months ago
- ☆61Updated 8 months ago
- Formalizing stochastic doubly-efficient debate☆107Updated 10 months ago
- Tutorial on neural theorem proving☆174Updated last year
- LeanUniverse: A Library for Consistent and Scalable Lean4 Dataset Management☆69Updated 6 months ago
- ☆172Updated 3 months ago
- Meta-learning inductive biases in the form of useful conserved quantities.☆37Updated 2 years ago
- The Energy Transformer block, in JAX☆59Updated last year
- A Scalable Approximate Method for Probabilistic Neurosymbolic Inference☆15Updated 6 months ago
- ☆56Updated last month
- Enjoy puzzle-solving directly in your browser.☆28Updated 3 months 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
- Probabilistic programming with large language models☆129Updated last week