stepfun-ai / StepFun-Prover-PreviewLinks
Large language models designed for formal theorem proving through tool-integrated reasoning.
☆32Updated 5 months ago
Alternatives and similar repositories for StepFun-Prover-Preview
Users that are interested in StepFun-Prover-Preview are comparing it to the libraries listed below
Sorting:
- ☆76Updated last month
- ☆47Updated 6 months ago
- Solving Inequality Proofs with Large Language Models.☆56Updated last month
- ☆42Updated last year
- An efficient implementation of the NSA (Native Sparse Attention) kernel☆128Updated 7 months ago
- ☆110Updated 4 months ago
- ☆148Updated this week
- ☆63Updated 7 months ago
- ☆165Updated last month
- [NeurIPS 2025 Spotlight] Co-Evolving LLM Coder and Unit Tester via Reinforcement Learning☆149Updated 4 months ago
- [NeurIPS 2024] Can LLMs Learn by Teaching for Better Reasoning? A Preliminary Study☆59Updated last year
- Technical report of Kimina-Prover Preview.☆353Updated 6 months ago
- ☆408Updated last month
- ☆105Updated 11 months ago
- ☆129Updated 8 months ago
- [COLM 2025] Code for Paper: Learning Adaptive Parallel Reasoning with Language Models☆139Updated last month
- ☆100Updated 6 months ago
- The official repo for "AceCoder: Acing Coder RL via Automated Test-Case Synthesis" [ACL25]☆96Updated 9 months ago
- ThetaEvolve: Test-time Learning on Open Problems, enabling RL training on AlphaEvolve/OpenEvolve and emphasizing scaling test-time comput…☆114Updated last month
- Klear-Reasoner: Advancing Reasoning Capability via Gradient-Preserving Clipping Policy Optimization☆81Updated last month
- Official implementation for DenseMixer: Improving MoE Post-Training with Precise Router Gradient☆66Updated 6 months ago
- CodeElo: Benchmarking Competition-level Code Generation of LLMs with Human-comparable Elo Ratings☆65Updated last year
- Kinetics: Rethinking Test-Time Scaling Laws☆86Updated 6 months ago
- ☆145Updated 5 months ago
- ☆71Updated last year
- Revisiting Mid-training in the Era of Reinforcement Learning Scaling☆182Updated 6 months ago
- [ICLR 2026] RPG: KL-Regularized Policy Gradient (https://arxiv.org/abs/2505.17508)☆65Updated last week
- [NeurIPS 2025] The official repo of SynLogic: Synthesizing Verifiable Reasoning Data at Scale for Learning Logical Reasoning and Beyond☆191Updated 7 months ago
- Conic10K: A large-scale dataset for closed-vocabulary math problem understanding. Accepted to EMNLP2023 Findings.☆31Updated 2 years ago
- This is the official implementation for paper "PENCIL: Long Thoughts with Short Memory".☆73Updated 8 months ago