Open-source alternatives to Code R1

SQL-R1: Training Natural Language to SQL Reasoning Model By Reinforcement Learning

Dream-Coder 7B is a diffusion LLM for code trained exclusively on open-source data across its development stages—adaptation, supervised fine-tuning, and reinforcement learning. It achieves an impressive 21.4% pass@1 on LiveCodeBench (2410-2505), outperforming other open-source diffusion LLMs by…

Z1: Efficient Test-time Scaling with Code Train Large Language Model to Reason with Shifted Thinking

📄 Paper | 🌐 Dataset (v2) | 📘 Model (v2)

📄 Paper | 🌐 Dataset | 📘 Model

#

SWE-Fixer: Training Open-Source LLMs for Effective and Efficient GitHub Issue Resolution

CodeV-R1 is an innovative open-source Large Language Model (LLM) specifically designed for the generation of high-quality Verilog code, addressing the challenges faced by existing models in this domain.

[arXiv](https://arxiv.org/abs/2507.08649) | [Codes](https://github.com/Leanabell-LM/Leanabell-Prover-V2) | [🤗 Huggingface] Xingguang Ji, Yahui Liu, Qi Wang$^{\heartsuit}$, Jingyuan Zhang, Yang Yue, Rui Shi, Chenxi Sun, Fuzheng Zhang, Guorui Zhou, Kun Gai

This repository contains the official code and resources for the paper "Synthesizing Sheet Music Problems for Evaluation and Reinforcement Learning".

Fortune is a framework for symbolic table reasoning using large language models (LLMs). Unlike prior approaches that rely heavily on supervised fine-tuning (SFT) with annotated formulas, Fortune introduces a reinforcement learning (RL) framework that learns directly from binary answer…

rStar2-Agent

Training performance of MiroMind-M1-RL-7B on AIME24 and AIME25.

This is the Github Repo for the paper: VeriReason: Reinforcement Learning with Testbench Feedback for Reasoning-Enhanced Verilog Generation

LeetCodeDataset is a dataset comprising Python LeetCode problems designed for training and evaluating Large Language Models (LLMs).

Nemo-Skills is a collection of pipelines to improve "skills" of large language models (LLMs). We support everything needed for LLM development, from synthetic data generation, to model training, to evaluation on a wide range of benchmarks. Start developing on a local workstation and move to a…

An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model

COLM’25 DeepRetrieval — 🔥 Training Search Agent by RLVR with Retrieval Outcome

Search-R1 is a distributed training system and reinforcement learning framework designed to create search-augmented language models. It provides an architecture for scaling model workloads across head and worker nodes while optimizing how models interleave internal reasoning with external tool calls. The system focuses on refining model behavior through custom reward signals and reinforcement learning to improve tool-use formatting and information retrieval. It implements an interleaved reasoning-search loop that allows models to alternate between internal thought generation and external data

🤗 Model | 📊 Dataset | 📖 Paper

We introduce StepFun-Prover-Preview, large language models designed for formal theorem proving through tool-integrated reasoning. Using a reinforcement learning pipeline that incorporates tool-based interactions, StepFun-Prover Preview can achieve strong performance in generating Lean 4 proofs…

Training Software Engineering Agents and Verifiers with SWE-Gym

ICLR'26 MedAgentGYM: Training LLM Agents for Code-Based Medical Reasoning at Scale

Yihe Deng , Nanyun Peng , Kai-Wei Chang