Alternatives and similar repositories for RL2

Users that are interested in RL2 are comparing it to the libraries listed below

• uclaml / SPPO
  The official implementation of Self-Play Preference Optimization (SPPO)
  ☆569Updated 5 months ago
• RLHFlow / Online-DPO-R1
  Codebase for Iterative DPO Using Rule-based Rewards
  ☆252Updated 3 months ago
• Zefan-Cai / KVCache-Factory
  Unified KV Cache Compression Methods for Auto-Regressive Models
  ☆1,204Updated 6 months ago
• cmriat / l0
  A scalable, end-to-end training pipeline for general-purpose agents
  ☆339Updated 2 weeks ago
• AIoT-MLSys-Lab / SVD-LLM
  [ICLR 2025🔥] SVD-LLM & [NAACL 2025🔥] SVD-LLM V2
  ☆231Updated 3 months ago
• KodCode-AI / kodcode
  ✨ A synthetic dataset generation framework that produces diverse coding questions and verifiable solutions - all in one framwork
  ☆242Updated last month
• Qihoo360 / 360-LLaMA-Factory
  adds Sequence Parallelism into LLaMA-Factory
  ☆527Updated this week
• RLHFlow / Minimal-RL
  ☆216Updated 2 months ago
• Infini-AI-Lab / TriForce
  [COLM 2024] TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decoding
  ☆258Updated 10 months ago
• zhuhanqing / APOLLO
  APOLLO: SGD-like Memory, AdamW-level Performance; MLSys'25 Oustanding Paper Honorable Mention
  ☆242Updated 2 months ago
• RLHFlow / Self-rewarding-reasoning-LLM
  Recipes to train the self-rewarding reasoning LLMs.
  ☆225Updated 4 months ago
• Simple-Efficient / RL-Factory
  Train your Agent model via our easy and efficient framework
  ☆1,277Updated this week
• wangyu-ustc / MemoryLLM
  The official implementation of the ICML 2024 paper "MemoryLLM: Towards Self-Updatable Large Language Models" and "M+: Extending MemoryLLM…
  ☆182Updated last week
• FanbinLu / STEVE-R1
  R1-like Computer-use Agent
  ☆78Updated 3 months ago
• RLHFlow / Online-RLHF
  A recipe for online RLHF and online iterative DPO.
  ☆522Updated 6 months ago
• bytedance / ABQ-LLM
  An acceleration library that supports arbitrary bit-width combinatorial quantization operations
  ☆227Updated 9 months ago
• HKUDS / SepLLM
  [ICML 2025] "SepLLM: Accelerate Large Language Models by Compressing One Segment into One Separator"
  ☆249Updated 2 weeks ago
• yfzhang114 / r1_reward
  ✨✨R1-Reward: Training Multimodal Reward Model Through Stable Reinforcement Learning
  ☆183Updated 2 months ago
• xinghaow99 / BitStack
  [ICLR 2025] BitStack: Any-Size Compression of Large Language Models in Variable Memory Environments
  ☆36Updated 5 months ago
• Ledzy / BAdam
  [NeurIPS 2024] BAdam: A Memory Efficient Full Parameter Optimization Method for Large Language Models
  ☆264Updated 4 months ago
• HJYao00 / Mulberry
  Mulberry, an o1-like Reasoning and Reflection MLLM Implemented via Collective MCTS
  ☆1,205Updated 3 months ago
• ByteDance-Seed / ShadowKV
  [ICML 2025 Spotlight] ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference
  ☆209Updated 2 months ago
• pat-jj / DeepRetrieval
  [COLM'25] DeepRetrieval - 🔥 Training Search Agent with Retrieval Outcomes via Reinforcement Learning
  ☆585Updated last month
• LZY-the-boys / Twin-Merging
  [NeurIPS2024] Twin-Merging: Dynamic Integration of Modular Expertise in Model Merging
  ☆136Updated 4 months ago
• QwenLM / ParScale
  Parallel Scaling Law for Language Model — Beyond Parameter and Inference Time Scaling
  ☆412Updated 2 months ago
• zhiyuanhubj / Meta-Ability-Alignment
  Official code of paper "Beyond 'Aha!': Toward Systematic Meta-Abilities Alignment in Large Reasoning Models"
  ☆79Updated last month
• cmu-l3 / l1
  L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning
  ☆228Updated 2 months ago
• agentica-project / verl-pipeline
  Async pipelined version of Verl
  ☆108Updated 3 months ago
• THUDM / slime
  slime is a LLM post-training framework aiming for RL Scaling.
  ☆596Updated this week
• NVIDIA-NeMo / RL
  Scalable toolkit for efficient model reinforcement
  ☆499Updated this week