Alternatives and similar repositories for SkyRL

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

• facebookresearch / sweet_rl
  Benchmark and research code for the paper SWEET-RL Training Multi-Turn LLM Agents onCollaborative Reasoning Tasks
  ☆219Updated last month
• eddycmu / demystify-long-cot
  ☆297Updated 3 weeks ago
• sail-sg / oat
  🌾 OAT: A research-friendly framework for LLM online alignment, including reinforcement learning, preference learning, etc.
  ☆379Updated last week
• SWE-Gym / SWE-Gym
  Code for Paper: Training Software Engineering Agents and Verifiers with SWE-Gym [ICML 2025]
  ☆486Updated last month
• TIGER-AI-Lab / verl-tool
  A version of verl to support tool use
  ☆251Updated this week
• GAIR-NLP / ToRL
  ☆220Updated 3 weeks ago
• NVIDIA-NeMo / RL
  Scalable toolkit for efficient model reinforcement
  ☆438Updated this week
• cmu-l3 / l1
  L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning
  ☆220Updated last month
• ypwang61 / One-Shot-RLVR
  official repository for “Reinforcement Learning for Reasoning in Large Language Models with One Training Example”
  ☆290Updated this week
• huggingface / Math-Verify
  ☆773Updated last month
• facebookresearch / swe-rl
  Official codebase for "SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution"
  ☆545Updated 3 months ago
• knoveleng / open-rs
  Official repo for paper: "Reinforcement Learning for Reasoning in Small LLMs: What Works and What Doesn't"
  ☆236Updated last month
• sail-sg / oat-zero
  A lightweight reproduction of DeepSeek-R1-Zero with indepth analysis of self-reflection behavior.
  ☆240Updated 2 months ago
• sunblaze-ucb / Intuitor
  Code for the paper: "Learning to Reason without External Rewards"
  ☆295Updated this week
• RAGEN-AI / VAGEN
  ☆169Updated this week
• openpsi-project / ReaLHF
  Super-Efficient RLHF Training of LLMs with Parameter Reallocation
  ☆303Updated last month
• PRIME-RL / ImplicitPRM
  Repo of paper "Free Process Rewards without Process Labels"
  ☆153Updated 3 months ago
• ByteDance-Seed / Agent-R
  Resources for our paper: "Agent-R: Training Language Model Agents to Reflect via Iterative Self-Training"
  ☆149Updated last week
• shangshang-wang / Tina
  Tina: Tiny Reasoning Models via LoRA
  ☆258Updated 3 weeks ago
• 0russwest0 / Awesome-Agent-RL
  ☆233Updated 3 weeks ago
• RUCAIBox / Slow_Thinking_with_LLMs
  A series of technical report on Slow Thinking with LLM
  ☆699Updated 2 weeks ago
• agentica-project / verl-pipeline
  Async pipelined version of Verl
  ☆100Updated 2 months ago
• ReTool-RL / ReTool
  ☆119Updated last month
• QwenLM / ParScale
  Parallel Scaling Law for Language Model — Beyond Parameter and Inference Time Scaling
  ☆395Updated last month
• ganler / code-r1
  Reproducing R1 for Code with Reliable Rewards
  ☆218Updated last month
• GAIR-NLP / LIMR
  ☆202Updated 4 months ago
• zwhe99 / DeepMath
  A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning
  ☆220Updated 2 weeks ago
• THUDM / ReST-MCTS
  ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search (NeurIPS 2024)
  ☆639Updated 5 months ago
• allenai / reward-bench
  RewardBench: the first evaluation tool for reward models.
  ☆604Updated last week
• StonyBrookNLP / appworld
  🌍 Repository for "AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agent", ACL'24 Best Resource Pap…
  ☆212Updated last month