Alternatives and similar repositories for MegaScience

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

• TsinghuaC3I / SSRL
  SSRL: Self-Search Reinforcement Learning
  ☆145Updated last month
• GAIR-NLP / OctoThinker
  Revisiting Mid-training in the Era of Reinforcement Learning Scaling
  ☆176Updated 2 months ago
• THUDM / DeepDive
  DeepDive: Advancing Deep Search Agents with Knowledge Graphs and Multi-Turn RL
  ☆169Updated last week
• THU-KEG / Agentic-Reward-Modeling
  [ACL 2025] Agentic Reward Modeling: Integrating Human Preferences with Verifiable Correctness Signals for Reliable Reward Systems
  ☆106Updated 4 months ago
• mukhal / ThinkPRM
  Process Reward Models That Think
  ☆55Updated 3 months ago
• TIGER-AI-Lab / General-Reasoner
  General Reasoner: Advancing LLM Reasoning Across All Domains [NeurIPS25]
  ☆179Updated 4 months ago
• DAMO-NLP-SG / LongPO
  [ICLR 2025] LongPO: Long Context Self-Evolution of Large Language Models through Short-to-Long Preference Optimization
  ☆40Updated 7 months ago
• Kwai-Klear / KlearReasoner
  Klear-Reasoner: Advancing Reasoning Capability via Gradient-Preserving Clipping Policy Optimization
  ☆73Updated 2 weeks ago
• ReasoningTransfer / Transferability-of-LLM-Reasoning
  ☆98Updated last month
• ByteDance-Seed / WideSearch
  WideSearch: Benchmarking Agentic Broad Info-Seeking
  ☆95Updated this week
• multimodal-art-projection / REER_DeepWriter
  REverse-Engineered Reasoning for Open-Ended Generation
  ☆69Updated last month
• THUDM / T1
  RL Scaling and Test-Time Scaling (ICML'25)
  ☆111Updated 8 months ago
• TIGER-AI-Lab / CritiqueFineTuning
  Code for "Critique Fine-Tuning: Learning to Critique is More Effective than Learning to Imitate" [COLM 2025]
  ☆173Updated 3 months ago
• MiniMax-AI / SynLogic
  The official repo of SynLogic: Synthesizing Verifiable Reasoning Data at Scale for Learning Logical Reasoning and Beyond
  ☆167Updated 3 months ago
• yuleiqin / RAIF
  A Recipe for Building LLM Reasoners to Solve Complex Instructions
  ☆24Updated 2 months ago
• xufangzhi / phi-Decoding
  [ACL 2025] An inference-time decoding strategy with adaptive foresight sampling
  ☆104Updated 4 months ago
• SihengLi99 / SEALONG
  Large Language Models Can Self-Improve in Long-context Reasoning
  ☆73Updated 10 months ago
• efficientscaling / Z1
  [EMNLP 2025 Industry] Repo for "Z1: Efficient Test-time Scaling with Code"
  ☆64Updated 6 months ago
• zjunlp / LightThinker
  [EMNLP 2025] LightThinker: Thinking Step-by-Step Compression
  ☆104Updated 6 months ago
• StigLidu / DualDistill
  [EMNLP 2025] The official implementation for paper "Agentic-R1: Distilled Dual-Strategy Reasoning"
  ☆100Updated last month
• open-compass / GPassK
  [ACL 2025] Are Your LLMs Capable of Stable Reasoning?
  ☆30Updated 2 months ago
• metal-chart-generation / metal
  ☆40Updated 4 months ago
• QwenLM / Self-Lengthen
  ☆90Updated 11 months ago
• xufangzhi / Genius
  [ACL 2025] A Generalizable and Purely Unsupervised Self-Training Framework
  ☆71Updated 4 months ago
• tianyi-lab / MoE-Embedding
  [ICLR 2025 Oral] "Your Mixture-of-Experts LLM Is Secretly an Embedding Model For Free"
  ☆82Updated 11 months ago
• bespokelabsai / verifiers
  Verifiers for LLM Reinforcement Learning
  ☆74Updated 5 months ago
• zhenyuhe00 / SWE-Swiss
  SWE-Swiss: A Multi-Task Fine-Tuning and RL Recipe for High-Performance Issue Resolution
  ☆88Updated 2 weeks ago
• mathllm / MathCoder2
  ☆69Updated 11 months ago
• test-time-interaction / TTI
  ☆62Updated 4 months ago
• inclusionAI / PromptCoT
  A unified suite for generating elite reasoning problems and training high-performance LLMs, including pioneering attention-free architect…
  ☆106Updated 2 weeks ago