Alternatives and similar repositories for BAPO

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

• KbsdJames / Omni-MATH
  The official repository of the Omni-MATH benchmark.
  ☆88Updated 11 months ago
• ltzheng / SimpleTIR
  End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning
  ☆330Updated 2 months ago
• WooooDyy / MathCritique
  Implementation for the research paper "Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision".
  ☆56Updated last year
• Vance0124 / Token-level-Direct-Preference-Optimization
  Reference implementation for Token-level Direct Preference Optimization(TDPO)
  ☆148Updated 9 months ago
• IAAR-Shanghai / xVerify
  xVerify: Efficient Answer Verifier for Reasoning Model Evaluations
  ☆139Updated 2 weeks ago
• GAIR-NLP / LIMR
  ☆212Updated 9 months ago
• CMU-AIRe / MRT
  Research Code for preprint "Optimizing Test-Time Compute via Meta Reinforcement Finetuning".
  ☆115Updated 3 months ago
• ruixin31 / Spurious_Rewards
  ☆344Updated 4 months ago
• hkust-nlp / dart-math
  [NeurIPS'24] Official code for *🎯DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving*
  ☆119Updated 11 months ago
• hkust-nlp / Laser
  Laser: Learn to Reason Efficiently with Adaptive Length-based Reward Shaping
  ☆60Updated 6 months ago
• CJReinforce / PURE
  Official code for the paper, "Stop Summation: Min-Form Credit Assignment Is All Process Reward Model Needs for Reasoning"
  ☆141Updated last month
• PRIME-RL / ImplicitPRM
  Repo of paper "Free Process Rewards without Process Labels"
  ☆166Updated 8 months ago
• RLHFlow / RAFT
  This is an official implementation of the Reward rAnked Fine-Tuning Algorithm (RAFT), also known as iterative best-of-n fine-tuning or re…
  ☆37Updated last year
• TIGER-AI-Lab / General-Reasoner
  General Reasoner: Advancing LLM Reasoning Across All Domains [NeurIPS25]
  ☆204Updated this week
• inclusionAI / PromptCoT
  A unified suite for generating elite reasoning problems and training high-performance LLMs, including pioneering attention-free architect…
  ☆128Updated last month
• OpenBMB / OlympiadBench
  [ACL 2024]Official GitHub repo for OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scie…
  ☆174Updated 5 months ago
• QwenLM / ProcessBench
  Official repository for ACL 2025 paper "ProcessBench: Identifying Process Errors in Mathematical Reasoning"
  ☆179Updated 6 months ago
• cmu-l3 / l1
  L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning
  ☆257Updated 6 months ago
• SparkJiao / dpo-trajectory-reasoning
  [EMNLP 2024] Source code for the paper "Learning Planning-based Reasoning with Trajectory Collection and Process Rewards Synthesizing".
  ☆82Updated 10 months ago
• rookie-joe / AutoPSV
  ☆51Updated last year
• ssmisya / PRMBench
  [ACL' 25] The official code repository for PRMBench: A Fine-grained and Challenging Benchmark for Process-Level Reward Models.
  ☆84Updated 9 months ago
• thu-ml / Noise-Contrastive-Alignment
  Code accompanying the paper "Noise Contrastive Alignment of Language Models with Explicit Rewards" (NeurIPS 2024)
  ☆57Updated last year
• limenlp / verl
  AdaRFT: Efficient Reinforcement Finetuning via Adaptive Curriculum Learning
  ☆48Updated 5 months ago
• BytedTsinghua-SIA / Enigmata
  Resources for the Enigmata Project.
  ☆73Updated 3 months ago
• sail-sg / CPO
  [NeurIPS 2024] The official implementation of paper: Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMs.
  ☆132Updated 8 months ago
• UCSB-NLP-Chang / ThinkPrune
  ☆45Updated 2 months ago
• GAIR-NLP / OctoThinker
  Revisiting Mid-training in the Era of Reinforcement Learning Scaling
  ☆180Updated 4 months ago
• genrm-star / genrm-critiques
  GenRM-CoT: Data release for verification rationales
  ☆67Updated last year
• zjunlp / LightThinker
  [EMNLP 2025] LightThinker: Thinking Step-by-Step Compression
  ☆123Updated 7 months ago
• GAIR-NLP / ReasonEval
  [AAAI 2025 oral] Evaluating Mathematical Reasoning Beyond Accuracy
  ☆76Updated last month