Alternatives and similar repositories for self-improvement-reversal

Users that are interested in self-improvement-reversal are comparing it to the libraries listed below

• KbsdJames / omni-math-rule
  The rule-based evaluation subset and code implementation of Omni-MATH
  ☆22Updated 7 months ago
• GAIR-NLP / weak-to-strong-reasoning
  ☆59Updated 11 months ago
• GAIR-NLP / ReasonEval
  [AAAI 2025 oral] Evaluating Mathematical Reasoning Beyond Accuracy
  ☆63Updated 7 months ago
• koalazf99 / nanoverl
  Collections of RLxLM experiments using minimal codes
  ☆13Updated 5 months ago
• hkust-nlp / mstar
  [ICML 2025] M-STAR (Multimodal Self-Evolving TrAining for Reasoning) Project. Diving into Self-Evolving Training for Multimodal Reasoning
  ☆63Updated 3 weeks ago
• KbsdJames / Omni-MATH
  The official repository of the Omni-MATH benchmark.
  ☆85Updated 7 months ago
• GAIR-NLP / BeHonest
  BeHonest: Benchmarking Honesty in Large Language Models
  ☆34Updated 11 months ago
• hkust-nlp / Laser
  Laser: Learn to Reason Efficiently with Adaptive Length-based Reward Shaping
  ☆52Updated 2 months ago
• rookie-joe / AutoPSV
  ☆48Updated 9 months ago
• ssmisya / PRMBench
  [ACL' 25] The official code repository for PRMBench: A Fine-grained and Challenging Benchmark for Process-Level Reward Models.
  ☆76Updated 5 months ago
• SparkJiao / dpo-trajectory-reasoning
  [EMNLP 2024] Source code for the paper "Learning Planning-based Reasoning with Trajectory Collection and Process Rewards Synthesizing".
  ☆80Updated 6 months ago
• NJU-RL / GLIDER
  [ICML 2025] Official Implementation of GLIDER
  ☆51Updated 2 months ago
• test-time-interaction / TTI
  ☆52Updated last month
• qtli / GSM-Plus
  GSM-Plus: Data, Code, and Evaluation for Enhancing Robust Mathematical Reasoning in Math Word Problems.
  ☆62Updated last year
• jinzhuoran / RAG-RewardBench
  RAG-RewardBench: Benchmarking Reward Models in Retrieval Augmented Generation for Preference Alignment
  ☆16Updated 7 months ago
• HKUNLP / critic-rl
  [ICML 2025] Teaching Language Models to Critique via Reinforcement Learning
  ☆105Updated 2 months ago
• FreedomIntelligence / OVM
  ☆68Updated last year
• hanxuhu / SeqIns
  The repository of the project "Fine-tuning Large Language Models with Sequential Instructions", code base comes from open-instruct and LA…
  ☆29Updated 8 months ago
• WangHanLinHenry / SPA-RL-Agent
  Official code for paper "SPA-RL: Reinforcing LLM Agent via Stepwise Progress Attribution"
  ☆38Updated 2 weeks 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…
  ☆33Updated 10 months ago
• WeiminXiong / IPR
  Watch Every Step! LLM Agent Learning via Iterative Step-level Process Refinement (EMNLP 2024 Main Conference)
  ☆61Updated 9 months ago
• THU-KEG / RM-Bench
  [ICLR 25 Oral] RM-Bench: Benchmarking Reward Models of Language Models with Subtlety and Style
  ☆58Updated 2 weeks ago
• BytedTsinghua-SIA / Enigmata
  Resources for the Enigmata Project.
  ☆58Updated last month
• YiCheng98 / IntegrativeDecoding
  Official Implementation for the paper "Integrative Decoding: Improving Factuality via Implicit Self-consistency"
  ☆28Updated 3 months ago
• hkust-nlp / GUIMid
  ☆21Updated 3 months ago
• hkust-nlp / dart-math
  [NeurIPS'24] Official code for *🎯DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving*
  ☆110Updated 7 months ago
• GAIR-NLP / Safety-J
  Safety-J: Evaluating Safety with Critique
  ☆16Updated last year
• hkust-nlp / RL-Verifier-Pitfalls
  Pitfalls of Rule- and Model-based Verifiers: A Case Study on Mathematical Reasoning.
  ☆21Updated 2 months ago
• genrm-star / genrm-critiques
  GenRM-CoT: Data release for verification rationales
  ☆63Updated 9 months ago
• GAIR-NLP / MetaCritique
  Evaluate the Quality of Critique
  ☆36Updated last year