Alternatives and similar repositories for self-improvement-reversal

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

• GAIR-NLP / weak-to-strong-reasoning
  ☆58Updated last year
• KbsdJames / omni-math-rule
  The rule-based evaluation subset and code implementation of Omni-MATH
  ☆25Updated 11 months ago
• GAIR-NLP / ReasonEval
  [AAAI 2025 oral] Evaluating Mathematical Reasoning Beyond Accuracy
  ☆76Updated last month
• koalazf99 / nanoverl
  Collections of RLxLM experiments using minimal codes
  ☆14Updated 9 months ago
• GAIR-NLP / BeHonest
  BeHonest: Benchmarking Honesty in Large Language Models
  ☆34Updated last year
• hkust-nlp / mstar
  [ICML 2025] M-STAR (Multimodal Self-Evolving TrAining for Reasoning) Project. Diving into Self-Evolving Training for Multimodal Reasoning
  ☆69Updated 4 months ago
• KbsdJames / Omni-MATH
  The official repository of the Omni-MATH benchmark.
  ☆88Updated 11 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
• hkust-nlp / Laser
  Laser: Learn to Reason Efficiently with Adaptive Length-based Reward Shaping
  ☆60Updated 6 months ago
• zzli2022 / TLDR
  Code for Research Project TLDR
  ☆24Updated 4 months ago
• test-time-interaction / TTI
  ☆64Updated 5 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
• jinzhuoran / RAG-RewardBench
  RAG-RewardBench: Benchmarking Reward Models in Retrieval Augmented Generation for Preference Alignment
  ☆16Updated 11 months ago
• GAIR-NLP / Safety-J
  Safety-J: Evaluating Safety with Critique
  ☆16Updated last year
• HKUNLP / critic-rl
  [ICML 2025] Teaching Language Models to Critique via Reinforcement Learning
  ☆118Updated 6 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
• BytedTsinghua-SIA / Enigmata
  Resources for the Enigmata Project.
  ☆72Updated 3 months ago
• FreedomIntelligence / OVM
  ☆68Updated last year
• hkust-nlp / RL-Verifier-Robustness
  From Accuracy to Robustness: A Study of Rule- and Model-based Verifiers in Mathematical Reasoning.
  ☆23Updated last month
• hanxuhu / SeqIns
  The repository of the project "Fine-tuning Large Language Models with Sequential Instructions", code base comes from open-instruct and LA…
  ☆30Updated last year
• WeiminXiong / IPR
  Watch Every Step! LLM Agent Learning via Iterative Step-level Process Refinement (EMNLP 2024 Main Conference)
  ☆63Updated last year
• lukahhcm / Awesome_Environment_Scaling
  Resources and paper list for 'Scaling Environments for Agents'. This repository accompanies our survey on how environments contribute to …
  ☆26Updated last week
• 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
• TianHongZXY / RLVR-Decomposed
  [NeurIPS 2025] Implementation for the paper "The Surprising Effectiveness of Negative Reinforcement in LLM Reasoning"
  ☆127Updated last month
• WooooDyy / MathCritique
  Implementation for the research paper "Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision".
  ☆56Updated last year
• TingchenFu / MathIF
  instruction-following benchmark for large reasoning models
  ☆45Updated 3 months ago
• hkust-nlp / GUIMid
  ☆21Updated 7 months ago
• GAIR-NLP / OctoThinker
  Revisiting Mid-training in the Era of Reinforcement Learning Scaling
  ☆180Updated 4 months ago
• rhyang2021 / ARIA
  Source code for our paper: "ARIA: Training Language Agents with Intention-Driven Reward Aggregation".
  ☆25Updated 3 months ago