Alternatives and similar repositories for PENCIL

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

• LAMDASZ-ML / Self-Backtracking
  ☆47Updated 5 months ago
• WindyLee0822 / Process_Q_Model
  official implementation of paper "Process Reward Model with Q-value Rankings"
  ☆60Updated 5 months ago
• THUDM / T1
  RL Scaling and Test-Time Scaling (ICML'25)
  ☆109Updated 5 months ago
• waterhorse1 / Natural-language-RL
  Natural Language Reinforcement Learning
  ☆90Updated 6 months ago
• google-deepmind / bbeh
  ☆83Updated 2 months ago
• hkust-nlp / B-STaR
  B-STAR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners
  ☆82Updated last month
• Yu-Fangxu / FoR
  [ICML 2025] Flow of Reasoning: Training LLMs for Divergent Reasoning with Minimal Examples
  ☆101Updated last month
• MLE-Dojo / MLE-Dojo
  ☆55Updated 2 weeks ago
• ryoungj / BoLT
  Code for "Reasoning to Learn from Latent Thoughts"
  ☆112Updated 3 months ago
• jwhj / OREO
  ☆114Updated 5 months ago
• zitian-gao / SC-MCTS
  Interpretable Contrastive Monte Carlo Tree Search Reasoning
  ☆49Updated 8 months ago
• Parallel-Reasoning / APR
  [COLM 2025] Code for Paper: Learning Adaptive Parallel Reasoning with Language Models
  ☆114Updated 2 months ago
• jwliao-ai / MARFT
  MARFT stands for Multi-Agent Reinforcement Fine-Tuning. This repository implements an LLM-based multi-agent reinforcement fine-tuning fra…
  ☆49Updated last month
• Open-Source-O1 / o1_Reasoning_Patterns_Study
  ☆102Updated 7 months ago
• mukhal / ThinkPRM
  Process Reward Models That Think
  ☆45Updated last week
• GAIR-NLP / OctoThinker
  Revisiting Mid-training in the Era of Reinforcement Learning Scaling
  ☆137Updated last week
• ltzheng / SimpleTIR
  End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning
  ☆127Updated this week
• test-time-interaction / TTI
  ☆48Updated last month
• SiliangZeng / Multi-Turn-RL-Agent
  ☆62Updated last month
• JacobPfau / fillerTokens
  ☆66Updated last year
• THU-KEG / Agentic-Reward-Modeling
  [ACL 2025] Agentic Reward Modeling: Integrating Human Preferences with Verifiable Correctness Signals for Reliable Reward Systems
  ☆96Updated last month
• GuanghaoYe / Emergence-of-Thinking
  ☆52Updated 5 months ago
• GAIR-NLP / AIME-Preview
  ☆71Updated 4 months ago
• YangLing0818 / SuperCorrect-llm
  [ICLR 2025] SuperCorrect: Advancing Small LLM Reasoning with Thought Template Distillation and Self-Correction
  ☆74Updated 3 months ago
• HKUNLP / critic-rl
  [ICML 2025] Teaching Language Models to Critique via Reinforcement Learning
  ☆103Updated 2 months ago
• satori-reasoning / Satori
  [ICML 2025] Satori: Reinforcement Learning with Chain-of-Action-Thought Enhances LLM Reasoning via Autoregressive Search
  ☆103Updated last month
• Agent-E3 / ExACT
  ☆19Updated 4 months ago
• siyuyuan / evoagent
  Resources for our paper: "EvoAgent: Towards Automatic Multi-Agent Generation via Evolutionary Algorithms"
  ☆115Updated 8 months ago
• katiekang1998 / reasoning_generalization
  ☆33Updated 6 months ago
• nick7nlp / FastCuRL
  FastCuRL: Curriculum Reinforcement Learning with Stage-wise Context Scaling for Efficient LLM Reasoning
  ☆52Updated last month