mlsanityData to 7 Oct 2026

Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learning

arXiv 2502.14768 ↗First posted 20 Feb 2025cs.CL cs.AIcited by 260

On the map: LLM reasoning → Reinforcement learning for reasoning

Abstract (arXiv)

Inspired by the success of DeepSeek-R1, we explore the potential of rule-based reinforcement learning (RL) in large reasoning models. To analyze reasoning dynamics, we use synthetic logic puzzles as training data due to their controllable complexity and straightforward answer verification. We make some key technical contributions that lead to effective and stable RL training: a system prompt that emphasizes the thinking and answering process, a stringent format reward function that penalizes outputs for taking shortcuts, and a straightforward training recipe that achieves stable convergence. Our 7B model develops advanced reasoning skills-such as reflection, verification, and summarization-that are absent from the logic corpus. Remarkably, after training on just 5K logic problems, it demonstrates generalization abilities to the challenging math benchmarks AIME and AMC.

Key facts. Cited by 260 papers in the map (data through 7 Oct 2026). Placed in Reinforcement learning for reasoning, one of 17 directions in LLM reasoning. Builds on 0 of its 24 references that are in the map. First posted on arXiv 20 Feb 2025.

Builds on

0 of 24 references.

No references here yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 189; 2026: 71.

260 papers.

Sort:

By area:

  1. 2025Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learningcited by 1,371
  2. 2025SimpleRL-Zoo: Investigating and Taming Zero Reinforcement Learning for Open Base Models in the Wildcited by 505
  3. 2025Video-R1: Reinforcing Video Reasoning in MLLMscited by 464
  4. 2025Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Modelscited by 381
  5. 2025ToolRL: Reward is All Tool Learning Needscited by 342
  6. 2025Absolute Zero: Reinforced Self-play Reasoning with Zero Datacited by 323
  7. 2025WebThinker: Empowering Large Reasoning Models with Deep Research Capabilitycited by 320
  8. 2025From System 1 to System 2: A Survey of Reasoning Large Language Modelscited by 319
  9. 2025Reinforcement Learning with Verifiable Rewards Implicitly Incentivizes Correct Reasoning in Base LLMscited by 276
  10. 2025Spurious Rewards: Rethinking Training Signals in RLVRcited by 199
  11. 2025A Survey of Reinforcement Learning for Large Reasoning Modelscited by 175
  12. 2025Crossing the Reward Bridge: Expanding RL with Verifiable Rewards Across Diverse Domainscited by 150
38 more
  1. 2025Pass@k Training for Adaptively Balancing Exploration and Exploitation of Large Reasoning Modelscited by 134
  2. 2025Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systemscited by 125
  3. 2025Between Underthinking and Overthinking: An Empirical Study of Reasoning Length and correctness in LLMscited by 115
  4. 2025Reinforcement Learning with Rubric Anchorscited by 108
  5. 2025Learning What Reinforcement Learning Can't: Interleaved Online Fine-Tuning for Hardest Questionscited by 95
  6. 2025Agent Lightning: Train ANY AI Agents with Reinforcement Learningcited by 94
  7. 2025CPPO: Accelerating the Training of Group Relative Policy Optimization-Based Reasoning Modelscited by 93
  8. 2025A Sober Look at Progress in Language Model Reasoning: Pitfalls and Paths to Reproducibilitycited by 89
  9. 2025Curriculum Reinforcement Learning from Easy to Hard Tasks Improves LLM Reasoningcited by 89
  10. 2025ReMA: Learning to Meta-think for LLMs with Multi-Agent Reinforcement Learningcited by 78
  11. 2025Concise Reasoning via Reinforcement Learningcited by 78
  12. 2026Scaling Reasoning Efficiently via Relaxed On-Policy Distillationcited by 71
  13. 2025R1-Reward: Training Multimodal Reward Model Through Stable Reinforcement Learningcited by 65
  14. 2025A Survey on (M)LLM-Based GUI Agentscited by 61
  15. 2025UFT: Unifying Supervised and Reinforcement Fine-Tuningcited by 58
  16. 2025Blending Supervised and Reinforcement Fine-Tuning with Prefix Samplingcited by 57
  17. 2025e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMscited by 56
  18. 2025One Token to Fool LLM-as-a-Judgecited by 56
  19. 2025Enigmata: Scaling Logical Reasoning in Large Language Models with Synthetic Verifiable Puzzlescited by 53
  20. 2025SRPO: Enhancing Multimodal LLM Reasoning via Reflection-Aware Reinforcement Learningcited by 53
  21. 2025OneThinker: All-in-one Reasoning Model for Image and Videocited by 52
  22. 2025Inverse Scaling in Test-Time Computecited by 49
  23. 2025SynLogic: Synthesizing Verifiable Reasoning Data at Scale for Learning Logical Reasoning and Beyondcited by 47
  24. 2025QwenLong-L1: Towards Long-Context Large Reasoning Models with Reinforcement Learningcited by 46
  25. 2025DUMP: Automated Distribution-Level Curriculum Learning for RL-based LLM Post-trainingcited by 45
  26. 2025Think or Not Think: A Study of Explicit Thinking in Rule-Based Visual Reinforcement Fine-Tuningcited by 44
  27. 2025Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMscited by 43
  28. 2025An Empirical Study on Reinforcement Learning for Reasoning-Search Interleaved LLM Agentscited by 43
  29. 2025Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoningcited by 43
  30. 2025From f(x) and g(x) to f(g(x)): LLMs Learn New Skills in RL by Composing Old Onescited by 40
  31. 2025Arctic-Text2SQL-R1: Simple Rewards, Strong Reasoning in Text-to-SQLcited by 38
  32. 2025Embodied-R: Collaborative Framework for Activating Embodied Spatial Reasoning in Foundation Models via Reinforcement Learningcited by 37
  33. 2025Making Slow Thinking Faster: Compressing LLM Chain-of-Thought via Step Entropycited by 37
  34. 2025Enhancing LLM Reasoning with Iterative DPO: A Comprehensive Empirical Investigationcited by 36
  35. 2025Jigsaw-R1: A Study of Rule-based Visual Reinforcement Learning with Jigsaw Puzzlescited by 36
  36. 2025Learning to Reason for Long-Form Story Generationcited by 34
  37. 2025QiMeng-CodeV-R1: Reasoning-Enhanced Verilog Generationcited by 34
  38. 2026RLCSD: Reinforcement Learning with Contrastive On-Policy Self-Distillationcited by 33

50 most cited of 260 All 260 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
  2. 2025Scaling Up RL: Unlocking Diverse Reasoning in LLMs via Prolonged Training
  3. 2025Revisiting Reinforcement Learning for LLM Reasoning from A Cross-Domain Perspective
  4. 2025RL of Thoughts: Navigating LLM Reasoning with Inference-time Reinforcement Learning
  5. 2025QuestA: Expanding Reasoning Capacity in LLMs via Question Augmentation
  6. 2025LogicPuzzleRL: Cultivating Robust Mathematical Reasoning in LLMs via Reinforcement Learning
  7. 2026PCL-Reasoner-V1.5: Advancing Math Reasoning with Offline Reinforcement Learning
  8. 2025Reasoning Core: A Scalable RL Environment for LLM Symbolic Reasoning