mlsanityData to 14 Oct 2026

SynLogic: Synthesizing Verifiable Reasoning Data at Scale for Learning Logical Reasoning and Beyond

arXiv 2505.19641 ↗First posted 26 May 2025cs.AI cs.CLcited by 50

On the map: LLM reasoning → Reinforcement learning for reasoning

Abstract (arXiv)

Recent advances such as OpenAI-o1 and DeepSeek R1 have demonstrated the potential of Reinforcement Learning (RL) to enhance reasoning abilities in Large Language Models (LLMs). While open-source replication efforts have primarily focused on mathematical and coding domains, methods and resources for developing general reasoning capabilities remain underexplored. This gap is partly due to the challenge of collecting diverse and verifiable reasoning data suitable for RL. We hypothesize that logical reasoning is critical for developing general reasoning capabilities, as logic forms a fundamental building block of reasoning. In this work, we present SynLogic, a data synthesis framework and dataset that generates diverse logical reasoning data at scale, encompassing 35 diverse logical reasoning tasks. The SynLogic approach enables controlled synthesis of data with adjustable difficulty and quantity. Importantly, all examples can be verified by simple rules, making them ideally suited for RL with verifiable rewards. In our experiments, we validate the effectiveness of RL training on the SynLogic dataset based on 7B and 32B models. SynLogic leads to state-of-the-art logical reasoning performance among open-source datasets, surpassing DeepSeek-R1-Distill-Qwen-32B by 6 points on BBEH. Furthermore, mixing SynLogic data with mathematical and coding tasks improves the training efficiency of these domains and significantly enhances reasoning generalization. Notably, our mixed training model outperforms DeepSeek-R1-Zero-Qwen-32B across multiple benchmarks. These findings position SynLogic as a valuable resource for advancing the broader reasoning capabilities of LLMs. We open-source both the data synthesis pipeline and the SynLogic dataset at https://github.com/MiniMax-AI/SynLogic.

Key facts. Cited by 50 papers in the map (data through 14 Oct 2026). Placed in Reinforcement learning for reasoning, one of 17 directions in LLM reasoning. Builds on 18 of its 29 references that are in the map. First posted on arXiv 26 May 2025.

Builds on

18 of 29 references.

Closest ancestors · 6

Same direction, newest first

  1. 2025SRPO: A Cross-Domain Implementation of Large-Scale Reinforcement Learning on LLM19 Apr
  2. 2025Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model31 Mar
  3. 2025SimpleRL-Zoo: Investigating and Taming Zero Reinforcement Learning for Open Base Models in the Wild24 Mar
  4. 2025DAPO: An Open-Source LLM Reinforcement Learning System at Scale18 Mar
  5. 2025Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRs3 Mar
  6. 2025Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learning20 Feb

Other references · 12

  1. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  2. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,371
  3. 2024Qwen2.5 Technical Reportcited by 4,942
  4. 2023GPQA: A Graduate-Level Google-Proof Q&A Benchmarkcited by 2,879
  5. 2024LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Codecited by 2,004
  6. 2022Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Themcited by 1,807
  7. 2025BIG-Bench Extra Hardcited by 125
  8. 2024On Memorization of Large Language Models in Logical Reasoningcited by 117
  9. 2025ACECODER: Acing Coder RL via Automated Test-Case Synthesiscited by 93
  10. 2024KOR-Bench: Benchmarking Language Models on Knowledge-Orthogonal Reasoning Taskscited by 70
  11. 2023Assessing Logical Puzzle Solving in Large Language Models: Insights from a Minesweeper Case Studycited by 15
  12. 2024LogicPro: Improving Complex Logical Reasoning via Program-Guided Learningcited by 14

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 19; 2026: 31.

50 papers.

Sort:

By area:

  1. 2025MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attentioncited by 263
  2. 2025A Survey of Reinforcement Learning for Large Reasoning Modelscited by 180
  3. 2025WebExplorer: Explore and Evolve for Training Long-Horizon Web Agentscited by 92
  4. 2025RLVE: Scaling Up Reinforcement Learning for Language Models with Adaptive Verifiable Environmentscited by 50
  5. 2025Jigsaw-R1: A Study of Rule-based Visual Reinforcement Learning with Jigsaw Puzzlescited by 36
  6. 2025SPELL: Self-Play Reinforcement Learning for Evolving Long-Context Language Modelscited by 29
  7. 2025InternBootcamp: Boosting LLM Reasoning with Verifiable Task Scalingcited by 20
  8. 2025AgentFrontier: Expanding the Capability Frontier of LLM Agents with ZPD-Guided Data Synthesiscited by 14
  9. 2025ReCode: Updating Code API Knowledge with Reinforcement Learningcited by 12
  10. 2026Good SFT Optimizes for SFT, Better SFT Prepares for Reinforcement Learningcited by 11
  11. 2026F-GRPO: Don't Let Your Policy Learn the Obvious and Forget the Rarecited by 11
  12. 2025SLR: Automated Synthesis for Scalable Logical Reasoningcited by 6
38 more
  1. 2025Mirage or Method? How Model-Task Alignment Induces Divergent RL Conclusionscited by 6
  2. 2025Towards an AI Musician: Synthesizing Sheet Music Problems for Musical Reasoningcited by 6
  3. 2026A Survey on Evaluating Quality and Trustworthiness in LLM-Generated Datacited by 6
  4. 2025Towards Self-Evolving Benchmarks: Synthesizing Agent Trajectories via Test-Time Exploration under Validate-by-Reproduce Paradigmcited by 5
  5. 2025Foundational Automatic Evaluators: Scaling Multi-Task Generative Evaluator Training for Reasoning-Centric Domainscited by 5
  6. 2026Pushing the Boundaries of Natural Reasoning: Interleaved Bonus from Formal-Logic Verificationcited by 5
  7. 2026ReSyn: Autonomously Scaling Synthetic Environments for Reasoning Modelscited by 5
  8. 2025Sound and Complete Neurosymbolic Reasoning with LLM-Grounded Interpretationscited by 4
  9. 2025INTELLECT-3: Technical Reportcited by 4
  10. 2025More Than One Teacher: Adaptive Multi-Guidance Policy Optimization for Diverse Explorationcited by 3
  11. 2026TRON: Targeted Rule-Verifiable Online Environments for Visual Reasoning RLcited by 3
  12. 2026Reasoning Core: A Scalable Procedural Data Generation Suite for Symbolic Pre-training and Post-Trainingcited by 2
  13. 2026SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMscited by 2
  14. 2026Logic Before Language: Pre-pretraining on Formal Derivations Fosters Skill Acquisition and Compressibilitycited by 2
  15. 2025Propositional Logic for Probing Generalization in Neural Networkscited by 1
  16. 2026UltraLogic: Enhancing LLM Reasoning through Large-Scale Data Synthesis and Bipolar Float Rewardcited by 1
  17. 2026TL-GRPO: Turn-Level RL for Reasoning-Guided Iterative Optimizationcited by 1
  18. 2026Can RL Teach Long-Horizon Reasoning to LLMs? Expressiveness Is Keycited by 1
  19. 2026Models Can Model, But Can't Bind: Structured Grounding in Text-to-Optimizationcited by 1
  20. 2026Reasoning Quality Emerges Early: Data Curation for Reasoning Modelscited by 1
  21. 2026Verifiable Visual Rewards Transfer from Synthetic Scenes to Natural Promptscited by 1
  22. 2025PuzzleClone: A DSL-Powered Framework for Synthesizing Verifiable Datacited by 0
  23. 2026Cognitively Layered Data Synthesis for Domain Adaptation of LLMs to Space Situational Awarenesscited by 0
  24. 2026From Pixels to Digital Agents: An Empirical Study on the Taxonomy and Technological Trends of Reinforcement Learning Environmentscited by 0
  25. 2026Apriel-Reasoner: RL Post-Training for General-Purpose and Efficient Reasoningcited by 0
  26. 2026SUPERNOVA: Eliciting General Reasoning in LLMs with Reinforcement Learning on Natural Instructionscited by 0
  27. 2026A Survey of Reinforcement Learning for Large Language Models under Data Scarcity: Challenges and Solutionscited by 0
  28. 2026Entropy Centroids as Intrinsic Rewards for Test-Time Scalingcited by 0
  29. 2026GenCircuit-RL: Reinforcement Learning from Hierarchical Verification for Genetic Circuit Designcited by 0
  30. 2026RAG-Match: Retrieval-Augmented Knowledge Injection and Hierarchical Reasoning for Calibrated Semantic Relevancecited by 0
  31. 2026DenoiseRL: Bootstrapping Reasoning Models to Recover from Noisy Prefixescited by 0
  32. 2026SFBench: The SciFy Scientific Feasibility Benchmarkcited by 0
  33. 2026Cross-Domain Hybrid OPD for Generalizable Search Agentscited by 0
  34. 2026Reasoning Core: Designing Broad Procedural Data for Completion-Supervised Reasoning Trainingcited by 0
  35. 2026Curriculum Learning as Transport: Understanding Curricula with Wasserstein Geodesicscited by 0
  36. 2026Frontier Learning: Training LLM Reasoners at the Edge of Capabilitycited by 0
  37. 2026ResOPD: Tail Residualization for Sparse On-Policy Distillationcited by 0
  38. 2026Tev: Scaling Long-Horizon Agentic Environments with Dense Progress Rewardscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Revisiting Reinforcement Learning for LLM Reasoning from A Cross-Domain Perspective
  2. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
  3. 2025Logical Reasoning in Large Language Models: A Survey
  4. 2025VerifyBench: A Systematic Benchmark for Evaluating Reasoning Verifiers Across Domains
  5. 2025Enigmata: Scaling Logical Reasoning in Large Language Models with Synthetic Verifiable Puzzles
  6. 2025Scaling Up RL: Unlocking Diverse Reasoning in LLMs via Prolonged Training
  7. 2026Scaling the Scaling Logic: Agentic Meta-Synthesis of Logic Reasoning
  8. 2025RL Squeezes, SFT Expands: A Comparative Study of Reasoning LLMs