mlsanityData to 14 Oct 2026

REASONING GYM: Reasoning Environments for Reinforcement Learning with Verifiable Rewards

arXiv 2505.24760 ↗First posted 30 May 2025cs.LG cs.AI cs.CLcited by 130

Not on the map. Why?

Cited by 64 in LLM reasoning, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We introduce Reasoning Gym (RG), a library of reasoning environments for reinforcement learning with verifiable rewards. It provides over 100 data generators and verifiers spanning multiple domains including algebra, arithmetic, computation, cognition, geometry, graph theory, logic, and various common games. Its key innovation is the ability to generate virtually infinite training data with adjustable complexity, unlike most previous reasoning datasets, which are typically fixed. This procedural generation approach allows for continuous evaluation across varying difficulty levels. Our experimental results demonstrate the efficacy of RG in both evaluating and reinforcement learning of reasoning models.

Key facts. Cited by 130 papers in the map (data through 14 Oct 2026). Builds on 66 of its 92 references that are in the map. First posted on arXiv 30 May 2025.

Builds on

66 of 92 references.

References · 66

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  3. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  4. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  5. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,371
  6. 2024Qwen2.5 Technical Reportcited by 4,942
  7. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  8. 2016Overcoming catastrophic forgetting in neural networkscited by 4,787
  9. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,720
  10. 2023SWE-bench: Can Language Models Resolve Real-World GitHub Issues?cited by 3,373
  11. 2023GPQA: A Graduate-Level Google-Proof Q&A Benchmarkcited by 2,879
  12. 2020Learning to summarize from human feedbackcited by 2,588
38 more
  1. 2024LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Codecited by 2,004
  2. 2022Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language modelscited by 1,998
  3. 2017Gradient Episodic Memory for Continual Learningcited by 1,898
  4. 2024MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmarkcited by 1,848
  5. 2022Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Themcited by 1,807
  6. 2023Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generationcited by 1,391
  7. 2025Understanding R1-Zero-Like Training: A Critical Perspectivecited by 1,345
  8. 2024OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problemscited by 1,136
  9. 2024Tulu 3: Pushing Frontiers in Open Language Model Post-Trainingcited by 1,053
  10. 2017Deeper, Broader and Artier Domain Generalizationcited by 986
  11. 2025Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?cited by 982
  12. 2020Meta-Learning in Neural Networks: A Surveycited by 950
  13. 2020Dark Experience for General Continual Learning: a Strong, Simple Baselinecited by 911
  14. 2021Robust fine-tuning of zero-shot modelscited by 797
  15. 2021Domain Generalization: A Surveycited by 764
  16. 2023OpenAssistant Conversations -- Democratizing Large Language Model Alignmentcited by 721
  17. 2024BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructionscited by 546
  18. 2018Progress & Compress: A scalable framework for continual learningcited by 520
  19. 2019Leveraging Procedural Generation to Benchmark Reinforcement Learningcited by 483
  20. 2021Dynabench: Rethinking Benchmarking in NLPcited by 459
  21. 2025RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learningcited by 386
  22. 2018Dynamic Few-Shot Visual Learning without Forgettingcited by 385
  23. 2020Curriculum Learning for Reinforcement Learning Domains: A Framework and Surveycited by 373
  24. 2025Absolute Zero: Reinforced Self-play Reasoning with Zero Datacited by 344
  25. 2025Reinforcement Learning for Reasoning in Large Language Models with One Training Examplecited by 295
  26. 2018Human-level performance in first-person multiplayer games with population-based deep reinforcement learningcited by 264
  27. 2018Meta-Learning: A Surveycited by 256
  28. 2023Challenges and Applications of Large Language Modelscited by 254
  29. 2025Learning to Reason without External Rewardscited by 210
  30. 2025ZebraLogic: On the Scaling Limits of LLMs for Logical Reasoningcited by 201
  31. 2020The NetHack Learning Environmentcited by 198
  32. 2022Will we run out of data? Limits of LLM scaling based on human-generated datacited by 195
  33. 2024Are We Done with MMLU?cited by 194
  34. 2025ARC-AGI-2: A New Challenge for Frontier AI Reasoning Systemscited by 190
  35. 2025AIMO-2 Winning Solution: Building State-of-the-Art Mathematical Reasoning Models with OpenMathReasoning datasetcited by 174
  36. 2022Evolving Curricula with Regret-Based Environment Designcited by 173
  37. 2025Crossing the Reward Bridge: Expanding RL with Verifiable Rewards Across Diverse Domainscited by 156
  38. 2024BALROG: Benchmarking Agentic LLM and VLM Reasoning On Gamescited by 146

50 most cited of 66 All 66 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 36; 2026: 94.

130 papers.

Sort:

By area:

  1. 2025A Survey of Reinforcement Learning for Large Reasoning Modelscited by 180
  2. 2025The Invisible Leash: Why RLVR May or May Not Escape Its Origincited by 97
  3. 2025Reasoning or Memorization? Unreliable Results of Reinforcement Learning Due to Data Contaminationcited by 82
  4. 2026Expanding the Capabilities of Reinforcement Learning via Text Feedbackcited by 53
  5. 2025RLVE: Scaling Up Reinforcement Learning for Language Models with Adaptive Verifiable Environmentscited by 50
  6. 2026Nemotron 3 Super: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoningcited by 38
  7. 2026Maximum Likelihood Reinforcement Learningcited by 36
  8. 2025OptimalThinkingBench: Evaluating Over and Underthinking in LLMscited by 35
  9. 2025Evolution Strategies at Scale: LLM Fine-Tuning Beyond Reinforcement Learningcited by 34
  10. 2025BroRL: Scaling Reinforcement Learning via Broadened Explorationcited by 25
  11. 2025MedAgentGym: A Scalable Agentic Training Environment for Code-Centric Reasoning in Biomedical Data Sciencecited by 23
  12. 2025RL Grokking Recipe: How Does RL Unlock and Transfer New Algorithms in LLMs?cited by 23
38 more
  1. 2025GEM: A Gym for Agentic LLMscited by 23
  2. 2025Differential Smoothing Mitigates Sharpening and Improves LLM Reasoningcited by 22
  3. 2025Beyond Log Likelihood: Probability-Based Objectives for Supervised Fine-Tuning across the Model Capability Continuumcited by 18
  4. 2025A Comedy of Estimators: On KL Regularization in RL Training of LLMscited by 18
  5. 2025Scaling Agentic Reinforcement Learning for Tool-Integrated Reasoning in VLMscited by 17
  6. 2026MemoHarness: Agent Harnesses That Learn from Experiencecited by 16
  7. 2025From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligencecited by 15
  8. 2026On-Policy Delta Distillationcited by 15
  9. 2026Multi-Task GRPO: Reliable LLM Reasoning Across Taskscited by 14
  10. 2025Output Supervision Can Obfuscate the Chain of Thoughtcited by 13
  11. 2026SETA: Scaling Environments for Terminal Agentscited by 12
  12. 2026VisGym: Diverse, Customizable, Scalable Environments for Multimodal Agentscited by 11
  13. 2026Stable Asynchrony: Variance-Controlled Off-Policy RL for LLMscited by 11
  14. 2026Sequential Beats Joint: On the Interplay between On-Policy Distillation and RLVRcited by 11
  15. 2026Golden Goose: A Simple Trick to Synthesize Unlimited RLVR Tasks from Unverifiable Internet Textcited by 10
  16. 2026Analyzing and Improving Chain-of-Thought Monitorability Through Information Theorycited by 10
  17. 2025Seemingly Simple Planning Problems are Computationally Challenging: The Countdown Gamecited by 9
  18. 2025h1: Bootstrapping LLMs to Reason over Longer Horizons via Reinforcement Learningcited by 9
  19. 2025Beyond Pass@k: Breadth-Depth Metrics for Reasoning Boundariescited by 9
  20. 2025BeyondBench: Contamination-Resistant Evaluation of Reasoning in Language Modelscited by 8
  21. 2025Reasoning Curriculum: Bootstrapping Broad LLM Reasoning from Mathcited by 8
  22. 2026SCALER:Synthetic Scalable Adaptive Learning Environment for Reasoningcited by 8
  23. 2026Actor-Curator: Co-adaptive Curriculum Learning via Policy-Improvement Bandits for RL Post-Trainingcited by 8
  24. 2025What Can You Do When You Have Zero Rewards During RL?cited by 7
  25. 2025SSR: Socratic Self-Refine for Large Language Model Reasoningcited by 7
  26. 2026Steer2Adapt: Dynamically Composing Steering Vectors Elicits Efficient Adaptation of LLMscited by 7
  27. 2026Outcome Rewards Do Not Guarantee Verifiable or Causally Important Reasoningcited by 7
  28. 2026Delay, Plateau, or Collapse: Evaluating the Impact of Systematic Verification Error on RLVRcited by 7
  29. 2025BuilderBench: The Building Blocks of Intelligent Agentscited by 6
  30. 2025How Does RL Post-training Induce Skill Composition? A Case Study on Countdowncited by 6
  31. 2026Composition-RL: Compose Your Verifiable Prompts for Reinforcement Learning of Large Language Modelscited by 6
  32. 2026Learning from Synthetic Data Improves Multi-hop Reasoningcited by 6
  33. 2026ExecVerify: White-Box RL with Verifiable Stepwise Rewards for Code Execution Reasoningcited by 6
  34. 2026Learning, Fast and Slow: Towards LLMs That Adapt Continuallycited by 6
  35. 2025Reasoning Core: A Scalable RL Environment for LLM Symbolic Reasoningcited by 5
  36. 2025AutoBaxBuilder: Bootstrapping Code Security Benchmarkingcited by 5
  37. 2026ReSyn: Autonomously Scaling Synthetic Environments for Reasoning Modelscited by 5
  38. 2026Multilingual Reasoning Gym: Multilingual Scaling of Procedural Reasoning Environmentscited by 5

50 most cited of 130 All 130 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024PUZZLES: A Benchmark for Neural Algorithmic Reasoning
  2. 2026SARL: Label-Free Reinforcement Learning by Rewarding Reasoning Topology
  3. 2026Reasoning Arena: Trace Tournaments When Verifiable Rewards Fall Short
  4. 2026SUPERNOVA: Eliciting General Reasoning in LLMs with Reinforcement Learning on Natural Instructions
  5. 2026Reasoning Depth and Environment Complexity: A Controlled Study of RLVR Data Allocation across Logical Reasoning Tasks
  6. 2026Select and Improve: Understanding the Mechanics of Post-Training for Reasoning
  7. 2025Limits of Generalization in RLVR: Two Case Studies in Mathematical Reasoning
  8. 2026A Primer in Post-Training Reasoning Data: What We Know About How It Works