mlsanityData to 7 Oct 2026

MARIO: MAth Reasoning with code Interpreter Output -- A Reproducible Pipeline

arXiv 2401.08190 ↗First posted 16 Jan 2024cs.CLcited by 81

On the map: LLM reasoning → Mathematical reasoning

Abstract (arXiv)

Large language models (LLMs) have seen considerable advancements in natural language understanding tasks, yet there remains a gap to bridge before attaining true artificial general intelligence, especially concerning shortcomings in mathematical reasoning capabilities. We postulate that the inherent nature of LLM training, which focuses on predicting probabilities of next token, presents challenges in effectively modeling mathematical reasoning that demands exact calculations, both from data-driven and theoretical standpoints. In this paper, we address this challenge by enriching the data landscape and introducing a novel math dataset, enhanced with a capability to utilize a Python code interpreter. This dataset is derived from GSM8K and MATH and has been further refined through a combination of GPT-4 annotations, human review, and self-training processes, where the errors in the original GSM8K training set have been fixed. Additionally, we propose a tentative, easily replicable protocol for the fine-tuning of math-specific LLMs, which has led to a significant improvement in the performance of a 7B-parameter LLM on the GSM8K and MATH datasets. We are committed to advancing the field of mathematical reasoning in LLMs and, to that end, we have made source code for data generation / training / inference, and the model checkpoints publicly available at urlhttps://github.com/MARIO-Math-Reasoning/MARIO. We hope this will facilitate further research and development within the community.

Key facts. Cited by 81 papers in the map (data through 7 Oct 2026). Placed in Mathematical reasoning, one of 17 directions in LLM reasoning. Builds on 35 of its 42 references that are in the map. First posted on arXiv 16 Jan 2024.

Builds on

35 of 42 references.

Closest ancestors · 7

Same direction, newest first

  1. 2023Llemma: An Open Language Model For Mathematics16 Oct
  2. 2023MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning5 Oct
  3. 2023ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving29 Sep
  4. 2023WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct18 Aug
  5. 2023Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verification15 Aug
  6. 2023Scaling Relationship on Learning Mathematical Reasoning with Large Language Models3 Aug
  7. 2022Solving Quantitative Reasoning Problems with Language Models29 Jun

Other references · 28

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  3. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  4. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  5. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  6. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  7. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  8. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  9. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,203
  10. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
  11. 2023Let's Verify Step by Stepcited by 3,598
  12. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,317
16 more
  1. 2023FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioningcited by 2,551
  2. 2023Code Llama: Open Foundation Models for Codecited by 2,105
  3. 2020Knowledge Distillation: A Surveycited by 1,578
  4. 2023PaLM 2 Technical Reportcited by 1,154
  5. 2022Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Taskscited by 1,057
  6. 2023MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Modelscited by 724
  7. 2022PAL: Program-aided Language Modelscited by 635
  8. 2023MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuningcited by 483
  9. 2022Large Language Models Are Reasoning Teacherscited by 318
  10. 2022Large Language Models are Better Reasoners with Self-Verificationcited by 304
  11. 2021ZeRO-Infinity: Breaking the GPU Memory Wall for Extreme Scale Deep Learningcited by 253
  12. 2023Specializing Smaller Language Models towards Multi-Step Reasoningcited by 249
  13. 2023Skywork: A More Open Bilingual Foundation Modelcited by 110
  14. 2023GPT Can Solve Mathematical Problems Without a Calculatorcited by 68
  15. 2023GRACE: Discriminator-Guided Chain-of-Thought Reasoningcited by 35
  16. 2022Chaining Simultaneous Thoughts for Numerical Reasoningcited by 14

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 16; 2025: 42; 2026: 23.

81 papers.

Sort:

By area:

  1. 2024Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvementcited by 1,057
  2. 2025The Lessons of Developing Process Reward Models in Mathematical Reasoningcited by 402
  3. 2025Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Modelscited by 381
  4. 2025ToolRL: Reward is All Tool Learning Needscited by 342
  5. 2025rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinkingcited by 308
  6. 2024Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMscited by 265
  7. 2025ToRL: Scaling Tool-Integrated RLcited by 166
  8. 2025AIMO-2 Winning Solution: Building State-of-the-Art Mathematical Reasoning Models with OpenMathReasoning datasetcited by 165
  9. 2024AlphaMath Almost Zero: Process Supervision without Processcited by 160
  10. 2024OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Datasetcited by 143
  11. 2025Reward-Guided Speculative Decoding for Efficient LLM Reasoningcited by 106
  12. 2024DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solvingcited by 92
38 more
  1. 2024LLaMA-Berry: Pairwise Optimization for O1-like Olympiad-Level Mathematical Reasoningcited by 90
  2. 2024AceMath: Advancing Frontier Math Reasoning with Post-Training and Reward Modelingcited by 76
  3. 2024Step-level Value Preference Optimization for Mathematical Reasoningcited by 71
  4. 2025Ego-R1: Chain-of-Tool-Thought for Ultra-Long Egocentric Video Reasoningcited by 67
  5. 2025ReasonFlux: Hierarchical LLM Reasoning via Scaling Thought Templatescited by 62
  6. 2025Visual Agentic Reinforcement Fine-Tuningcited by 53
  7. 2025Code to Think, Think to Code: A Survey on Code-Enhanced Reasoning and Reasoning-Driven Code Intelligence in LLMscited by 47
  8. 2024JiuZhang3.0: Efficiently Improving Mathematical Reasoning by Training Small Data Synthesis Modelscited by 44
  9. 2025Scaling Laws of Synthetic Data for Language Modelscited by 44
  10. 2025Solver-Informed RL: Grounding Large Language Models for Authentic Optimization Modelingcited by 44
  11. 2024MathCoder2: Better Math Reasoning from Continued Pretraining on Model-translated Mathematical Codecited by 39
  12. 2025S2R: Teaching LLMs to Self-verify and Self-correct via Reinforcement Learningcited by 37
  13. 2025Demystifying Reinforcement Learning in Agentic Reasoningcited by 32
  14. 2025To Code or not to Code? Adaptive Tool Integration for Math Language Models via Expectation-Maximizationcited by 25
  15. 2024An LLM Agent for Automatic Geospatial Data Analysiscited by 21
  16. 2025Process-based Self-Rewarding Language Modelscited by 21
  17. 2026SCRIBE: Structured Mid-Level Supervision for Tool-Using Language Modelscited by 20
  18. 2024Markov Chain of Thought for Efficient Mathematical Reasoningcited by 19
  19. 2025Towards Concise and Adaptive Thinking in Large Reasoning Models: A Surveycited by 18
  20. 2024Search, Verify and Feedback: Towards Next Generation Post-training Paradigm of Foundation Models via Verifier Engineeringcited by 16
  21. 2024MARIO Eval: Evaluate Your Math LLM with your Math LLM--A mathematical dataset evaluation toolkitcited by 14
  22. 2025Full-Step-DPO: Self-Supervised Preference Optimization with Step-wise Rewards for Mathematical Reasoningcited by 14
  23. 2025Linking Process to Outcome: Conditional Reward Modeling for LLM Reasoningcited by 14
  24. 2025Better Process Supervision with Bi-directional Rewarding Signalscited by 12
  25. 2026AgentV-RL: Scaling Reward Modeling with Agentic Verifiercited by 12
  26. 2025A Survey on Feedback-based Multi-step Reasoning for Large Language Models on Mathematicscited by 11
  27. 2025Rectified Sparse Attentioncited by 10
  28. 2025Omni-Thinker: Scaling Multi-Task RL in LLMs with Hybrid Reward and Task Schedulingcited by 9
  29. 2025ResT: Reshaping Token-Level Policy Gradients for Tool-Use Large Language Modelscited by 9
  30. 2025Orthogonal Finetuning Made Scalablecited by 7
  31. 2025Reward Models Identify Consistency, Not Causalitycited by 6
  32. 2025Towards Better Understanding of Program-of-Thought Reasoning in Cross-Lingual and Multilingual Environmentscited by 6
  33. 2025MetaLadder: Ascending Mathematical Solution Quality via Analogical-Problem Reasoning Transfercited by 6
  34. 2024GeoCoder: Solving Geometry Problems by Generating Modular Code through Vision-Language Modelscited by 5
  35. 2025Layer-Aware Task Arithmetic: Disentangling Task-Specific and Instruction-Following Knowledgecited by 5
  36. 2025Supervised Optimism Correction: Be Confident When LLMs Are Surecited by 5
  37. 2025ASyMOB: Algebraic Symbolic Mathematical Operations Benchmarkcited by 5
  38. 2026LycheeDecode: Accelerating Long-Context LLM Inference via Hybrid-Head Sparse Decodingcited by 5

50 most cited of 81 All 81 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Mathematical Reasoning in Large Language Models: Assessing Logical and Arithmetic Errors across Wide Numerical Ranges
  2. 2025Do LLMs Overthink Basic Math Reasoning? Benchmarking the Accuracy-Efficiency Tradeoff in Language Models
  3. 2024GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models
  4. 2026Mathematical Reasoning in Large Language Models: Benchmarks, Architectures, Evaluation, and Open Challenges
  5. 2024Assessing the Emergent Symbolic Reasoning Abilities of Llama Large Language Models
  6. 2025Can LLMs textitunderstand Math? -- Exploring the Pitfalls in Mathematical Reasoning
  7. 2024ReasonAgain: Using Extractable Symbolic Programs to Evaluate Mathematical Reasoning
  8. 2025Thinking Machines: Mathematical Reasoning in the Age of LLMs