mlsanityData to 7 Oct 2026

Reasoning Curriculum: Bootstrapping Broad LLM Reasoning from Math

arXiv 2510.26143 ↗First posted 30 Oct 2025cs.AI cs.CLcited by 8

On the map: LLM reasoning → Reinforcement learning for reasoning

also in 1 more
Abstract (arXiv)

Reinforcement learning (RL) can elicit strong reasoning in large language models (LLMs), yet most open efforts focus on math and code. We propose Reasoning Curriculum, a simple two-stage curriculum that first elicits reasoning skills in pretraining-aligned domains such as math, then adapts and refines these skills across other domains via joint RL. Stage 1 performs a brief cold start and then math-only RL with verifiable rewards to develop reasoning skills. Stage 2 runs joint RL on mixed-domain data to transfer and consolidate these skills. The curriculum is minimal and backbone-agnostic, requiring no specialized reward models beyond standard verifiability checks. Evaluated on Qwen3-4B and Llama-3.1-8B over a multi-domain suite, reasoning curriculum yields consistent gains. Ablations and a cognitive-skill analysis indicate that both stages are necessary and that math-first elicitation increases cognitive behaviors important for solving complex problems. Reasoning Curriculum provides a compact, easy-to-adopt recipe for general reasoning.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Placed in Reinforcement learning for reasoning, one of 17 directions in LLM reasoning. Builds on 27 of its 41 references that are in the map. First posted on arXiv 30 Oct 2025.

Builds on

27 of 41 references.

Closest ancestors · 8

Same direction, newest first

  1. 2025Revisiting Reinforcement Learning for LLM Reasoning from A Cross-Domain Perspective17 Jun
  2. 2025Reinforcement Learning for Reasoning in Large Language Models with One Training Example29 Apr
  3. 2025Nemotron-CrossThink: Scaling Self-Learning beyond Math Reasoning15 Apr
  4. 2025Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model31 Mar
  5. 2025SimpleRL-Zoo: Investigating and Taming Zero Reinforcement Learning for Open Base Models in the Wild24 Mar
  6. 2025DAPO: An Open-Source LLM Reinforcement Learning System at Scale18 Mar
  7. 2025Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRs3 Mar
  8. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning22 Jan

Other references · 19

  1. 2024The Llama 3 Herd of Modelscited by 14,192
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  3. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
  4. 2025Qwen3 Technical Reportcited by 8,195
  5. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  6. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,203
  7. 2021Program Synthesis with Large Language Modelscited by 3,509
  8. 2023GPQA: A Graduate-Level Google-Proof Q&A Benchmarkcited by 2,748
  9. 2024HybridFlow: A Flexible and Efficient RLHF Frameworkcited by 1,980
  10. 2024LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Codecited by 1,906
  11. 2017Decoupled Weight Decay Regularizationcited by 1,722
  12. 2021FinQA: A Dataset of Numerical Reasoning over Financial Datacited by 552
7 more
  1. 2024CRUXEval: A Benchmark for Code Reasoning, Understanding and Executioncited by 294
  2. 2025ZebraLogic: On the Scaling Limits of LLMs for Logical Reasoningcited by 186
  3. 2025REASONING GYM: Reasoning Environments for Reinforcement Learning with Verifiable Rewardscited by 121
  4. 2022MultiHiertt: Numerical Reasoning over Multi Hierarchical Tabular and Textual Datacited by 120
  5. 2021HiTab: A Hierarchical Table Dataset for Question Answering and Natural Language Generationcited by 117
  6. 2025SuperGPQA: Scaling LLM Evaluation across 285 Graduate Disciplinescited by 67
  7. 2025CodeI/O: Condensing Reasoning Patterns via Code Input-Output Predictioncited by 54

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 8.

8 papers.

  1. 2026Multi-Task GRPO: Reliable LLM Reasoning Across Taskscited by 12
  2. 2026Transferability for General Reasoning: An Automated Curriculum for Multi-Domain RLVRcited by 4
  3. 2026Harmony in Diversity: Multi-domain Contrastive Policy Optimization for Large Reasoning Modelscited by 2
  4. 2026Theory-Level Autoformalization: From Isolated Statements to Unified Formal Knowledge Basescited by 1
  5. 2026M2A: Synergizing Mathematical and Agentic Reasoning in Large Language Modelscited by 0
  6. 2026Internalizing Curriculum Judgment for LLM Reinforcement Fine-Tuningcited by 0
  7. 2026SCOPE-RL: Optimizing Reasoning Paths Before and After Successcited by 0
  8. 2026Toward Skill-Native LLMs: Skill Entropy for Benchmarking and Training Long-Horizon Reasoningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Curriculum Reinforcement Learning from Easy to Hard Tasks Improves LLM Reasoning
  2. 2025h1: Bootstrapping LLMs to Reason over Longer Horizons via Reinforcement Learning
  3. 2025Self-Evolving Curriculum for LLM Reasoning
  4. 2026Curriculum Reinforcement Learning Can Incentivize Reasoning Capacity in LLMs Beyond the Base Model
  5. 2025Provable Benefit of Curriculum in Transformer Tree-Reasoning Post-Training
  6. 2026From Reasoning Chains to Verifiable Subproblems: Curriculum Reinforcement Learning Enables Credit Assignment for LLM Reasoning
  7. 2025VCRL: Variance-based Curriculum Reinforcement Learning for Large Language Models
  8. 2025Does Math Reasoning Improve General LLM Capabilities? Understanding Transferability of LLM Reasoning