mlsanityData to 14 Oct 2026

Confucius3-Math: A Lightweight High-Performance Reasoning LLM for Chinese K-12 Mathematics Learning

arXiv 2506.18330 ↗First posted 23 Jun 2025cs.LG cs.AI cs.CLcited by 5

On the map: LLM reasoning → Reinforcement learning for reasoning

Abstract (arXiv)

We introduce Confucius3-Math, an open-source large language model with 14B parameters that (1) runs efficiently on a single consumer-grade GPU; (2) achieves SOTA performances on a range of mathematical reasoning tasks, outperforming many models with significantly larger sizes. In particular, as part of our mission to enhancing education and knowledge dissemination with AI, Confucius3-Math is specifically committed to mathematics learning for Chinese K-12 students and educators. Built via post-training with large-scale reinforcement learning (RL), Confucius3-Math aligns with national curriculum and excels at solving main-stream Chinese K-12 mathematical problems with low cost. In this report we share our development recipe, the challenges we encounter and the techniques we develop to overcome them. In particular, we introduce three technical innovations: Targeted Entropy Regularization, Recent Sample Recovery and Policy-Specific Hardness Weighting. These innovations encompass a new entropy regularization, a novel data scheduling policy, and an improved group-relative advantage estimator. Collectively, they significantly stabilize the RL training, improve data efficiency, and boost performance. Our work demonstrates the feasibility of building strong reasoning models in a particular domain at low cost. We open-source our model and code at https://github.com/netease-youdao/Confucius3-Math.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Placed in Reinforcement learning for reasoning, one of 17 directions in LLM reasoning. Builds on 25 of its 34 references that are in the map. First posted on arXiv 23 Jun 2025.

Builds on

25 of 34 references.

Closest ancestors · 6

Same direction, newest first

  1. 2025DUMP: Automated Distribution-Level Curriculum Learning for RL-based LLM Post-training13 Apr
  2. 2025Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model31 Mar
  3. 2025Understanding R1-Zero-Like Training: A Critical Perspective26 Mar
  4. 2025DAPO: An Open-Source LLM Reinforcement Learning System at Scale18 Mar
  5. 2025LIMR: Less is More for RL Scaling17 Feb
  6. 2017Proximal Policy Optimization Algorithms20 Jul

Other references · 19

  1. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  2. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  3. 2025Qwen3 Technical Reportcited by 8,820
  4. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,371
  5. 2025s1: Simple test-time scalingcited by 1,341
  6. 2024Large Language Monkeys: Scaling Inference Compute with Repeated Samplingcited by 991
  7. 2025LIMO: Less is More for Reasoningcited by 498
  8. 2023Evaluating the Performance of Large Language Models on GAOKAO Benchmarkcited by 186
  9. 2018Understanding the impact of entropy on policy optimizationcited by 176
  10. 2025Skywork Open Reasoner 1 Technical Reportcited by 165
  11. 2024O1 Replication Journey: A Strategic Progress Report -- Part 1cited by 143
  12. 2024MathBench: Evaluating the Theory and Application Proficiency of LLMs with a Hierarchical Mathematics Benchmarkcited by 105
7 more
  1. 2023To Repeat or Not To Repeat: Insights from Scaling LLM under Token-Crisiscited by 92
  2. 2021Scaling Scaling Laws with Board Gamescited by 63
  3. 2017Safe and Nested Subgame Solving for Imperfect-Information Gamescited by 41
  4. 2024Mitigating the Language Mismatch and Repetition Issues in LLM-based Machine Translation via Model Editingcited by 18
  5. 2020Revisiting Maximum Entropy Inverse Reinforcement Learning: New Perspectives and Algorithmscited by 10
  6. 2024Embracing AI in Education: Understanding the Surge in Large Language Model Use by Secondary Studentscited by 5
  7. 2024Shaping AI's Impact on Billions of Livescited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 3.

5 papers.

  1. 2025A Survey of Reinforcement Learning for Large Reasoning Modelscited by 180
  2. 2025UloRL:An Ultra-Long Output Reinforcement Learning Approach for Advancing Large Language Models' Reasoning Abilitiescited by 11
  3. 2026GanitLLM: Difficulty-Aware Bengali Mathematical Reasoning through Curriculum-GRPOcited by 6
  4. 2026PA3: Policy-Aware Agent Alignment through Chain-of-Thoughtcited by 4
  5. 2026OmniEdu: Open Foundation Models for Learning and Teachingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Big-Math: A Large-Scale, High-Quality Math Dataset for Reinforcement Learning in Language Models
  2. 2026One Sample to Rule Them All: Extreme Data Efficiency in Multidiscipline Reasoning with Reinforcement Learning
  3. 2025Scaling Up RL: Unlocking Diverse Reasoning in LLMs via Prolonged Training
  4. 2025MATH-Beyond: A Benchmark for RL to Expand Beyond the Base Model
  5. 2025LogicPuzzleRL: Cultivating Robust Mathematical Reasoning in LLMs via Reinforcement Learning
  6. 2025DeepMath-103K: A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning
  7. 2025JT-Math: A Multi-Stage Framework for Advanced Mathematical Reasoning in Large Language Models
  8. 2024Multi-Step Reasoning with Large Language Models, a Survey