mlsanityData to 14 Oct 2026

REAMS: Reasoning Enhanced Algorithm for Maths Solving

arXiv 2509.16241 ↗First posted 16 Sep 2025cs.CL cs.AI cs.PLcited by 0

Not on the map. Why?

Abstract (arXiv)

The challenges of solving complex university-level mathematics problems, particularly those from MIT, and Columbia University courses, and selected tasks from the MATH dataset, remain a significant obstacle in the field of artificial intelligence. Conventional methods have consistently fallen short in this domain, highlighting the need for more advanced approaches. In this paper, we introduce a language-based solution that leverages zero-shot learning and mathematical reasoning to effectively solve, explain, and generate solutions for these advanced math problems. By integrating program synthesis, our method reduces reliance on large-scale training data while significantly improving problem-solving accuracy. Our approach achieves an accuracy of 90.15%, representing a substantial improvement over the previous benchmark of 81% and setting a new standard in automated mathematical problem-solving. These findings highlight the significant potential of advanced AI methodologies to address and overcome the challenges presented by some of the most complex mathematical courses and datasets.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 9 of its 12 references that are in the map. First posted on arXiv 16 Sep 2025.

Builds on

9 of 12 references.

References · 9

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  3. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,371
  4. 2022Large Language Models are Zero-Shot Reasonerscited by 4,374
  5. 2022Solving Quantitative Reasoning Problems with Language Modelscited by 1,392
  6. 2021MiniF2F: a cross-system benchmark for formal Olympiad-level mathematicscited by 391
  7. 2021A Neural Network Solves, Explains, and Generates University Math Problems by Program Synthesis and Few-Shot Learning at Human Levelcited by 96
  8. 2024Dual Instruction Tuning with Large Language Models for Mathematical Reasoningcited by 10
  9. 2021Solving Machine Learning Problemscited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025A Survey on Mathematical Reasoning and Optimization with Large Language Models
  2. 2026Artificial Intelligence for Mathematical Reasoning: An Integrated Survey of Language Models, Neuro-symbolic Systems, and Verified Discovery
  3. 2025UGMathBench: A Diverse and Dynamic Benchmark for Undergraduate-Level Mathematical Reasoning with Large Language Models
  4. 2026MathMixup: Boosting LLM Mathematical Reasoning with Difficulty-Controllable Data Synthesis and Curriculum Learning
  5. 2024Mathematics and Machine Creativity: A Survey on Bridging Mathematics with AI
  6. 2025A Survey on Large Language Models for Mathematical Reasoning
  7. 2026Mathematical Reasoning in Large Language Models: Benchmarks, Architectures, Evaluation, and Open Challenges
  8. 2025Mathematical Computation and Reasoning Errors by Large Language Models