mlsanityData to 7 Oct 2026

Enhancing Mathematical Problem Solving in LLMs through Execution-Driven Reasoning Augmentation

arXiv 2602.03950 ↗First posted 3 Feb 2026cs.AI cs.LG cs.MAcited by 0

On the map: LLM reasoning → Mathematical reasoning

Abstract (arXiv)

Mathematical problem solving is a fundamental benchmark for assessing the reasoning capabilities of artificial intelligence and a gateway to applications in education, science, and engineering where reliable symbolic reasoning is essential. Although recent advances in multi-agent LLM-based systems have enhanced their mathematical reasoning capabilities, they still lack a reliably revisable representation of the reasoning process. Existing agents either operate in rigid sequential pipelines that cannot correct earlier steps or rely on heuristic self-evaluation that can fail to identify and fix errors. In addition, programmatic context can distract language models and degrade accuracy. To address these gaps, we introduce Iteratively Improved Program Construction (IIPC), a reasoning method that iteratively refines programmatic reasoning chains and combines execution feedback with the native Chain-of-thought abilities of the base LLM to maintain high-level contextual focus. IIPC surpasses competing approaches in the majority of reasoning benchmarks on multiple base LLMs. All code and implementations are released as open source.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Mathematical reasoning, one of 17 directions in LLM reasoning. Builds on 21 of its 32 references that are in the map. First posted on arXiv 3 Feb 2026.

Builds on

21 of 32 references.

Closest ancestors · 3

Same direction, newest first

  1. 2025How Is LLM Reasoning Distracted by Irrelevant Context? An Analysis Using a Controlled Benchmark24 May
  2. 2025A Survey on Mathematical Reasoning and Optimization with Large Language Models22 Mar
  3. 2023Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verification15 Aug

Other references · 18

  1. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  2. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  3. 2022Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Taskscited by 1,057
  4. 2023Large Language Models Cannot Self-Correct Reasoning Yetcited by 965
  5. 2023Large Language Models Can Be Easily Distracted by Irrelevant Contextcited by 820
  6. 2022PAL: Program-aided Language Modelscited by 635
  7. 2025Why Do Multi-Agent LLM Systems Fail?cited by 559
  8. 2024OpenCodeInterpreter: Integrating Code Generation with Execution and Refinementcited by 242
  9. 2024LLM-SR: Scientific Equation Discovery via Programming with Large Language Modelscited by 117
  10. 2023Cumulative Reasoning with Large Language Modelscited by 94
  11. 2024Agents Thinking Fast and Slow: A Talker-Reasoner Architecturecited by 35
  12. 2024LLMPhy: Parameter-Identifiable Physical Reasoning Combining Large Language Models and Physics Enginescited by 29
6 more
  1. 2025Beyond Final Answers: Evaluating Large Language Models for Math Tutoringcited by 23
  2. 2024When Large Language Model Meets Optimizationcited by 22
  3. 2024Reasoning Through Execution: Unifying Process and Outcome Rewards for Code Generationcited by 21
  4. 2025One Size doesn't Fit All: A Personalized Conversational Tutoring Agent for Mathematics Instructioncited by 17
  5. 2025Execution Guided Line-by-Line Code Generationcited by 10
  6. 2025Evaluating Large Language Models for Financial Reasoning: A CFA-Based Benchmark Studycited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025OR-LLM-Agent: Automating Modeling and Solving of Operations Research Optimization Problems with Reasoning LLM
  2. 2026From Atomic to Agentic: Towards Interpretable Evaluation of LLMs' Agentic Mathematical Capabilities
  3. 2026Rethinking Math Reasoning Evaluation: A Robust LLM-as-a-Judge Framework Beyond Symbolic Rigidity
  4. 2025Thinking Machines: Mathematical Reasoning in the Age of LLMs
  5. 2025Teaching LLMs According to Their Aptitude: Adaptive Reasoning for Mathematical Problem Solving
  6. 2026Mathematical Reasoning in Large Language Models: Benchmarks, Architectures, Evaluation, and Open Challenges
  7. 2025Evaluating Intermediate Reasoning of Code-Assisted Large Language Models for Mathematics
  8. 2023Modeling Complex Mathematical Reasoning via Large Language Model based MathAgent