mlsanityData to 7 Oct 2026

SEGO: Sequential Subgoal Optimization for Mathematical Problem-Solving

arXiv 2310.12960 ↗First posted 19 Oct 2023cs.CLcited by 1

Not on the map. Why?

Abstract (arXiv)

Large Language Models (LLMs) have driven substantial progress in artificial intelligence in recent years, exhibiting impressive capabilities across a wide range of tasks, including mathematical problem-solving. Inspired by the success of subgoal-based methods, we propose a novel framework called SEquential subGoal Optimization (SEGO) to enhance LLMs' ability to solve mathematical problems. By establishing a connection between the subgoal breakdown process and the probability of solving problems, SEGO aims to identify better subgoals with theoretical guarantees. Addressing the challenge of identifying suitable subgoals in a large solution space, our framework generates problem-specific subgoals and adjusts them according to carefully designed criteria. Incorporating these optimized subgoals into the policy model training leads to significant improvements in problem-solving performance. We validate SEGO's efficacy through experiments on two benchmarks, GSM8K and MATH, where our approach outperforms existing methods, highlighting the potential of SEGO in AI-driven mathematical problem-solving. Data and code associated with this paper will be available at https://github.com/zhaoxlpku/SEGO

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 42 of its 54 references that are in the map. First posted on arXiv 19 Oct 2023.

Builds on

42 of 54 references.

References · 42

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  3. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  4. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  5. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  6. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  7. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  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. 2018Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challengecited by 4,710
  11. 2023Let's Verify Step by Stepcited by 3,598
  12. 2019The Curious Case of Neural Text Degenerationcited by 2,881
30 more
  1. 2023Code Llama: Open Foundation Models for Codecited by 2,105
  2. 2018CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledgecited by 1,793
  3. 2016Variational Inference: A Review for Statisticianscited by 1,466
  4. 2022Least-to-Most Prompting Enables Complex Reasoning in Large Language Modelscited by 1,397
  5. 2022Solving Quantitative Reasoning Problems with Language Modelscited by 1,359
  6. 2023PaLM 2 Technical Reportcited by 1,154
  7. 2022Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Taskscited by 1,057
  8. 2021Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategiescited by 736
  9. 2017Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problemscited by 642
  10. 2023WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instructcited by 618
  11. 2023LLM+P: Empowering Large Language Models with Optimal Planning Proficiencycited by 496
  12. 2023MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuningcited by 483
  13. 2022Complexity-Based Prompting for Multi-Step Reasoningcited by 387
  14. 2019Search on the Replay Buffer: Bridging Planning and Reinforcement Learningcited by 188
  15. 2023Progressive-Hint Prompting Improves Reasoning in Large Language Modelscited by 147
  16. 2021Goal-Conditioned Reinforcement Learning with Imagined Subgoalscited by 129
  17. 2020Maximum Entropy Gain Exploration for Long Horizon Multi-goal Reinforcement Learningcited by 100
  18. 2021A Neural Network Solves, Explains, and Generates University Math Problems by Program Synthesis and Few-Shot Learning at Human Levelcited by 96
  19. 2020Automatic Curriculum Learning through Value Disagreementcited by 86
  20. 2021Asymmetric self-play for automatic goal discovery in robotic manipulationcited by 71
  21. 2019Dynamical Distance Learning for Semi-Supervised and Unsupervised Skill Discoverycited by 65
  22. 2021MWPToolkit: An Open-Source Framework for Deep Learning-Based Math Word Problem Solverscited by 39
  23. 2022Learning Math Reasoning from Self-Sampled Correct and Partially-Correct Solutionscited by 38
  24. 2023Decomposing the Enigma: Subgoal-based Demonstration Learning for Formal Theorem Provingcited by 37
  25. 2019Discovering Options for Exploration by Minimizing Cover Timecited by 30
  26. 2020Divide-and-Conquer Monte Carlo Tree Search For Goal-Directed Planningcited by 19
  27. 2018Finding Options that Minimize Planning Timecited by 17
  28. 2021Computational Benefits of Intermediate Rewards for Goal-Reaching Policy Learningcited by 17
  29. 2022Phasic Self-Imitative Reduction for Sparse-Reward Goal-Conditioned Reinforcement Learningcited by 16
  30. 2021C-Planning: An Automatic Curriculum for Learning Goal-Reaching Taskscited by 15

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Scaling Reasoning without Attentioncited by 3