Lune

ACL Findings2025

Problem-Solving Logic Guided Curriculum In-Context Learning for LLMs Complex Reasoning

Xuetao Ma, Wenbin Jiang, Hua Huang

Abstract

In-context learning (ICL) can significantly enhance the complex reasoning capabilities of large language models (LLMs), with the key lying in the selection and ordering of demonstration examples. Previous methods typically relied on simple features to measure the relevance between examples. We argue that these features are not sufficient to reflect the intrinsic connections between examples. In this study, we propose a curriculum ICL strategy guided by problem-solving logic. We select demonstration examples by analyzing the problemsolving logic and order them based on curriculum learning. Specifically, we constructed a problem-solving logic instruction set based on the BREAK dataset and fine-tuned a language model to analyze the problem-solving logic of examples. Subsequently, we selected appropriate demonstration examples based on problem-solving logic and assessed their difficulty according to the number of problemsolving steps. In accordance with the principles of curriculum learning, we ordered the examples from easy to hard to serve as contextual prompts. Experimental results on multiple benchmarks indicate that our method outperforms previous ICL approaches in terms of performance and efficiency, effectively enhancing the complex reasoning capabilities of LLMs. Our project will be released at https: //github.com/maxuetao/CurriculumICL

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

4 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Tree of Thoughts: Deliberate Problem Solving with Large Language Models cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
  • Dynamic Cognitive Planning for Cognitive-Functional Dialogue: A Case Study in Emotional Support Conversation cites Tree of Thoughts: Deliberate Problem Solving with Large Language Models
  • Dynamic Cognitive Planning for Cognitive-Functional Dialogue: A Case Study in Emotional Support Conversation cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
  • UORA: Uniform Orthogonal Reinitialization Adaptation in Parameter Efficient Fine-Tuning of Large Models cites LoRA: Low-Rank Adaptation of Large Language Models
  • A Survey on In-context Learning cites Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity
  • A Survey on In-context Learning cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers4

  1. UORA: Uniform Orthogonal Reinitialization Adaptation in Parameter Efficient Fine-Tuning of Large ModelsXueyan Zhang, Jinman Zhao, Zhifei Yang, Yibo Zhong et al.ACL 2025 · 15 citations
  2. Process-Supervised Reinforcement Learning for Code GenerationYufan Ye, Ting Zhang, Wenbin Jiang, Hua HuangEMNLP 2025 · 1 citation
  3. SMART: Evaluating LLMs' Mathematical Reasoning via a Human Cognitive Process-Inspired BenchmarkYujie Hou, Mei Wang, Yaoyao Zhong, Ting Zhang et al.ACL 2026
  4. Dynamic Cognitive Planning for Cognitive-Functional Dialogue: A Case Study in Emotional Support ConversationJiaqi Liu, Yankun Yang, Jiakang Xu, Zhongqiang Du et al.AAAI 2026

Builds on25

  1. Chain-of-Thought Prompting Elicits Reasoning in Large Language ModelsJason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma et al.NeurIPS 2022 · 22,562 citations
  2. LoRA: Low-Rank Adaptation of Large Language ModelsEdward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu et al.ICLR 2022 · 18,833 citations
  3. Tree of Thoughts: Deliberate Problem Solving with Large Language ModelsShunyu Yao, Dian Yu, Jeffrey Zhao, Izhak Shafran et al.NeurIPS 2023 · 5,068 citations
  4. Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order SensitivityYao Lu, Max Bartolo, Alastair Moore, Sebastian Riedel et al.ACL 2022 · 1,494 citations
  5. A Survey on In-context LearningQingxiu Dong, Lei Li, Damai Dai, Ce Zheng et al.EMNLP 2024 · 479 citations

Related papers

  1. The Impact of Reasoning Step Length on Large Language ModelsMingyu Jin, Qinkai Yu, Dong Shu, Haiyan Zhao et al.ACL Findings 2024 · 39 citations
  2. Let's Be Self-generated via Step by Step: A Curriculum Learning Approach to Automated Reasoning with Large Language ModelsKangyang Luo, Zichen Ding, Zhenmin Weng, Lingfeng Qiao et al.ACL Findings 2025 · 1 citation
  3. Chain-of-Quizzes: Pedagogy-inspired Example Selection in In-Context-LearningYiquan Wu, Anlai Zhou, Yuhang Liu, Yifei Liu et al.ACL Findings 2024
  4. What Makes a Good Curriculum? Disentangling the Effects of Data Ordering on LLM Mathematical ReasoningYaning Jia, Chunhui Zhang, Xingjian Diao, Xiangchi Yuan et al.ACL 2026 · 4 citations
  5. GraphIC: A Graph-Based In-Context Example Retrieval Model for Multi-Step ReasoningJiale Fu, Yaqing Wang, Simeng Han, Jiaming Fan et al.AAAI 2026 · 3 citations
Dusk over the sea between two cliffs drawn in fine vertical lines